{"benchmark_count":56,"benchmark_coverage":{"aa-intelligence-index":{"conflict":0,"contamination_warning":0,"directly_comparable":28,"exact":28,"measured_models":28,"other_supplemental":0,"total_models":100},"ale-bench":{"conflict":0,"contamination_warning":0,"directly_comparable":64,"exact":64,"measured_models":64,"other_supplemental":0,"total_models":100},"apex-agents":{"conflict":0,"contamination_warning":0,"directly_comparable":51,"exact":51,"measured_models":51,"other_supplemental":0,"total_models":100},"appworld":{"conflict":0,"contamination_warning":0,"directly_comparable":5,"exact":5,"measured_models":5,"other_supplemental":0,"total_models":100},"arc-agi-1":{"conflict":0,"contamination_warning":0,"directly_comparable":52,"exact":52,"measured_models":52,"other_supplemental":0,"total_models":100},"arc-agi-2":{"conflict":0,"contamination_warning":0,"directly_comparable":54,"exact":54,"measured_models":54,"other_supplemental":0,"total_models":100},"arena-agent":{"conflict":0,"contamination_warning":0,"directly_comparable":45,"exact":45,"measured_models":45,"other_supplemental":0,"total_models":100},"arena-text":{"conflict":0,"contamination_warning":0,"directly_comparable":80,"exact":80,"measured_models":80,"other_supplemental":0,"total_models":100},"automationbench":{"conflict":0,"contamination_warning":0,"directly_comparable":0,"exact":0,"measured_models":3,"other_supplemental":3,"total_models":100},"bfcl-v4":{"conflict":0,"contamination_warning":0,"directly_comparable":6,"exact":6,"measured_models":10,"other_supplemental":4,"total_models":100},"chess-puzzles":{"conflict":0,"contamination_warning":0,"directly_comparable":64,"exact":64,"measured_models":64,"other_supplemental":0,"total_models":100},"critpt":{"conflict":0,"contamination_warning":0,"directly_comparable":87,"exact":87,"measured_models":87,"other_supplemental":0,"total_models":100},"cursorbench":{"conflict":0,"contamination_warning":0,"directly_comparable":18,"exact":18,"measured_models":18,"other_supplemental":0,"total_models":100},"deepswe":{"conflict":0,"contamination_warning":0,"directly_comparable":28,"exact":28,"measured_models":35,"other_supplemental":7,"total_models":100},"epoch-eci":{"conflict":0,"contamination_warning":0,"directly_comparable":86,"exact":86,"measured_models":86,"other_supplemental":0,"total_models":100},"frontiercode":{"conflict":0,"contamination_warning":0,"directly_comparable":40,"exact":40,"measured_models":40,"other_supplemental":0,"total_models":100},"frontiermath":{"conflict":0,"contamination_warning":0,"directly_comparable":68,"exact":68,"measured_models":68,"other_supplemental":0,"total_models":100},"frontiermath-tier-4":{"conflict":0,"contamination_warning":0,"directly_comparable":53,"exact":53,"measured_models":53,"other_supplemental":0,"total_models":100},"gdpval":{"conflict":0,"contamination_warning":0,"directly_comparable":5,"exact":5,"measured_models":5,"other_supplemental":0,"total_models":100},"gdpval-aa-v2.1":{"conflict":0,"contamination_warning":0,"directly_comparable":79,"exact":79,"measured_models":79,"other_supplemental":0,"total_models":100},"gpqa-diamond":{"conflict":0,"contamination_warning":0,"directly_comparable":53,"exact":53,"measured_models":92,"other_supplemental":39,"total_models":100},"gso":{"conflict":0,"contamination_warning":0,"directly_comparable":17,"exact":17,"measured_models":17,"other_supplemental":0,"total_models":100},"hle":{"conflict":0,"contamination_warning":0,"directly_comparable":16,"exact":16,"measured_models":54,"other_supplemental":38,"total_models":100},"hle-text":{"conflict":0,"contamination_warning":0,"directly_comparable":63,"exact":63,"measured_models":63,"other_supplemental":0,"total_models":100},"ifbench":{"conflict":0,"contamination_warning":0,"directly_comparable":8,"exact":8,"measured_models":8,"other_supplemental":0,"total_models":100},"ifeval":{"conflict":0,"contamination_warning":0,"directly_comparable":0,"exact":0,"measured_models":3,"other_supplemental":3,"total_models":100},"ioi":{"conflict":0,"contamination_warning":0,"directly_comparable":38,"exact":38,"measured_models":38,"other_supplemental":0,"total_models":100},"livebench":{"conflict":0,"contamination_warning":0,"directly_comparable":57,"exact":57,"measured_models":57,"other_supplemental":0,"total_models":100},"livecodebench":{"conflict":0,"contamination_warning":0,"directly_comparable":52,"exact":52,"measured_models":60,"other_supplemental":8,"total_models":100},"mcp-atlas":{"conflict":0,"contamination_warning":0,"directly_comparable":23,"exact":23,"measured_models":24,"other_supplemental":1,"total_models":100},"mirrorcode":{"conflict":0,"contamination_warning":0,"directly_comparable":27,"exact":27,"measured_models":27,"other_supplemental":0,"total_models":100},"mmlu-pro":{"conflict":0,"contamination_warning":0,"directly_comparable":54,"exact":54,"measured_models":63,"other_supplemental":9,"total_models":100},"mmmu-pro":{"conflict":0,"contamination_warning":0,"directly_comparable":43,"exact":43,"measured_models":70,"other_supplemental":27,"total_models":100},"osworld-2":{"conflict":0,"contamination_warning":0,"directly_comparable":9,"exact":9,"measured_models":10,"other_supplemental":1,"total_models":100},"otis-mock-aime":{"conflict":0,"contamination_warning":0,"directly_comparable":78,"exact":78,"measured_models":78,"other_supplemental":0,"total_models":100},"programbench":{"conflict":0,"contamination_warning":0,"directly_comparable":53,"exact":53,"measured_models":53,"other_supplemental":0,"total_models":100},"scicode":{"conflict":0,"contamination_warning":0,"directly_comparable":77,"exact":77,"measured_models":84,"other_supplemental":7,"total_models":100},"simplebench":{"conflict":0,"contamination_warning":0,"directly_comparable":37,"exact":37,"measured_models":37,"other_supplemental":0,"total_models":100},"simpleqa-verified":{"conflict":0,"contamination_warning":0,"directly_comparable":62,"exact":62,"measured_models":66,"other_supplemental":4,"total_models":100},"skillsbench":{"conflict":0,"contamination_warning":0,"directly_comparable":15,"exact":15,"measured_models":22,"other_supplemental":7,"total_models":100},"sre-bench":{"conflict":0,"contamination_warning":0,"directly_comparable":31,"exact":31,"measured_models":31,"other_supplemental":0,"total_models":100},"swe-bench-live":{"conflict":0,"contamination_warning":0,"directly_comparable":7,"exact":7,"measured_models":7,"other_supplemental":0,"total_models":100},"swe-bench-pro-v2":{"conflict":0,"contamination_warning":0,"directly_comparable":16,"exact":16,"measured_models":16,"other_supplemental":0,"total_models":100},"swe-bench-verified":{"conflict":0,"contamination_warning":0,"directly_comparable":55,"exact":55,"measured_models":60,"other_supplemental":5,"total_models":100},"swe-rebench-v2":{"conflict":0,"contamination_warning":6,"directly_comparable":11,"exact":5,"measured_models":35,"other_supplemental":24,"total_models":100},"tau3-banking":{"conflict":0,"contamination_warning":0,"directly_comparable":22,"exact":22,"measured_models":25,"other_supplemental":3,"total_models":100},"tau3-banking-aa":{"conflict":0,"contamination_warning":0,"directly_comparable":43,"exact":43,"measured_models":43,"other_supplemental":0,"total_models":100},"terminal-bench-2.1":{"conflict":0,"contamination_warning":0,"directly_comparable":57,"exact":57,"measured_models":69,"other_supplemental":12,"total_models":100},"terminal-bench-3":{"conflict":0,"contamination_warning":0,"directly_comparable":11,"exact":11,"measured_models":11,"other_supplemental":0,"total_models":100},"terminal-bench-4":{"conflict":0,"contamination_warning":0,"directly_comparable":47,"exact":47,"measured_models":59,"other_supplemental":12,"total_models":100},"terminal-bench-science-0.1":{"conflict":0,"contamination_warning":0,"directly_comparable":36,"exact":36,"measured_models":36,"other_supplemental":0,"total_models":100},"vending-bench-2":{"conflict":0,"contamination_warning":0,"directly_comparable":50,"exact":50,"measured_models":50,"other_supplemental":0,"total_models":100},"vibe-code-bench":{"conflict":0,"contamination_warning":0,"directly_comparable":76,"exact":76,"measured_models":76,"other_supplemental":0,"total_models":100},"webdev-arena":{"conflict":0,"contamination_warning":0,"directly_comparable":86,"exact":86,"measured_models":86,"other_supplemental":0,"total_models":100},"weirdml":{"conflict":0,"contamination_warning":0,"directly_comparable":48,"exact":48,"measured_models":48,"other_supplemental":0,"total_models":100},"weirdml-v3":{"conflict":0,"contamination_warning":0,"directly_comparable":25,"exact":25,"measured_models":25,"other_supplemental":0,"total_models":100}},"benchmark_ids":["epoch-eci","aa-intelligence-index","arena-text","livebench","hle","hle-text","simpleqa-verified","gpqa-diamond","mmlu-pro","otis-mock-aime","frontiermath","arc-agi-2","frontiermath-tier-4","mmmu-pro","critpt","ifbench","ifeval","simplebench","chess-puzzles","arc-agi-1","swe-bench-verified","swe-rebench-v2","swe-bench-live","deepswe","swe-bench-pro-v2","cursorbench","gso","frontiercode","ioi","livecodebench","scicode","ale-bench","vibe-code-bench","webdev-arena","mirrorcode","programbench","weirdml-v3","terminal-bench-2.1","terminal-bench-4","sre-bench","tau3-banking-aa","mcp-atlas","skillsbench","apex-agents","bfcl-v4","arena-agent","appworld","vending-bench-2","gdpval-aa-v2.1","terminal-bench-3","terminal-bench-science-0.1","gdpval","osworld-2","automationbench","tau3-banking","weirdml"],"measurement_count":2530,"meta":{"api_version":"1.13.0","attribution":{"note":"Upstream benchmark owners are credited per measurement in source_name, source_url and source_license; reuse of a single value carries that source's attribution as well.","required":true,"text":"Source: LLM Benchmarks (https://llmbenchmarks.io/)","url":"https://llmbenchmarks.io/"},"canonical_url":"https://llmbenchmarks.io/api/v1/table.json","dataset_schema_version":"1.13.0","generated_at":"2026-11-01T09:20:59Z","license":"Database compilation: CC-BY-4.0; upstream licenses apply per result.","missing_value":"null means not evaluated or not available for the exact configuration","snapshot_fingerprint":"05938638d694a12c288656894517d32d267c73cd9ab6d7e6ca3fb3d5c3b80ac9"},"model_count":100,"quality":{"all_evidence_directly_comparable_percent":91.5,"canonical_protocol_is_explicit_per_benchmark":true,"conflict_cells":0,"correction_review_target_hours":24,"directly_comparable_cells":2316,"directly_comparable_percent":91.5,"essential_benchmark_count":16,"essential_benchmark_ids":["aa-intelligence-index","apex-agents","arena-text","epoch-eci","frontiermath","gdpval-aa-v2.1","gpqa-diamond","hle","livebench","livecodebench","mcp-atlas","mmlu-pro","scicode","swe-bench-verified","swe-rebench-v2","terminal-bench-2.1"],"essential_benchmarks_fully_ingested_from_selected_source_inventory":16,"essential_benchmarks_meeting_attainable_coverage":16,"essential_benchmarks_meeting_coverage":5,"essential_benchmarks_upstream_limited":["aa-intelligence-index","apex-agents","gpqa-diamond","hle","livebench","livecodebench","mcp-atlas","mmlu-pro","swe-bench-verified","swe-rebench-v2","terminal-bench-2.1"],"essential_benchmarks_with_upstream_capacity_for_target":11,"essential_coverage_status":{"aa-intelligence-index":{"absolute_target_models":60,"additional_direct_cells_to_absolute_target":32,"additional_direct_cells_to_attainable_target":0,"attainable_coverage_met":true,"attainable_target_models":28,"selected_source_inventory_fully_utilized":true,"selected_top_100_models_with_comparable_upstream_result":28,"status":"upstream-limited","target_reachable_from_current_upstream":false,"top_100_directly_comparable_models":28,"upstream_canonical_published_models_before_top_100":42,"upstream_comparable_models_before_top_100":42},"apex-agents":{"absolute_target_models":60,"additional_direct_cells_to_absolute_target":9,"additional_direct_cells_to_attainable_target":0,"attainable_coverage_met":true,"attainable_target_models":51,"selected_source_inventory_fully_utilized":true,"selected_top_100_models_with_comparable_upstream_result":51,"status":"upstream-limited","target_reachable_from_current_upstream":false,"top_100_directly_comparable_models":51,"upstream_canonical_published_models_before_top_100":56,"upstream_comparable_models_before_top_100":56},"arena-text":{"absolute_target_models":60,"additional_direct_cells_to_absolute_target":0,"additional_direct_cells_to_attainable_target":0,"attainable_coverage_met":true,"attainable_target_models":60,"selected_source_inventory_fully_utilized":true,"selected_top_100_models_with_comparable_upstream_result":80,"status":"met","target_reachable_from_current_upstream":true,"top_100_directly_comparable_models":80,"upstream_canonical_published_models_before_top_100":391,"upstream_comparable_models_before_top_100":391},"epoch-eci":{"absolute_target_models":60,"additional_direct_cells_to_absolute_target":0,"additional_direct_cells_to_attainable_target":0,"attainable_coverage_met":true,"attainable_target_models":60,"selected_source_inventory_fully_utilized":true,"selected_top_100_models_with_comparable_upstream_result":86,"status":"met","target_reachable_from_current_upstream":true,"top_100_directly_comparable_models":86,"upstream_canonical_published_models_before_top_100":253,"upstream_comparable_models_before_top_100":253},"frontiermath":{"absolute_target_models":60,"additional_direct_cells_to_absolute_target":0,"additional_direct_cells_to_attainable_target":0,"attainable_coverage_met":true,"attainable_target_models":60,"selected_source_inventory_fully_utilized":true,"selected_top_100_models_with_comparable_upstream_result":68,"status":"met","target_reachable_from_current_upstream":true,"top_100_directly_comparable_models":68,"upstream_canonical_published_models_before_top_100":89,"upstream_comparable_models_before_top_100":89},"gdpval-aa-v2.1":{"absolute_target_models":60,"additional_direct_cells_to_absolute_target":0,"additional_direct_cells_to_attainable_target":0,"attainable_coverage_met":true,"attainable_target_models":60,"selected_source_inventory_fully_utilized":true,"selected_top_100_models_with_comparable_upstream_result":79,"status":"met","target_reachable_from_current_upstream":true,"top_100_directly_comparable_models":79,"upstream_canonical_published_models_before_top_100":208,"upstream_comparable_models_before_top_100":208},"gpqa-diamond":{"absolute_target_models":60,"additional_direct_cells_to_absolute_target":7,"additional_direct_cells_to_attainable_target":0,"attainable_coverage_met":true,"attainable_target_models":53,"selected_source_inventory_fully_utilized":true,"selected_top_100_models_with_comparable_upstream_result":53,"status":"upstream-limited","target_reachable_from_current_upstream":true,"top_100_directly_comparable_models":53,"upstream_canonical_published_models_before_top_100":128,"upstream_comparable_models_before_top_100":128},"hle":{"absolute_target_models":60,"additional_direct_cells_to_absolute_target":44,"additional_direct_cells_to_attainable_target":0,"attainable_coverage_met":true,"attainable_target_models":16,"selected_source_inventory_fully_utilized":true,"selected_top_100_models_with_comparable_upstream_result":16,"status":"upstream-limited","target_reachable_from_current_upstream":false,"top_100_directly_comparable_models":16,"upstream_canonical_published_models_before_top_100":19,"upstream_comparable_models_before_top_100":19},"livebench":{"absolute_target_models":60,"additional_direct_cells_to_absolute_target":3,"additional_direct_cells_to_attainable_target":0,"attainable_coverage_met":true,"attainable_target_models":57,"selected_source_inventory_fully_utilized":true,"selected_top_100_models_with_comparable_upstream_result":57,"status":"upstream-limited","target_reachable_from_current_upstream":true,"top_100_directly_comparable_models":57,"upstream_canonical_published_models_before_top_100":67,"upstream_comparable_models_before_top_100":67},"livecodebench":{"absolute_target_models":60,"additional_direct_cells_to_absolute_target":8,"additional_direct_cells_to_attainable_target":0,"attainable_coverage_met":true,"attainable_target_models":52,"selected_source_inventory_fully_utilized":true,"selected_top_100_models_with_comparable_upstream_result":52,"status":"upstream-limited","target_reachable_from_current_upstream":true,"top_100_directly_comparable_models":52,"upstream_canonical_published_models_before_top_100":130,"upstream_comparable_models_before_top_100":130},"mcp-atlas":{"absolute_target_models":60,"additional_direct_cells_to_absolute_target":37,"additional_direct_cells_to_attainable_target":0,"attainable_coverage_met":true,"attainable_target_models":23,"selected_source_inventory_fully_utilized":true,"selected_top_100_models_with_comparable_upstream_result":23,"status":"upstream-limited","target_reachable_from_current_upstream":false,"top_100_directly_comparable_models":23,"upstream_canonical_published_models_before_top_100":25,"upstream_comparable_models_before_top_100":25},"mmlu-pro":{"absolute_target_models":60,"additional_direct_cells_to_absolute_target":6,"additional_direct_cells_to_attainable_target":0,"attainable_coverage_met":true,"attainable_target_models":54,"selected_source_inventory_fully_utilized":true,"selected_top_100_models_with_comparable_upstream_result":54,"status":"upstream-limited","target_reachable_from_current_upstream":true,"top_100_directly_comparable_models":54,"upstream_canonical_published_models_before_top_100":127,"upstream_comparable_models_before_top_100":127},"scicode":{"absolute_target_models":60,"additional_direct_cells_to_absolute_target":0,"additional_direct_cells_to_attainable_target":0,"attainable_coverage_met":true,"attainable_target_models":60,"selected_source_inventory_fully_utilized":true,"selected_top_100_models_with_comparable_upstream_result":77,"status":"met","target_reachable_from_current_upstream":true,"top_100_directly_comparable_models":77,"upstream_canonical_published_models_before_top_100":136,"upstream_comparable_models_before_top_100":136},"swe-bench-verified":{"absolute_target_models":60,"additional_direct_cells_to_absolute_target":5,"additional_direct_cells_to_attainable_target":0,"attainable_coverage_met":true,"attainable_target_models":55,"selected_source_inventory_fully_utilized":true,"selected_top_100_models_with_comparable_upstream_result":55,"status":"upstream-limited","target_reachable_from_current_upstream":true,"top_100_directly_comparable_models":55,"upstream_canonical_published_models_before_top_100":88,"upstream_comparable_models_before_top_100":88},"swe-rebench-v2":{"absolute_target_models":60,"additional_direct_cells_to_absolute_target":49,"additional_direct_cells_to_attainable_target":0,"attainable_coverage_met":true,"attainable_target_models":11,"selected_source_inventory_fully_utilized":true,"selected_top_100_models_with_comparable_upstream_result":11,"status":"upstream-limited","target_reachable_from_current_upstream":false,"top_100_directly_comparable_models":11,"upstream_canonical_published_models_before_top_100":11,"upstream_comparable_models_before_top_100":11},"terminal-bench-2.1":{"absolute_target_models":60,"additional_direct_cells_to_absolute_target":3,"additional_direct_cells_to_attainable_target":0,"attainable_coverage_met":true,"attainable_target_models":57,"selected_source_inventory_fully_utilized":true,"selected_top_100_models_with_comparable_upstream_result":57,"status":"upstream-limited","target_reachable_from_current_upstream":true,"top_100_directly_comparable_models":57,"upstream_canonical_published_models_before_top_100":75,"upstream_comparable_models_before_top_100":75}},"essential_fresh_cells":823,"essential_fresh_percent":97.2,"essential_stale_cells":24,"essential_stale_cells_on_currently_observed_canonical_source":24,"essential_stale_cells_with_source_observation_gap":0,"essential_thinking_disclosure_cells":521,"essential_thinking_disclosure_percent":61.5,"essential_thinking_undisclosed_cells":326,"essential_visible_cells":847,"sourced_cells":2530,"standard_view":"all-sourced-evidence-with-protocol-labels","target_gaps":{"directly_comparable_percent":{"met":true,"new_qualifying_cells_needed":0,"replacements_needed":0},"essential_absolute_coverage_cells_needed":203,"essential_attainable_coverage_cells_needed":0,"essential_fresh_percent":{"met":true,"new_qualifying_cells_needed":0,"replacements_needed":0}},"targets":{"correction_review_hours":24,"directly_comparable_percent":85,"essential_fresh_percent":90,"essential_models_per_benchmark":60},"thinking_disclosure_by_benchmark":{"aa-intelligence-index":{"directly_comparable_cells":28,"disclosed_cells":20,"disclosed_percent":71.4,"undisclosed_cells":8},"ale-bench":{"directly_comparable_cells":64,"disclosed_cells":49,"disclosed_percent":76.6,"undisclosed_cells":15},"apex-agents":{"directly_comparable_cells":51,"disclosed_cells":20,"disclosed_percent":39.2,"undisclosed_cells":31},"appworld":{"directly_comparable_cells":5,"disclosed_cells":0,"disclosed_percent":0.0,"undisclosed_cells":5},"arc-agi-1":{"directly_comparable_cells":52,"disclosed_cells":44,"disclosed_percent":84.6,"undisclosed_cells":8},"arc-agi-2":{"directly_comparable_cells":54,"disclosed_cells":47,"disclosed_percent":87.0,"undisclosed_cells":7},"arena-agent":{"directly_comparable_cells":45,"disclosed_cells":28,"disclosed_percent":62.2,"undisclosed_cells":17},"arena-text":{"directly_comparable_cells":80,"disclosed_cells":46,"disclosed_percent":57.5,"undisclosed_cells":34},"automationbench":{"directly_comparable_cells":0,"disclosed_cells":0,"disclosed_percent":0.0,"undisclosed_cells":0},"bfcl-v4":{"directly_comparable_cells":6,"disclosed_cells":0,"disclosed_percent":0.0,"undisclosed_cells":6},"chess-puzzles":{"directly_comparable_cells":64,"disclosed_cells":57,"disclosed_percent":89.1,"undisclosed_cells":7},"critpt":{"directly_comparable_cells":87,"disclosed_cells":62,"disclosed_percent":71.3,"undisclosed_cells":25},"cursorbench":{"directly_comparable_cells":18,"disclosed_cells":18,"disclosed_percent":100.0,"undisclosed_cells":0},"deepswe":{"directly_comparable_cells":28,"disclosed_cells":27,"disclosed_percent":96.4,"undisclosed_cells":1},"epoch-eci":{"directly_comparable_cells":86,"disclosed_cells":2,"disclosed_percent":2.3,"undisclosed_cells":84},"frontiercode":{"directly_comparable_cells":40,"disclosed_cells":39,"disclosed_percent":97.5,"undisclosed_cells":1},"frontiermath":{"directly_comparable_cells":68,"disclosed_cells":57,"disclosed_percent":83.8,"undisclosed_cells":11},"frontiermath-tier-4":{"directly_comparable_cells":53,"disclosed_cells":44,"disclosed_percent":83.0,"undisclosed_cells":9},"gdpval":{"directly_comparable_cells":5,"disclosed_cells":1,"disclosed_percent":20.0,"undisclosed_cells":4},"gdpval-aa-v2.1":{"directly_comparable_cells":79,"disclosed_cells":61,"disclosed_percent":77.2,"undisclosed_cells":18},"gpqa-diamond":{"directly_comparable_cells":53,"disclosed_cells":39,"disclosed_percent":73.6,"undisclosed_cells":14},"gso":{"directly_comparable_cells":17,"disclosed_cells":6,"disclosed_percent":35.3,"undisclosed_cells":11},"hle":{"directly_comparable_cells":16,"disclosed_cells":5,"disclosed_percent":31.2,"undisclosed_cells":11},"hle-text":{"directly_comparable_cells":63,"disclosed_cells":47,"disclosed_percent":74.6,"undisclosed_cells":16},"ifbench":{"directly_comparable_cells":8,"disclosed_cells":8,"disclosed_percent":100.0,"undisclosed_cells":0},"ifeval":{"directly_comparable_cells":0,"disclosed_cells":0,"disclosed_percent":0.0,"undisclosed_cells":0},"ioi":{"directly_comparable_cells":38,"disclosed_cells":32,"disclosed_percent":84.2,"undisclosed_cells":6},"livebench":{"directly_comparable_cells":57,"disclosed_cells":38,"disclosed_percent":66.7,"undisclosed_cells":19},"livecodebench":{"directly_comparable_cells":52,"disclosed_cells":40,"disclosed_percent":76.9,"undisclosed_cells":12},"mcp-atlas":{"directly_comparable_cells":23,"disclosed_cells":11,"disclosed_percent":47.8,"undisclosed_cells":12},"mirrorcode":{"directly_comparable_cells":27,"disclosed_cells":27,"disclosed_percent":100.0,"undisclosed_cells":0},"mmlu-pro":{"directly_comparable_cells":54,"disclosed_cells":42,"disclosed_percent":77.8,"undisclosed_cells":12},"mmmu-pro":{"directly_comparable_cells":43,"disclosed_cells":35,"disclosed_percent":81.4,"undisclosed_cells":8},"osworld-2":{"directly_comparable_cells":9,"disclosed_cells":7,"disclosed_percent":77.8,"undisclosed_cells":2},"otis-mock-aime":{"directly_comparable_cells":78,"disclosed_cells":62,"disclosed_percent":79.5,"undisclosed_cells":16},"programbench":{"directly_comparable_cells":53,"disclosed_cells":43,"disclosed_percent":81.1,"undisclosed_cells":10},"scicode":{"directly_comparable_cells":77,"disclosed_cells":53,"disclosed_percent":68.8,"undisclosed_cells":24},"simplebench":{"directly_comparable_cells":37,"disclosed_cells":8,"disclosed_percent":21.6,"undisclosed_cells":29},"simpleqa-verified":{"directly_comparable_cells":62,"disclosed_cells":52,"disclosed_percent":83.9,"undisclosed_cells":10},"skillsbench":{"directly_comparable_cells":15,"disclosed_cells":0,"disclosed_percent":0.0,"undisclosed_cells":15},"sre-bench":{"directly_comparable_cells":31,"disclosed_cells":27,"disclosed_percent":87.1,"undisclosed_cells":4},"swe-bench-live":{"directly_comparable_cells":7,"disclosed_cells":3,"disclosed_percent":42.9,"undisclosed_cells":4},"swe-bench-pro-v2":{"directly_comparable_cells":16,"disclosed_cells":16,"disclosed_percent":100.0,"undisclosed_cells":0},"swe-bench-verified":{"directly_comparable_cells":55,"disclosed_cells":40,"disclosed_percent":72.7,"undisclosed_cells":15},"swe-rebench-v2":{"directly_comparable_cells":11,"disclosed_cells":6,"disclosed_percent":54.5,"undisclosed_cells":5},"tau3-banking":{"directly_comparable_cells":22,"disclosed_cells":19,"disclosed_percent":86.4,"undisclosed_cells":3},"tau3-banking-aa":{"directly_comparable_cells":43,"disclosed_cells":30,"disclosed_percent":69.8,"undisclosed_cells":13},"terminal-bench-2.1":{"directly_comparable_cells":57,"disclosed_cells":41,"disclosed_percent":71.9,"undisclosed_cells":16},"terminal-bench-3":{"directly_comparable_cells":11,"disclosed_cells":11,"disclosed_percent":100.0,"undisclosed_cells":0},"terminal-bench-4":{"directly_comparable_cells":47,"disclosed_cells":39,"disclosed_percent":83.0,"undisclosed_cells":8},"terminal-bench-science-0.1":{"directly_comparable_cells":36,"disclosed_cells":32,"disclosed_percent":88.9,"undisclosed_cells":4},"vending-bench-2":{"directly_comparable_cells":50,"disclosed_cells":3,"disclosed_percent":6.0,"undisclosed_cells":47},"vibe-code-bench":{"directly_comparable_cells":76,"disclosed_cells":59,"disclosed_percent":77.6,"undisclosed_cells":17},"webdev-arena":{"directly_comparable_cells":86,"disclosed_cells":49,"disclosed_percent":57.0,"undisclosed_cells":37},"weirdml":{"directly_comparable_cells":48,"disclosed_cells":33,"disclosed_percent":68.8,"undisclosed_cells":15},"weirdml-v3":{"directly_comparable_cells":25,"disclosed_cells":25,"disclosed_percent":100.0,"undisclosed_cells":0}},"thinking_disclosure_cells":1610,"thinking_disclosure_percent":69.5,"thinking_undisclosed_cells":706,"unknown_thinking_is_never_inferred":true,"visible_cells":2530},"rows":[{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bd3f4b9127522f85eef17335009ed080803bd901e8c4227e329e88eb87380562","measurement_key":"9563c668196c43eb8432e030e9c73331d2a461f29ff84c2aac900d16052b758c","metric":"index_score","protocol_fingerprint":"ff3aadf4e201cbeb10a8718d8c05c6c1a72ddb0a0cfbfc86f35e5ae115c2acac","run_fingerprint":"b2d83c91b700f8484fd63b3d9703405d9d5a1235f8084606919aa286c43c9df8","score":56.853856,"score_display":"56.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:16Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0d61f2caeeb99a1fc0234c9d43fc69decbe2688a742daed736cd57fb2843f227","measurement_key":"fd320a184d1c70b3452033aa0ca14001f445f218ace97e3ea7087638444c2aa9","metric":"performance_rating","protocol_fingerprint":"c2edd8d4c38660c681e4fd4857862e563cc9344321c9f62a8287a3235d44a90c","run_fingerprint":"319b24c34162e26cf1539535711df172934ad236e5995f1dfb6d420dde739ce4","score":2951.32,"score_display":"2951.32","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5c458526aef24450b7dc29bafa5f2c4a83afc1e18a394140450e76650a46a8de","measurement_key":"45288ae1d1a453bd6f9f96da98821deaaf69871d9c1d04cad1c7c61d7399f9ab","metric":"pass_at_1","protocol_fingerprint":"925e7392b66354d25392570cb0544fe4125cf86bcfee1eb0ca1ac3d5cfab2995","run_fingerprint":"f1ee9fddf4756444a826bdaaa3ac12346b27d9a61091ecb2f803d5851da248a3","score":64.7,"score_display":"64.7","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_138452291adbe4025c01d25b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":55,"at":"2026-09-06T19:02:22Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"87725e7b6ad28920efedc3e609084a3b882a9cd4e0d2834beeae56e488cc00e5","measurement_key":"ad2b6fc47dc36cd2ab577fce31e6dc2a2f0555171e09119f571062a522692472","metric":"pass_at_2_accuracy","protocol_fingerprint":"d34c2d359536016f27e3aff27e6b7bc679d90fe39a26d13dbeb96ff4547f5eeb","run_fingerprint":"ce6574aa279e06198bccec76c7f78a20b82790d4201380548821c2469451b5cf","score":97.5,"score_display":"97.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":58,"at":"2026-09-03T22:49:18Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"22416d4e9d88abba95b2d4906e3d146784c67760348c189f584e11f6c3645db9","measurement_key":"cf8bad677c0e2a6844ae37e1b1f53a873d24585dd1d98fefe6e97477e3363f28","metric":"accuracy","protocol_fingerprint":"b28d063f4e06ef5ecce16f5af8d1f6ae972c1cfcc5d40ff95a612ee586729b39","run_fingerprint":"9b7dc98d98bedae0a63458bc64a7ce49fe29bc6500ab28488bc5208ca70ba9e7","score":95.0,"score_display":"95","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"73c1ae1be1eafe3f5e1163d8b16f71865c6327b57d0b16398034c019075e33ba","measurement_key":"83dc54300b403f780ff54fd3828ea7fb225d1134921be96294a934eb5f436529","metric":"ips_score","protocol_fingerprint":"db0617a03c49a34a923e2f8ffda6cd267cd5dc66edc46d706ff106876c9d1ff7","run_fingerprint":"7a11c18cffbd75c479f344df49aac1bb85d9e833bfa80c437a59547f4496525b","score":0.12960129693659303,"score_display":"0.1296","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"246cfc9f8dd4aa4f572c730f0320030513e1993007620ffacbcd392ea332c15d","measurement_key":"e2783ef97260325ddb0eac0ccd0eb1737f35675412d0d209c0cd92f7fee62006","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"f3fe335d198407b8eae129b636da4d7cb87c20cb921cb9b8fd4ebfc7d4bdeca0","score":1475.647885100779,"score_display":"1476","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:42:38.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"51f0da173a8628fcb7699a66cd0e7f0c739fe39c3dfbe76a181fac2684d4003f","measurement_key":"8f56ac4933b8813ff19e9a12c60b5366d6b9d062bb9482fa268656216a17ec35","metric":"mean_score","protocol_fingerprint":"86f9ec27db74333671b2d764f3712aded33e58fbf4c4bcd07cb6a6f2413ca95c","run_fingerprint":"24363a4a21b6d7180bfb4c8ecb60e23a22a2b0bdb3bcc8519792e76a3434f0ae","score":74.0,"score_display":"74.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"41acdc62087a6a65d16751f288cd532ebb680fd37e425e80982e23241a9d9b21","measurement_key":"414ceb8da40fcb4f7c61a2a4dba37ccf7e58a646a67d3390a1b538fd78a48899","metric":"accuracy","protocol_fingerprint":"3eb901ca4f835e5f8e567b934a3a5f206c51f2cee95c93b16e1a5cf06633e2d5","run_fingerprint":"46019d866e6bcfa2a7365749a933c5f0c88daec3682cf20d04a6e6151f1d59e0","score":31.7142857142857,"score_display":"31.7","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":58,"at":"2026-09-04T01:03:12Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"52da400c4513cb966dad2116a772e4a6a055a9abc03486fa0f2102253ae1ae18","measurement_key":"da1e818db0236b3b3980c4b0bc43f2268a28e71cf3149113319c13e14be801f7","metric":"pass_at_1","protocol_fingerprint":"d4e26041d9b76d03a07c7366187d69f1095660ca79d9891f8caf0c00b728abb8","run_fingerprint":"3b9fde1893a272dc3b59dce4eb0ab69a9fda40d39d87d5fcaed61eae87bde541","score":73.23008849557522,"score_display":"73.2","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dfeca08c310bd20edd622e52fd3ddd2c38c8066b05080ff16e0719c27460d230","measurement_key":"3f45afdb806641158185868e8baf6fa73c82c1f8e91ae01622f970b5e2a7b21a","metric":"eci","protocol_fingerprint":"7ebfea7bab2e4747e9bb4b134bc1e2a358408c8e41c568da62257ecf353d821b","run_fingerprint":"6e87df35476dea2f67c27291daa3411a4b429106b1f4acfb883694dd6144df98","score":169.06,"score_display":"169.06","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9276dc96b9e1782b83ae6c86","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":55,"at":"2026-09-06T19:02:21Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4b566fbcb87258b345d372b5fe07e9dba84004e009b93dcdb4385adc7a36a7f6","measurement_key":"47ae559edec5a2c92238a6b18807fdd14bb511581c56257022c0d9f939390645","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"e19b193e393c9e81b783925a453da14203f8cff7a54b1f5af520cac4f7770b2a","run_fingerprint":"2d82ee0270e995af682c4778552573bf76e9a6661b668da79f4b2b1f70208f98","score":53.26,"score_display":"53.3","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T14:57:43.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"40392a2fabb1edd72abef4d132a67bcb41a3f5b6a36cedec884a66b8a1fa5cc4","measurement_key":"452bd43ccb1dfe483fe89d1944d56463f072ee882bf851d05ec61577ba174560","metric":"mean_score","protocol_fingerprint":"313848536ae7469ee53b15def714d6dcc5afc20f13f3509167c3e5b0871cedf3","run_fingerprint":"6fd8f32a8a063a7ff44cfb20d6b6aef57a952cb5dd5a3601c30e7ebd66962130","score":93.6842105263158,"score_display":"93.7","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":63,"at":"2026-08-30T02:22:12.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7865a44e9658471fb16e762c68809b9e338f2ccdaece3cb91f7edadbeb35d327","measurement_key":"d9a48ec9d163d0368ed13d54b4ba71367d4b38a3ed17ff2a67512f02de2b77cf","metric":"mean_score","protocol_fingerprint":"04a3a0352ec5ad74f3c30888cdf8e8bb18489aa80e36e7b0c0f77af63d2842d8","run_fingerprint":"e1ef89374da6b91c2d8faacb07535630fe76623009011266307d5783b3aba45e","score":97.6,"score_display":"97.6","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"36e9084a51a24b9ca343519fb5f061cc0701764160cbcec5593c612eb5f03c4e","measurement_key":"96990a6d5813534f8461c6db88b99c8af25552bb4efdc6a9e3a1309c2073bfa9","metric":"elo","protocol_fingerprint":"2e91e2e91472eda21f4f7e0f089a1651686238263436658a4d19e3c86ac43aa3","run_fingerprint":"f8bb22f60f8544e280e74ffd6bcb69d2e7c6041669ef2d7b16c557a7adab66b9","score":1583.69,"score_display":"1584","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_f83cfc2a9e19b8d654d7b58e","benchmark_version":"GPQA Diamond (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4a0c0baf62127c909ccbb6a4734d17990384e9b8471a2244694d088e4f168735","measurement_key":"88bc2f50787021598056036d71039279f17fb5881ad6203af402db5bcef8058c","metric":"accuracy","protocol_fingerprint":"59087f63ed4c023451438f8ee8ba33c99013eaea3114b59436e916996ebbfd44","run_fingerprint":"d207c38bcf93ca0233d9a7c109c14c1a124df2c72f3ebf981768d5cd5ca20c1e","score":96.060606,"score_display":"96.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"diamond-198-zero-shot-5-repeats","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gso":{"benchmark_release_id":"release_176f07ea4e9e0b8dfeede990","benchmark_version":"GSO current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":35,"at":"2026-09-27","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"be8f99a18b01cc90b97b3d83fe86a5194b5d1ac41c83c299c964b332aada9e22","measurement_key":"05368b06986d95a405c7d5489334b4a7d2d55eee66d724e3de09a9b080712836","metric":"opt_at_1","protocol_fingerprint":"eebc9651e1990fb52f6f206b1084d65a0640d7c2d9774a2676ec8676ee434518","run_fingerprint":"46dd1c7ab248af99bce0dca5d42879c4d5dc59671492329fd9e596404bc303d2","score":79.41,"score_display":"79.4","source":{"id":"epoch-gso","name":"Epoch AI mirror · GSO","url":"https://epoch.ai/benchmarks/gso"},"source_authority_tier":"B","split_or_window":"official-set-opt-at-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_373c486c9fe4fc91578ca390","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"hle":{"benchmark_release_id":"release_8817af9d9a0235bce0826e22","benchmark_version":"HLE finalized 2,500 · Scale protocol 2025-04-03","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":52,"at":"2026-09-09T18:59:21Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"63e7e59d049e0dd8675c3295a3c2bc8e34dd4160c3d88e64c1248b62cbfe6e6c","measurement_key":"8b994aa6c0b63f76e65c1bb12ae6cec2ccc710adc7793277c6bf8e95b484179f","metric":"accuracy","protocol_fingerprint":"7ecbd39ffc3bf8715a9b204e1a5b5537484a38ea30faa2d60dd602ae2f7ad249","run_fingerprint":"61a76dd8868255a3b3909d02d6fa3b7672b92bbfcd4fee3e77ecaff6f5674e6a","score":54.8,"score_display":"54.80","source":{"id":"scale-hle","name":"Scale AI Labs · Humanity's Last Exam Full","url":"https://labs.scale.com/leaderboard/humanitys_last_exam"},"source_authority_tier":"A+","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_38556cdaf0f3888ee868b8cb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5b76c510cf20f46f89f480f44245a40f716e1d3a67a0c4e2cdbc908e596e2af7","measurement_key":"bc81510a0d3f9e02870fb575f051bedb12765aa3c4946c59aaafe4d02a64bd8d","metric":"accuracy","protocol_fingerprint":"2af561e3547a161f266c858e2da266c8a3686a586d0456e21e5863b3b54bc181","run_fingerprint":"2e49cc198a4a2284cb72277bd6dbb9a5673b863a94b3458984b2c520e3f91bf9","score":54.680259,"score_display":"54.7","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":47,"at":"2026-09-14T23:34:42Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bbc37cb201b1665196fd0ae262f4ed8e8054f6a8e5637c03c223b87d857cdfb0","measurement_key":"f5e6f22dfd2f8fefe4026a1494a593e84d56c677c8d626bf173664063e175c17","metric":"score","protocol_fingerprint":"7a6eb621851bec0b74e66fba6ba514b3183dff39a19a47ed8fa5e55b05b86f8d","run_fingerprint":"2489de89e66c5446f66d11127e12349674f7de2fcff9622d4a9d23ad6b9dbcda","score":100.0,"score_display":"100.0","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":56,"at":"2026-09-05T16:42:11Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"413c2ef9e8360cb6fd8bdc28414a39651a7bf9cca804d565df431b3935da031e","measurement_key":"2b493a1da4f78e4ac3ccff243818616e948027a371113fce3a49e3f04ca4ecb4","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"f6ba353da222a95140a834495556445c7241a83d1f3b73789713cca425ca51ba","score":82.16064285714288,"score_display":"82.16","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T18:04:06.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a63dabde48a505aa7a36467f90919df747a8eb3d251abf8c2a866d09a62b6121","measurement_key":"1ca8c90a0c16e7818f88ba516497122ba22035cb0669c6898403e3573364fe60","metric":"mean_score","protocol_fingerprint":"712acdabde9fec9e9674eeab8ceacc45f20e87c6f37ca1761015d0e8eb290bcb","run_fingerprint":"f3c0ba72c6a41dec217946658746864f5d0c68c6852f2ed71a38de70157979c1","score":60.0,"score_display":"60.0","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c4f777d86318d2e0b37f270728e9aefdd8da6010189e6279370b3d69279bd69c","measurement_key":"1a6c9772416f4213fa3aadc422dc5b19a20c8e6b09a0502fb6c7e5cba5ff9347","metric":"accuracy","protocol_fingerprint":"5a7867656e43542c6cc90fd79af05ff5ba7a2136e56a3fe40ef8e7878437f909","run_fingerprint":"99ec5413a659f95420f1708928d795734597c527bd93a9cef0459e4c48eb77e6","score":86.878613,"score_display":"86.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T14:57:43.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c133a59aaea1182115fb6cc7bddd8c4d90b567eef3db965b41a1cc71334d9a4b","measurement_key":"f3f63da60b4057bd091ba48e73d336c22e501fdb0166e99b28d25e846672dcb3","metric":"mean_score","protocol_fingerprint":"966adef4976badfac20721ce0a1dd126f88966c8309933d9a2fd20e6aff1f86b","run_fingerprint":"0d76f06dfb6b9d946c231f3a49d761768417f3deb68d7ce20a75c4a1ef2f54fb","score":100.0,"score_display":"100.0","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cfb49952b20b10ec546cac567c8232779b36bc6f92cab9e07f650a0aae175ed0","measurement_key":"9b305b245c873c23aebba452a329caa0314b879f72608535f721b1d91803509d","metric":"fully_resolved_rate","protocol_fingerprint":"95554c804b3d3488cce1c61c1addef0b15f5eb4e2cb658476d8c8a4a69945000","run_fingerprint":"986773133f9bfa0747fdcf125b5408fad239a71c754b0a64d6bea6d334629378","score":5.5,"score_display":"5.5","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f57b923423daeb47cbc0735cb5c5cd39642628e17dea035f74220e5f58e119ae","measurement_key":"7d9cbde24d86848afce644c3274a553fb69a1d61a6876b47a844bf8c05918631","metric":"subproblem_accuracy","protocol_fingerprint":"ee39d1995ea289ec8c14a15e390ea330a1f94e4f235f923ce2d7a3b0c8e6b5bf","run_fingerprint":"d114cb371ebb440f250faa69648bc7bade19bee1ee6b1522621114aeec4d2eda","score":56.4814814814815,"score_display":"56.5","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T14:57:43.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ba487a803e8367590119e1033cb332fcb1e32fc9ad9f27881da40ad61c570e91","measurement_key":"437d3a3deaeb054f09ed3f6cc1cfa5ecdf2ff964dd137688e33001e0060c96a4","metric":"accuracy","protocol_fingerprint":"2854e3d43358f88d6e47f693d81162b933415b351afa2cdfc215f08a78adcd61","run_fingerprint":"df1a193413ea3fa2fa0794e0369663191350e47f41e35a586efd953f6374b626","score":75.6,"score_display":"75.6","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5f3381dee4001c3a4be7550a39f91b25c173852e58ffc26b233a7f99529187be","measurement_key":"bbde8a6c8b41662393f3123a9784988ec138e5e832447fb1899e46dd17117c17","metric":"fully_solved_rate","protocol_fingerprint":"d237b1e83538dd1fc10db7618f65ecf6adffc3c8b022e5b4713fda66bf16d985","run_fingerprint":"61834725e3c31bee87b533ec57ac834fcb1c618b504b00ec964f6d0d67ea78e8","score":56.87,"score_display":"56.9","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-pro-v2":{"benchmark_release_id":"release_d9b58bd286ce316ccf0ed891","benchmark_version":"Scale SWE-Bench Pro V2 public leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":25,"at":"2026-10-07T01:44:58Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"25985fed3ca843fb1cb09fc706d2504d186391b04edc7b1156738cda32e854ec","measurement_key":"5b42bf92cad18cd78bd7481054fd479d188fe9ecb197d806cfcd336780f10e13","metric":"resolved_rate","protocol_fingerprint":"4bc77a451f721a891d7ea51d63796e31ec4953aea5af7311f8740b66c6fd744a","run_fingerprint":"eb5a51b64c3e091ab3d245ebb7db1e0f3df555452e331326634b6c683a1af2c7","score":96.9,"score_display":"96.9","source":{"id":"scale-swe-bench-pro-v2","name":"Scale AI Labs · SWE-bench Pro V2","url":"https://labs.scale.com/leaderboard/swe_bench_pro_public_v2"},"source_authority_tier":"A+","split_or_window":"public-v2-642","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_a8eb1aa90528f25d7a199e22","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f5eb9e107c3be4d5e8f75c89d74e1231e591ededca82c0fcf8796cb6301eb491","measurement_key":"22d697092864f198901cfed50dca26307e7e94ee28f26d834497297991c89286","metric":"pass_at_1","protocol_fingerprint":"f9840e8c650299f0b3ff78d44f36cf5ebd2dfcf465799587b93c39759d11f106","run_fingerprint":"704e8dddd83992489aaad8301110dcbf7e4403f5092ec9c96d4b2d542f61eb64","score":41.443299,"score_display":"41.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:09:19Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8faf7df5250b61b0138c02e34704e6ff9ee6085d5efc172b5bed6af6f6386b0a","measurement_key":"3ea69b1004585900f2b2033dbd757375709ba99d6e8a89e5f61063fb6c404a7f","metric":"accuracy","protocol_fingerprint":"b2cfc1f6453633f55ed1f444420221deb0c3736a0f4b94755fdf388c115c2981","run_fingerprint":"31a5004faf4c16afc592f51a1134f701526d30cd619a224114baa69a0b405e3a","score":87.266,"score_display":"87.3","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"49129a3f85dcb70cbd083dbf5e3c90bda29e12ea1d3aaddac9f9e2b107c9a99f","measurement_key":"e96468df4bad587a5e767c0550aeec77bc25b48a4a283754b9d12ac51b76ae6f","metric":"accuracy","protocol_fingerprint":"d7d11042790079edad82bb1abd1aad8600cdc1f8e3b286cfe771aa8bd20d38ee","run_fingerprint":"031909787bf8cbfbab478b69b4e8748a290c1c262b57100d5c09632c337717b2","score":59.596,"score_display":"59.6","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"17bdd8840d010d19aa2b4dc26d0c1b36682c3b6f1c692e86eee7a3b37b024e85","measurement_key":"091f8eacc95309136b42741e852f24f255bf50638b957f5dab62593d91978966","metric":"accuracy","protocol_fingerprint":"d05ec267b780ae1aaa7f08e1be2af16055c12d7d811ea626692c9f839a2aba19","run_fingerprint":"7a12a4379083ae05c430487f76bd7b0fd535c281bec50017f99b59e23207a6bc","score":62.857,"score_display":"62.9","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:16Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a7ec89e84db94833c2358299cdd8fca8f682cb01823622b2569276e3f2bdd0a0","measurement_key":"f29da36a2a990c590e7fd07eee1809499e5815205e84b042d667bfd436a8a01a","metric":"mean_final_balance_usd","protocol_fingerprint":"cc9fb18a90926b80745487407023b43b6b38c6beb0a76f23d2522810152ae557","run_fingerprint":"b5ab987f1d03f3511c4ea27caee959af6eaa636b8ea5c9eea6b5a3eb83781b2e","score":15514.701666666668,"score_display":"15514.70","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2315d6296613da07b43f9c55","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:09:25Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f69fadc2dad38e91d06cfe38c8fc3ebb33680899c0345cdcb5243faacb6ab4fb","measurement_key":"58d3493d5531fa673dd7d7a5cd43d8a2e2a0c287ac5ea967447d0ffc7a5c6399","metric":"score","protocol_fingerprint":"41892bda746320939fc120ca2546e4907455517f55ab8144325f2fce073d3f41","run_fingerprint":"3168256c1f6b7de0ac4c3bed943edd57a1a08c31ce2058985f706ada1c18c011","score":89.594,"score_display":"89.6","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"11ea0b38a8e9c9783f093e9aaebbf9bcc6156fdbbf5b1240ff13e1b26eb20834","measurement_key":"9c2257f7233eb09ab8e63a887ae2d801d24364d8ffbb224d10fa3ea099d24745","metric":"arena_score","protocol_fingerprint":"442422ad0dde6f9afac723800b517a077c6cd85550c4514675179008aa01f345","run_fingerprint":"67984a98170624fc9861869b648376752c130fc521bbe5f27abc896660ef73d6","score":1773.3545606290113,"score_display":"1773","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:16Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"231e040e4238f44ea49e19e998d2ccf85982c9b99c8880fdd4336ea3a3adbe83","measurement_key":"fe5ea70d8a451cccbb2c76ed881b17e3c04c9dc7164979bdf65c9068f2b3660b","metric":"accuracy","protocol_fingerprint":"8ef8215c0ebf37651b14f2e485100d791f62dd592f8b348bbe2f92dd1dc5c1cd","run_fingerprint":"90d8f867f78de4c4c162946486b2de38c513f00112804f23741a5fa93f7d200e","score":93.57,"score_display":"93.6","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a45ce5352161ba5d3a87a651","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"63e379b8ff7277a43793313fdd70b0505de49c63d054dd176b414e0e082077de","measurement_key":"8ce32331611d47fd3daf00ff941b9c70a4199ef9729fcb260e4fb8c4c07364f2","metric":"token_efficiency_weighted_score","protocol_fingerprint":"74b30cd6fbe5538aa72458734b83df5bb9ca837e739ce9b9600fbc373388e1e7","run_fingerprint":"e9a693818f0ba08a7f2226b81c67d0b6c8c227717e384a279b836bbfd95dfdef","score":42.220231363636366,"score_display":"42.2","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_68496eb7a3dbdd992be334df","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"openai/gpt-6-astra","model_name":"GPT 6 astra","parameter_count_active":null,"parameter_count_total":null,"provider":"OpenAI","selection_rank":1,"weights_status":"closed"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"25338822491a5686002b0607491a6ca8feb1dc204140293c35a75ea05dcd7cba","measurement_key":"5fa6376adb4f1135ec483aac7351c1e070b49b95ad4ff5a30c10a105ff5cc53d","metric":"index_score","protocol_fingerprint":"81ebbedac6bb686cde756f69be10b88f093baa09cc773496800bebf083fb3cd0","run_fingerprint":"a8a5760096d595b49eeb49e787e1dd8df989d8a35cc70f3ad081fd634e7f75fa","score":58.406034,"score_display":"58.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":26,"at":"2026-10-05T10:25:48Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2448ce38ffa3c59e36214ba49ce3995cbe9653589a507ae60e6654c1e48c3e6a","measurement_key":"7bb7896073dbcaad84203e8ff595582f89ba5560d9d04ccd00aa384137e35b4b","metric":"performance_rating","protocol_fingerprint":"9482b517aa668f1b1f7e79656e624fc554b91de96483745271e9193220171c39","run_fingerprint":"43b4a6da6ca60774d6b36ac7158690000052ac4310aeb80122433058bb55f7f3","score":2147.38,"score_display":"2147.38","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_37e371ca4768fbe805410768","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2a1c6f5cf8a3f4dadf61fd1058e56f45361c16e1449613c791722864a49f89c8","measurement_key":"abb00a15df8cc3126b644c25db0ee4ecfeab1fc071a77e190fc201e0dfd6fab9","metric":"pass_at_1","protocol_fingerprint":"23f10d9bdf1a4d6dc532a2040fad5fc575bf339ecd97d6a824a4fbb34fb2f893","run_fingerprint":"b7d307a29e8002468892c13578ac62c115860c8cdc45181c767e4d45ef4acb8f","score":73.5,"score_display":"73.5","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:16Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5a21c9bdd54738037e6897c97d43ddb14ae467074ad06492f71219c8ab639d80","measurement_key":"57ee1adda515dad56198b56359cc9d559a184cefeaba2031116edc7569d44438","metric":"pass_at_2_accuracy","protocol_fingerprint":"55c1379708f54011fe6209562f23097353ba4c1673e14d76e4b935194212a208","run_fingerprint":"7b4285aba63a0e7c39b0ecd7fb1a68e36e2478ea1a41ae0a067fa57697e2c33d","score":97.5,"score_display":"97.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-09-30T18:53:20Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1eeb20ed84f86d957135d77863cea385e5fe92dc4d3fca9ecc45bcdd13515bbd","measurement_key":"e11345ef0cf63b459f0a5aac6390569a2054af8dc231da0c5de7b8be4eb3f6a1","metric":"accuracy","protocol_fingerprint":"315b4f3d86330f1b0ad624dbc9cb71b7d38a32a3451c9f98622199f6464ab2d3","run_fingerprint":"96309dd627582d04cc724cb621097e4f8256a417e6fccaf5d7d84c49397b51d7","score":91.66666666666666,"score_display":"92","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f1adeffc9125246a21115cdbb6485535717f91ed02e9821e032a1d6bbaec7ae9","measurement_key":"53a39651650a35e4b5189a1d876060a5575f107931465cc7db7d5506d138a041","metric":"ips_score","protocol_fingerprint":"3891df5a797d999b8fe8794b8938e0f59fdef21b32ab320fd7ebd0f9cdcab60e","run_fingerprint":"bf2d9775f56feb46bde78f3af9a5bfd65011c105d7734a3496e218e01c236e64","score":0.20939685760341706,"score_display":"0.2094","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2274a8e4d22f18b621e653a8fac635a716c008265dc9d0f19e04b01f3af08304","measurement_key":"d2a8b734a099acebbc3f399e7e0e1a27e981d25c32978be89191ca5a878d4a7b","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"2c5ccaf9ad09a70a31c5b4a49cffc25c7d97071c6384f42fc3b3d3b4793afbdd","score":1508.697590625909,"score_display":"1509","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_37e371ca4768fbe805410768","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"automationbench":{"benchmark_release_id":"release_0e98d905ec617087da8bc4a5","benchmark_version":"AutomationBench · official leaderboard private set","comparison_lane":"source-specific","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":40,"at":"2026-09-22","last_confirmed_at":"2026-11-01T07:28:19Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7c495b38a5c9ad7bfd4753fe8bdcdcafff109b2243f6e0cc4dd832221667c419","measurement_key":"3742f895de0d8e128bd8aa55d6eabeaefec10a897edcf4355fe6579984d2c0e2","metric":"success_rate","protocol_fingerprint":"bf38f00a53ed41f7fe4d189f8e24016158b36abd18578c7814c55d6b17f3cc8d","run_fingerprint":"8de057bd410d5d9ffdc4d3476a35f657850923e7d181ce26098feb11f4fd882a","score":40.0,"score_display":"40.0","source":{"id":"anthropic-opus-5-5-card","name":"Anthropic · Claude Opus 5.5 System Card","url":"https://www-cdn.anthropic.com/fc1b44717c85dc068bc6ba5024219938094694bd/Claude%20Opus%205.5%20System%20Card.pdf"},"source_authority_tier":"B","split_or_window":"official-leaderboard-private-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:01:31.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d99e05caa99fcc4310088198da65aeeefb79ccefac92610d9dd2a01eb9fb285c","measurement_key":"1bdb961775f44f53932bff405d7927b8caf1031faf4c61ed0938901f7b944344","metric":"mean_score","protocol_fingerprint":"7c87a06d004a39ff6bfd5f6513e0cfc6f673a695f56e189a064a27b1bfc0dd07","run_fingerprint":"15f181eb321c6ced3a956777c5f76f1a15e397eb69c142d85fcfa627e69b5165","score":67.0,"score_display":"67.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:03Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"32029d217e7adc76ccd4c4ad27909f64a410c9d669a2f05834ddb00f94f299f0","measurement_key":"e631b2e4e9187e08bd2012f87b944633a98531320470a67cf5ee4fbaca02e78d","metric":"accuracy","protocol_fingerprint":"56fca9bd3c46f9c3222f92eac14614023fb6ad69e553a40dcdc6720d8ea97108","run_fingerprint":"e5e071ac92c352bcbd2d233ced5b5ddae009cdc2a61ed1ab11ec7844c3704fae","score":31.7142857142857,"score_display":"31.7","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"cursorbench":{"benchmark_release_id":"release_9acebd5b002e9c3f18a30606","benchmark_version":"CursorBench 4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"befbf255767fc01bbdad4c23aac601be6e1245245f1c4d29b3f359c678be217c","measurement_key":"157e17e175696c89f6bafb636f7df3a41116acfa3bf5ce15ddb27e2f9af53668","metric":"score","protocol_fingerprint":"83d1cdf2d778ee124394c10baa2874ad50c7d194434194fe9bd11c556416228f","run_fingerprint":"a6222044d80d0ecd305e15bae26bb18ff6284b8e24dd887da98e7ebec361f291","score":57.8,"score_display":"57.8","source":{"id":"epoch-cursorbench","name":"Epoch AI mirror · CursorBench","url":"https://epoch.ai/benchmarks/cursorbench"},"source_authority_tier":"B","split_or_window":"official-current-suite","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_12e8a62d68d933c29dcdf020","benchmark_version":"DeepSWE 1.1 vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":40,"at":"2026-09-22","last_confirmed_at":"2026-11-01T07:28:19Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5dcd2e5bff9d17d797b12928119cbbf0f7be536d18671dd3ef7e6f01d750f4c2","measurement_key":"3c48fdbdfefd6d4df3d047bc190bc95012ff226bb25df1f89965298e30f1f94c","metric":"resolved_rate","protocol_fingerprint":"a5cbf75f23ca816482032c8d34b067581919f96816decdf209092b05efa865f9","run_fingerprint":"78cd262e0c7bb48c44fd719220c0c73597c4d613e1bf9c309f8b7f57b52b3379","score":74.2,"score_display":"74.2","source":{"id":"anthropic-opus-5-5-card","name":"Anthropic · Claude Opus 5.5 System Card","url":"https://www-cdn.anthropic.com/fc1b44717c85dc068bc6ba5024219938094694bd/Claude%20Opus%205.5%20System%20Card.pdf"},"source_authority_tier":"B","split_or_window":"vendor-model-card-run","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fb3d58069785743e36e95043","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"62e39f040f099b705e608a5a47a9b74df17e6e11f5c0c8722b39411376bc570d","measurement_key":"671d2292bb91bd86f5eced3866bf5bb1c96ed1bcabc3723d1c188703cd1a79bc","metric":"eci","protocol_fingerprint":"f3fa80a685806f77c42d904ab340df7bdbd1096fdb1f68a5910bae883b09246a","run_fingerprint":"92567516d7e4029a291e039226d855ce389615731852cbd63c15082e807f5677","score":168.4,"score_display":"168.40","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f9bccce8d4fa3cdf550e517a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d5627d58d93fe374d8471a2f56715984db0e29645c78f2b5b0d29b4273c90c31","measurement_key":"7ecb1a1eb0e4a4b2112d5ce9ef4e72f461760f34f0304201cdbc066e30ac3051","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"f47b5fcf31c037c3984dae6d00e33dd6a78c5acf154abd1130cabe14bfdfd4c4","run_fingerprint":"b03012e398d7252eded9f4428abf41aa1a2633afe3a79e9c40f24425de96f261","score":54.64,"score_display":"54.6","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_9bcad8178005dc3a63c077d5","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T18:27:39.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"62d3803fc8f10c86a7c1f7858040cbad0d50e2330a464b9beadc41ebf34fa0a8","measurement_key":"c06b4c2e9d7ac194180cf95b388a6bf1b39ecb74043f155282ebecae82f1f274","metric":"mean_score","protocol_fingerprint":"4e2bced60f1ef278854d63ac4e8ca31823c2c92c09c92122c32905e6348ade6f","run_fingerprint":"df2796b9b6eda77e8c52a24b33f141535ddcf83fe83077f4687398f818541780","score":91.22807017543859,"score_display":"91.2","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T18:27:39.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1a9ba1d68ce3da33282f8592cf0278f68b87a369d69331ad35b2843f4f1b3d96","measurement_key":"2b437f27534cbba1fde81734fe2e8e887eed03ac943827bf7dad2c9ee0e277e1","metric":"mean_score","protocol_fingerprint":"f0f19eb269aa45592a3427a4bb852adbd365864a3ad88b0c430a42d42ef2d8f8","run_fingerprint":"0e41c38fa862ca88746933f8dba99c99a1d153f1338f2c7ec44315f08545c9ae","score":95.0,"score_display":"95.0","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5ca408164414cbf9e4088426eb2f6a44a89af43590326427f18ea98b56085637","measurement_key":"bfe5f6218b74410a2c778542d0b6275f48813823d8ca70d2dbf4b060c24711dd","metric":"elo","protocol_fingerprint":"241513c18e44140122a191607f17fc9dd2c39d9f45af88ce27c36ce48b2a37a3","run_fingerprint":"7c00f6d125828882478afc60881d59f7fbde5979559c6db45432d9e7f4b2155e","score":1866.27,"score_display":"1866","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T18:27:39.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"506c1ad91eefca4538eaa020cffc94da8f4b29430616d804980370df30776069","measurement_key":"437796794a616cdb182a04737dbbd22750d1edb2816b55a86079c31b475dfe6d","metric":"accuracy","protocol_fingerprint":"919ebf8a3d132d097dbb0cc21c7ba269afb98b98144deb645c0be6e6390220de","run_fingerprint":"37c40d2f488d30bdd4bbe22f8b5ed20ac85bfa7aaeeeac947817052fe05b5470","score":90.59343434343434,"score_display":"90.6","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a158b9c3ae8fb3ca5325fbd4ba8eeca36a3bf0c5624e3cd29a5af4863e1f97b3","measurement_key":"63c1c824a13dc6d1ae3e0f4f5fa8840cb9f2c73479d78a83b42bea179ec3c600","metric":"accuracy","protocol_fingerprint":"4bb35cdffa7da4653c3f76ea0c475ae842608d588f64ddc5a5e4a0f9d1bde2c0","run_fingerprint":"dea35a53e7d991c4c7c4b3fc71f8155cb2a035ecc7eac600518c0ce68ded66eb","score":61.353105,"score_display":"61.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":40,"at":"2026-09-22","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9a6e835ba7cb6b1537832a8bd4f5ffa7a601f621d67ca87032480cf3e07dc27c","measurement_key":"2900e838bb34c825d9b10196a8f5c883548828a8fc3dd3a4882b5f3aa9b8a457","metric":"score","protocol_fingerprint":"7b7b55521975458bf69e2674951bf4ad411810c371182f987b6b761e6131283b","run_fingerprint":"9b7b952dd1d52f9597f4ce2f2ab974a28e3bd7a4420cf762ab431cc52344932e","score":95.056,"score_display":"95.1","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-09-30T18:53:19Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b64ea79f2b88710103459ae2364e6e01a3a6a285ea34be265205e89e6790efdb","measurement_key":"46ab48e6968a5834ed7831fa62e402196c47902ecdec64d5d378d5f655c1a7af","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"cdf5d8b03bc09f2ec3259baa3a2141bb4b8936f73c3f78261407c8b8177538f6","score":83.21657142857143,"score_display":"83.22","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T16:42:00.000Z","last_confirmed_at":"2026-10-29T17:24:59Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4e2813b81e9b0bf15507f9ee3b93d5c9eac9bdc8244ad6b0cf701c203aba6e57","measurement_key":"d1fc1bde17487550bc3eb3ce732d75f40ddce2f69dfd8dff38cc90cfeca48ec8","metric":"mean_score","protocol_fingerprint":"16c548b388367f0b7c76db1763b5889ec1e4d4a986b20227b16a4569ff7d348d","run_fingerprint":"fc1191f2a0a28111f2be51aaccbe22a4905bff5da1fd24fdaadb6f3b865cbe00","score":77.4,"score_display":"77.4","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"72c0c7154e9395931ff4bc2fca733903c9aeed35656c48faeb983947803bf0d7","measurement_key":"ad06921113a7409924e8de355a94c4ead9d6456cc71c19f5082a4a1b1a583df0","metric":"accuracy","protocol_fingerprint":"c460578f5b259e5a325bcf140810789b6667c21a1cc093827483293ad4510cc6","run_fingerprint":"0bb9c84e99fa02f1d32cb57c8b4a79df9826d079150715c6cd1d688bf6826ecc","score":87.687861,"score_display":"87.7","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T18:27:39.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f1d81ce5b474147f6223c0914ee1da9d202433bef69daf8ec0d454e51d3e19d1","measurement_key":"ff3a567aaf9e1364b722c429b8f8946b27da4f1857f8d9bf7491c1bbe97e1458","metric":"mean_score","protocol_fingerprint":"4ab8432dffdd095ab10181addaf3fcc8c8f586ceccecd8dbf74f176305c5c768","run_fingerprint":"af451d1fe3928df696e53118c61ff3c5ce5feeb0d4335805774302963a1bc7b1","score":100.0,"score_display":"100.0","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"03f1cfd3cd42733cc006eba5c6c821838facc200288fc2aa0a64f0c86e164562","measurement_key":"bb086d4576bd44bd08580a99304d8ac6ab267755a56edc5b749db68f1f6c09ce","metric":"fully_resolved_rate","protocol_fingerprint":"07fb234dfa73bddc1508bb05a8bf4eebd69e54ac282f5fa1003cfbe6f6ffa78d","run_fingerprint":"3ab135ec55bcb491f277049fbdf047ba804d46ea41d3e6cf92c38cea25fc71b8","score":18.5,"score_display":"18.5","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:02Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fe3d897f43bf8cffc5e5e4a6e5cafd86218c2744de763d2f0f5d5cdd8d010de3","measurement_key":"8ed4aa0b416ac50c5488348805c5ad9d7bf0e6350b0f6dbb06bbb8a08e352a2e","metric":"subproblem_accuracy","protocol_fingerprint":"624755413dd473f97bfa598805569a937857b4644a94b64e0348aba02cbde007","run_fingerprint":"bea384eb645df97fa8901edc56e8a3d5fefb3179b7eb53ba672341f644e59385","score":66.8981481481482,"score_display":"66.9","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T18:27:39.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c11471bbb41780b90e6097d94fa891e1863026ba4991a704d8c11db973805250","measurement_key":"939ba93bac799179360831cd60400132a6f97ff844da41e332fc5df6b885ad47","metric":"accuracy","protocol_fingerprint":"63ee90334824e9cf59ed152b9627654b2fcb965eef7037ccf787c24b853603fe","run_fingerprint":"a9c3f5f2f38cac847d801519da2e4f6b461a954c4f5e352efaa7df692a2fe384","score":72.2,"score_display":"72.2","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":40,"at":"2026-09-22","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a801403c40b5c7aef1c61d7ed547bdf6aaefe42b0ce253fe31c8b757f54991b3","measurement_key":"035bac63caff4ac63fe6c5844b2f18d8cd861c1a40a8f8bbde48ff607dac8680","metric":"fully_solved_rate","protocol_fingerprint":"4a55027c3948aa511f98b5c335d5a91f898f964d2b20298753f01ca9e7840698","run_fingerprint":"ecc638fab9cee439f89a134c689cedd2db34ada3dd57497d3830325007a70043","score":33.588,"score_display":"33.6","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-live":{"benchmark_release_id":"release_9d2de9d5be7e9822af19f7b3","benchmark_version":"SWE-bench-Live Lite","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":11,"at":"2026-10-21","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"db978663dbb2e8f823709bb49eec361cd8b5342b51f92c98f9e4f39b2afd5977","measurement_key":"a43282d784400884ced9871256f4255672e6219dbbb72be048c3d2cf7cffe76b","metric":"resolved_rate","protocol_fingerprint":"ffb549af0b67a5007b617b9499e72d7ec536efe47268a7c134ee80aa49eda3ea","run_fingerprint":"9a3dadbe0b29ac5b8d40c45fd59ac8b0e3a6f22b96acb1525362a0af65952a00","score":71.66666666666667,"score_display":"71.7","source":{"id":"swe-bench-live","name":"SWE-bench-Live · Lite","url":"https://swe-bench-live.github.io/reports-0605.jsonl"},"source_authority_tier":"A","split_or_window":"lite-300-python","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_ac8995612553984b32210e23","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7c76a3394c9cc587309591a9d38eddf5a610e9bb80583a668f997edae39101e3","measurement_key":"35cbd1e08242d717dfd8d3890440fd919b6310086d7cb2bc4bbb949a744fbbdd","metric":"accuracy","protocol_fingerprint":"237f81a3678fd2ab0e0e1425a2d8bfdaebd0f2314ab95bd43b6ddcde4c74105d","run_fingerprint":"4aa566bf935ccb8ace357734aaba310af2b2afc731d32946ea575b837cf4ceb8","score":87.64,"score_display":"87.6","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_37e371ca4768fbe805410768","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f2c19d3ea0ff7daa8ad29ee653f57c22e09d9890f18b0a1c80cda076120cf28b","measurement_key":"de7721b041c2a25f5ab9d7e8f79c06c5fcb34bb1e9f0909fdd31268779d742d4","metric":"accuracy","protocol_fingerprint":"f0fbfc9751a9782b3b33aab1bcab998085606bcf9fb6b9aa78136eeeca10f93f","run_fingerprint":"f255c7983232aa9084d4cf19aad58ccf305681730d842489ef3e8eebaec704bd","score":65.152,"score_display":"65.2","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f57c79054ff4ab03f5deed77a317fe490b8fa5a39040d40fb49a24ea79d66257","measurement_key":"667fbb072d374c5a7e850e256a065413a1e9e0f120b16b39df517d1f3b0001f2","metric":"accuracy","protocol_fingerprint":"2d6d4e673a66f9deaf161c441bf0eeeab1ab980cb5b19761491ecc49549b85f3","run_fingerprint":"a0593655cd6b6f707e41587893477e13e8aa39d33fae81c7ed9aabc5a89a9ad4","score":47.143,"score_display":"47.1","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":26,"at":"2026-10-05T10:25:48Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"29ffdce71eadff6f6151fd743dd72a9a42350b584d0e22d79ea6509f370370fc","measurement_key":"148e8cf5ca523872e9f796eb0ddb8cbb78fd551d96aea4de567467803d09b41e","metric":"mean_final_balance_usd","protocol_fingerprint":"b9e308c17db60b50ad2b30391faed42194797f8c3a82dca4f1f5b099cdb75f72","run_fingerprint":"fa6f4efa1932d9dea8fd06d8d6792cdcdb1f0f54a03203805cd26d499e4f81a6","score":9235.248333333331,"score_display":"9235.25","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3a3f12ef819b20354dad02a8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c920b94d1841091f06765bee5d5f76ff60f9fb3f04fe1b1a1dbb2adf6650c092","measurement_key":"bc515c4049abdf4481a1e5eed769b83958eccdf48a4c7adc47a0064649931bf7","metric":"score","protocol_fingerprint":"cba944f0ea0e1d5985d9068e9134f5529095f8e82695f6146d1ebf7bdd2fde65","run_fingerprint":"766ef172e0f2e578d25e17bcf704b5dba742c0194c737e58378624a2fbb893db","score":90.294,"score_display":"90.3","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"511e8b5de685f77217b6cd2b86424d861b892173b2654d3b1fef45535301cccc","measurement_key":"aab8ffbd70d1d2a58e0a9e861c7315099686cbda69e96697bff2201ec4fce269","metric":"arena_score","protocol_fingerprint":"943a6b04c5ed0ce14cf9cf8446203aa7065ca94fab1753dc2a57897ae87ad14a","run_fingerprint":"205440804ffe5a16efdcc2516998a8e6016f52820ba5fc43720089c1f2a00d66","score":1809.8391605525123,"score_display":"1810","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_644045ef3ccf710aa2a97573","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dca96e0a47f9348e6b9d2c99a5e85beaebf86635a287f2acdad55e641a6b7776","measurement_key":"79ac90110b55b6ae1fda1b77fd78e33954165a77ee2cac1855fef99d48996cd7","metric":"token_efficiency_weighted_score","protocol_fingerprint":"ddbd7e67ba37d1654b6878e6bd07510202c2db31a4fd07c7af992fe723a0528d","run_fingerprint":"da671ad38a38519cddf2d1cd0d5c96ed3c98b906ee582c2da6af6912216c1dc1","score":31.20028142857143,"score_display":"31.2","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_ac8995612553984b32210e23","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"anthropic/claude-opus-5-5","model_name":"Claude Opus 5.5","parameter_count_active":null,"parameter_count_total":null,"provider":"Anthropic","selection_rank":2,"weights_status":"closed"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e2035d37eecf12bb79b03d144ef9b0646ab10a40cd2427a4a9502ccf9df88959","measurement_key":"edf40207de8c17144c99f11c82fba902f802d3a8fa81e05869892b8bc572fde6","metric":"index_score","protocol_fingerprint":"e2cd58476c62d709590df128f7e6f309788120d3a857d204e134ff7926fc6e7c","run_fingerprint":"1e254691d4341d3d5524408a40b477bae62c016e6a109b4f5e92b60f6b684287","score":50.976519,"score_display":"51.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_88989cec8b812f0eb187ba3a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:04Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bd7ce2f252445107005a7008f30b51a6594513a1091a2c57977842c3506d2d5c","measurement_key":"20f972d688b5a20ce89f1c9889b7fa5dd98b89d897690f2c61fb69d0a4f2c038","metric":"performance_rating","protocol_fingerprint":"3f965b4a622570f1f9a2075437a5db4a514450cbdac0122c9910bb000af2db2f","run_fingerprint":"b566cac034efe943b6fd21fcbd31e44f9a762886474cbe360cc361d56e466f3b","score":2608.82,"score_display":"2608.82","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_88989cec8b812f0eb187ba3a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:02Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c8785258edef6a28e5c1e3c36f5ebf92454bb2cfd78e5f90a3e19b8e94f67b55","measurement_key":"fe37771d40e7753f99b5d7d61c8d3ac4a786476eb5041b735c84f97a667677cb","metric":"pass_at_1","protocol_fingerprint":"1df53f9ac83d8582dfe10982c03cc721354a33671800571a398380f102d14684","run_fingerprint":"4b7f5fa1dbc173f882b8a9a390097567a144ed5be59c05c2623c10d1591f2575","score":68.3,"score_display":"68.3","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_88989cec8b812f0eb187ba3a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6be5afdd047ff07c538263aeb91400a37a8bf49f2c8b13fed7f43369e1a79c76","measurement_key":"54b864b18c8c5175488a1432f9a7a81ae4d3750f1e653f70ab4245b652574117","metric":"ips_score","protocol_fingerprint":"01f5243b415dc445a947bfff08782f7990e45798b26ccd0cb03bee3c2281ad68","run_fingerprint":"51c8f3fbe4e642e4223a5a3a891b4b402a611283285b57d11068bf39220991ea","score":0.10574985212598499,"score_display":"0.1057","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_88989cec8b812f0eb187ba3a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7fd7ac99a188957c65b18d9d7dd36acaff5937d98a5111f704b2e83416d967ba","measurement_key":"c9cb350279647fa00295622223c8cc8a775d1545db6c97844e9243766de9e8d6","metric":"accuracy","protocol_fingerprint":"78f9e5d2623fa0c0df7ebb66e9d9fa411b1e744757f72a9066cfee6e42522057","run_fingerprint":"f712039d59462b86bd57dfafcab59ec9a0196105ead33fcccf5544c2e79c6bae","score":28.0,"score_display":"28.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_88989cec8b812f0eb187ba3a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4f7232732eb5451c4ca10aa1ab40cc98c272267f60ee14dba7e96b938a04b968","measurement_key":"24eef2789dc683bd364a07a652945fcdabc706e972bd86d5f82d76ca4776d1aa","metric":"eci","protocol_fingerprint":"9d37bcc57f33aaa11b5ce79844c8a3be804c34656246ff039d46c4b9376672b9","run_fingerprint":"958d7a286eba8f15d769b76dc593d07708b44530b21efd15a23f58adcb3391f6","score":168.11,"score_display":"168.11","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fad73ddca55d063974c32c5e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":5,"at":"2026-10-26T20:00:37.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"01025299746a32bccae6ca2c95026ba3164866885364f316e43511d6f22b51d3","measurement_key":"fabdcc38e49f9011aa6b57349c7abe526b81d8c2c1276af6705ed53d2928ba77","metric":"mean_score","protocol_fingerprint":"f5cab8d251dff3632f3f2c87610226684f9bfa0528ddb04c22cddec3c4a0ae89","run_fingerprint":"b63903e3688dcd7419a45ed333ee26c800d2aceed4aafac7879ecddb186475de","score":90.87719298245615,"score_display":"90.9","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_88989cec8b812f0eb187ba3a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"48cf421319097e7b8b0604e431cb62c982f59cc9988f99244fe7222c847a6305","measurement_key":"07cbffd23ce00658b9959f11d27bd2154d6fbdc0d7e501c9b2421b809ad24fa7","metric":"elo","protocol_fingerprint":"42b1936483c5fc488f45eb2b6d7373b969098a05bacf7c0e9b60c70d3453c03f","run_fingerprint":"50fa39e17f118f3ee85a2caf2bd447b3dce5f8ea3378fe0149d839ee90cd266b","score":1475.63,"score_display":"1476","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_88989cec8b812f0eb187ba3a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":5,"at":"2026-10-26T20:00:37.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"42ac047d1577f4c173cd5f3ce295514e8adac126aa2fb639a0b1676953910fd8","measurement_key":"e179e3c49faf6e6752e132d0f71f0adc2622bc8ef28d85343557ce65ba4ee363","metric":"accuracy","protocol_fingerprint":"ae5a92fcd50d67c04e43cc9dfcdc064be19627ff985b9e4fb01f50e9edd1e4d9","run_fingerprint":"f5dd0bf1f989e8357b1a1522eed176feb5109393daad95d452afd9b468a8fca1","score":94.31818181818183,"score_display":"94.3","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_88989cec8b812f0eb187ba3a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b360e218054c8eeccf0a39b0d88426a3fa1ecb931391b76acbef5bdebce3049d","measurement_key":"31153ec5c1374d5b0a219affa5aee9e524d99a8187c629316ebbf2c7bc943863","metric":"accuracy","protocol_fingerprint":"78d83fbc32e7b318f91156ed47963899689d5387245b7b400d58ffcc26f1b9d5","run_fingerprint":"0cac11b4c96f9dcf1f45592709433961c7967adff7ede6f5e3b5d629312cf1b1","score":46.246525,"score_display":"46.2","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_88989cec8b812f0eb187ba3a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3073e2d26a38c6a5f34d5b38e9d7949cb754421a9dc55068db9960cd59ff9324","measurement_key":"a51f291c97c662f2e07dcf149e5a18be2261dc6d18ca401df85f05f669f87581","metric":"accuracy","protocol_fingerprint":"e91ead25b62406b52b2af4bf8db48d0a75455b005217ebd701e5078a505c1fca","run_fingerprint":"2ed2d0b4daedaa368cecac9170c2e6ee24440fc463eac34dffa3d8984f67af48","score":84.682081,"score_display":"84.7","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_88989cec8b812f0eb187ba3a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":5,"at":"2026-10-26T20:00:37.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fc8b5f1c591d90ad7cf10828d4c74dbc2cc9b0b6ccb3159a3a04e8824dd47273","measurement_key":"1e1614ef5334cad22d2d2bc495a698f93a96a64a6028d2e880a8171a00062cbe","metric":"mean_score","protocol_fingerprint":"a3db0f25c15dd80f8f1df610686cf08d4d7f681733644a3036d4c846bd1bb05b","run_fingerprint":"3c08b444337e4391b44c6c6f56e4cd6422a604266e7f6e16e41713f09e795c0f","score":100.0,"score_display":"100.0","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_88989cec8b812f0eb187ba3a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:02Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"629a67343581fa25ff20776bd47e10625d338eed4f067c86ff8221b127daa859","measurement_key":"698cfcdab33eefe8ce6acac2cc09b5b0f42fcbcf032fcfeb2bac7bff3f664a02","metric":"subproblem_accuracy","protocol_fingerprint":"eecea57ed4fdc58974fe4230b5b34221a300959c5e5c6a80150344fab26542ed","run_fingerprint":"e82f6853f4b542eea146da946741a04d117924a87c89d29c36afaa9584474ce6","score":55.0925925925926,"score_display":"55.1","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_88989cec8b812f0eb187ba3a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":5,"at":"2026-10-26T20:00:37.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"98707626e65cfe1e239493ebc56900a13614bec6a9e27d6430ca8418ad5c0426","measurement_key":"d20a2f3704c21f7e6cde2d89b69e37d1bd4923595921c2b0c4f773356626274c","metric":"accuracy","protocol_fingerprint":"ef6c4f75d3d21789ddb6c88f010f9bb1d237f50fd153ff31736b885e1189bf67","run_fingerprint":"f8f4497949fdd184b8c6760e812f6dccb2c1b695f71b89e8c4ff15ec2d0ebb68","score":57.3,"score_display":"57.3","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_88989cec8b812f0eb187ba3a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":5,"at":"2026-10-27T03:18:55Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b505166eb530691643f7b9d782f4784150ec37d38511f0a0a2bc16d3ba81f03b","measurement_key":"78cb107dcd5e20179692c235ce9e46b5e044d993ad68f05ad1c551aafc1b4c65","metric":"accuracy","protocol_fingerprint":"cb3e5222b38738b00835f4a4fd4da5e4bee7fa3736fce859b040c4f3c15a998d","run_fingerprint":"511b882edee979bd4f47171c205574a0793a289f21aa6295cd006670bb396f9b","score":49.495,"score_display":"49.5","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_88989cec8b812f0eb187ba3a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":2,"at":"2026-10-29T17:25:04Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fc8242e60b385466c5589af9c89e15b77c9305c418c3e7e702fb6dbe834f6d40","measurement_key":"16738e36852bd91b0ae19fbeec7f9d27ba2b4c25aa5019a8b03476b17bbddd9a","metric":"mean_final_balance_usd","protocol_fingerprint":"b239c1b99ae50cb636faa6d17469451a96b4bc9dc248ba558a9dcdfc2672f696","run_fingerprint":"133c331a282d0dcf12cc0e2ac4cee13f1ca70236865c16862956240d20226b7a","score":9107.458333333334,"score_display":"9107.46","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c68c5fd57a2d216f86c6b300","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":5,"at":"2026-10-27T03:18:56Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f4d6c1febb85adc142a91f2cd46db6716b055c23e2e675349948585d2462cf7e","measurement_key":"a19a522690031c1496a8db890a3e9b1fd5b2815f26b51671360545184858a70f","metric":"score","protocol_fingerprint":"41e79e2964f6ab021ac4242fa0cb152af108e6a58e724666dae2ef612673913c","run_fingerprint":"42d42bc3d064a7e97922db8972a24497c58f63ce801c068b3378dab3edde8abd","score":83.997,"score_display":"84.0","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_88989cec8b812f0eb187ba3a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"35f541080c298bd325b7e31a8d583190bb52860bba503287a8fb190661671c0d","measurement_key":"372ed0f76996ce160754b531e1b3875b66d48050df42941484954becc5cc484d","metric":"arena_score","protocol_fingerprint":"f7dc56d40d4260e5791c0016449a4942d23fd3ae92607868c2f304f3114e811a","run_fingerprint":"a9a2db9175449572100cf67cb852f4db64bcd2bce347c006f0b41c4de891f7b8","score":1672.6547058209349,"score_display":"1673","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_88989cec8b812f0eb187ba3a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":2,"at":"2026-10-29T17:25:05Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5e02557bb2443d43895993337c9186bcf7630d0baa8ceff5277ffa501b23673e","measurement_key":"98dc34effc8d27f721adadc34740428480bd2a680dfafd176dc7fe877769d6c6","metric":"token_efficiency_weighted_score","protocol_fingerprint":"ac684f33d15bf8e92dc72115f8694925aec2eef88d6f0f9917e40d25269b7ff5","run_fingerprint":"48bcdb7c34051737694f4995e3b87913de5d382533bd0b03d961d3b6f4bbf111","score":28.086310681818183,"score_display":"28.1","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_27776d0f653863ca06f226d9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"openai/gpt-6-1-terra","model_name":"GPT 6.1 Terra","parameter_count_active":null,"parameter_count_total":null,"provider":"OpenAI","selection_rank":3,"weights_status":"unknown"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"61202f3a1118b82d71e592bcb2f622cd0f1b8fe1614f0d358d8ee944aec66ce0","measurement_key":"4abd81003140eca3ee868a605bf36755a7057dbeb79262df6eae252cf3d3442c","metric":"index_score","protocol_fingerprint":"b5ac69a22b19ecaf3c8f59e2bfd80fbc3ab11425ff38427a62926045af452cc4","run_fingerprint":"b8a13d852cb5f0d8c924abb074aba94f685e426d96e598cad1e2909abfab9249","score":54.508734,"score_display":"54.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:15Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0deccede355734801a5179354ec936e3b6168a32a7888b8b4f34494fe384b4c7","measurement_key":"025b8ffa8b8d6a0b04b0291b84eace55988c454914b4b91da90f3356c97328b3","metric":"performance_rating","protocol_fingerprint":"a6ecf64ee9aeda07ecff54b9c2e22e3a2e70e22b41b4786096462fe7bc5980b0","run_fingerprint":"b0062de33b311a624d070229cd30cbb861650ac79b3c990ea054876d35198806","score":2743.75,"score_display":"2743.75","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-10-01T00:44:56Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b01b33724562c0286fa5472634fddca4cd4bbc683d29d379eb75a7fa3855d4f9","measurement_key":"f1c6c79ac47ca60bd36a498a174dddf162d455da2122bc6026ff209e47698364","metric":"pass_at_1","protocol_fingerprint":"689ad11ccd00a883405b1a07ff7fc60580154bd6734b5797405b32320d760c7e","run_fingerprint":"ce1318e9329a8b958f706b9305f8f005548c950e7fceaae2bf4040ba1344e9ef","score":60.0,"score_display":"60.0","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":26,"at":"2026-10-05T10:25:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3aa17d51a5d744f6cdd6c9101ee771d01dfb0493fae5b19d6d08663207e0c1b7","measurement_key":"18b2c8011c18586b2f309d5e7f3a7c248d7eeedbebc1be7789b9cb0f5116bbb3","metric":"pass_at_2_accuracy","protocol_fingerprint":"5d64108a49bf54a9fc6a3b3849dbe4d14948c397253a818f5ec9b237ebd6a6d3","run_fingerprint":"a80f9f67dd9d4eaf9be0015eef7c72e0d531eab7aee83139778a3222da001985","score":96.5,"score_display":"96.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-10-01T00:45:01Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"df5abfa7bdd40a5503867a372e0c8fd07426aab0231f48720f1313e159ce5daa","measurement_key":"bfb39175db643b97989efb59b6e2fa830a31791b2b8693f11bf5c4abbec02537","metric":"accuracy","protocol_fingerprint":"2921570a0438a4d0f49597cd194c8d87d5de98dc53a452863c498b702c27f139","run_fingerprint":"85c64eabea4dddba36ea180ffc8b75b5ef01bc8098269c30fcaa900e3cccc788","score":94.16666666666667,"score_display":"94","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c9bf739492d63b0b37385677093c2ab362f2e0e11ba580d7a833b3bcf0c0c414","measurement_key":"c4ade7ff8a0ca3f05880fb8bbae5e99dea75e0cfde7bf74dad2ef811f8dc6a9a","metric":"ips_score","protocol_fingerprint":"2a681a457c208dcd574e1bb7305ab92bb199f91d7a120c9c5c0e9000ed808849","run_fingerprint":"89f47e8a7a683995589c62fef33ab70cdc3d2948f9a3afd27308530a1e9ca1ef","score":0.12466693893518165,"score_display":"0.1247","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2221aa322dfd3c62556f67843cb98a432a3006c468b6ff56c292a9cdaa301322","measurement_key":"16c62123acab2c4d5de2ef00b3e2656dd1c744bbc4ab80628c9af5641ebe3975","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"f4bb869031c0f32744611b52574eb66455574f988007629b0c5ec209e00b5695","score":1481.3279556386954,"score_display":"1481","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T12:40:12.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9c14f265e6a72a7799e2f206071a46d79c017b84cce897321fd2933b209b1df6","measurement_key":"85a132b1fdc214ad98b3404efbf9be2b502d3a9f194b817d8d4d5a6ea282c045","metric":"mean_score","protocol_fingerprint":"d29693ae5589cba535a0d3ac93ef0e493c88c462f05f6523e35f7724a5112601","run_fingerprint":"6d48f5aa7a939bede8402e6b9dc42017bb6ce5f5716f73615b437e7086b7dd4c","score":68.0,"score_display":"68.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"54b585f00e1319c168c9ad7757d36ba1806c667b29bf72a57ca371e5495b4b3d","measurement_key":"eb9227f5dd52a55134d22ec7e4128d6ad36155391e022580b6f08a227b6e7eef","metric":"accuracy","protocol_fingerprint":"3b319bb2660e1142e8aa68dedf83a1e48cd257c8e82fdfaa3b3d28704f2f94f4","run_fingerprint":"6a55635df4c3bdba50646808f2ee0c2a1799da2ac1bce88199b00551c249fa37","score":31.7142857142857,"score_display":"31.7","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1e1811f89243f121b6af42506a39677fbea395e75b3bb56c2c4ee4b4fc882413","measurement_key":"fabf074a361028f8eea855ca83450e3cc18a319c9d83e611d5ba4feefde5f2a4","metric":"eci","protocol_fingerprint":"58c3ce1c018c38dd41fd0511a3491eb91908b10724bc3992a5b438b4628094be","run_fingerprint":"8587ebf76c4a6fe19732affec6df0f1997ac73fb790506f95ff039bb88c679b3","score":167.82,"score_display":"167.82","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f344b195b71bb391164d5d96","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-10-01T00:44:56Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0d8191da8224992f5f8cb4d65bb6d2f27ec4f4af5e641ace838db64d9c095055","measurement_key":"d5c66f8c0529b9fd95242cdb1240754a2a358f20b1a42110d5cbeb1bb2e164f5","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"a162760f44520a96a355010193409303db46962a0d7c9a9d64a0e8c05c69da1e","run_fingerprint":"38569a3c91d174208e19a8061c505abd58b3946f364a068f87c017f3bd9ff3db","score":50.23,"score_display":"50.2","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_64133a3ee4324a3d4e8eabda","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":32,"at":"2026-09-29T22:00:34.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"30a05ffc0fce382ccfaa265f7f38b5f99b57e1477fcdbd167cc050cfae90b8e6","measurement_key":"bf181c795e7e67f5211cae89bfc6d4a449885817155853e539404adc48facbd7","metric":"mean_score","protocol_fingerprint":"702c9408f392e2b8a214bd0c1b07cc3f8e14d785c34bb58e89fff092a08d6449","run_fingerprint":"b4ed9d4e8fab2f53f15ae67596c0cfc5882d1215092f666334ee6ed032ad1152","score":93.6842105263158,"score_display":"93.7","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"eb0491926d90b0813a9ec5fffd6cf863c893eac16f43dcd4358ab567223e5070","measurement_key":"6328799432da22ba6adbefa88c7505ce45fdf4c663822a4068c51ab48c10021a","metric":"elo","protocol_fingerprint":"d757e6a98dac42027709d8e0a6ac15ce67c2dee656acd2b19cb0474732f791cc","run_fingerprint":"5f96da894d2ed8ab3a66a1eaa85b96f885f6dd1ebff40ac96f6a4a8d3989dcca","score":1608.89,"score_display":"1609","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":32,"at":"2026-09-29T22:00:34.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"02fef9fce5b543000edbd124fe48d58a480bbfbe75196dc083b11693a3d900c4","measurement_key":"f963258de5773e46dd5ad503e86e3927c90c3ac86985998cc5d418318cc0378a","metric":"accuracy","protocol_fingerprint":"5bc1057a9127eb8745ece81bd45ce8e12363f10a506b09c4a0e9d6621ed4742b","run_fingerprint":"363713a747ee237e4774b09ae00247b2257c4c959944d72159c9b093c6c0cf36","score":95.39141414141415,"score_display":"95.4","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a81cfc7ab685b5e67fc1aa528c1df8a92f309613a5064722f22b0481604d746d","measurement_key":"613a84ef3120046be4f311734404caafd678e449a6da468b42b266a6a08beffe","metric":"accuracy","protocol_fingerprint":"485a315864e86fddb023767c6d4016884ea0cf92ac39c877e9189aa0f652b41d","run_fingerprint":"46440da5ae85421e5a475347aeaed5fe756970a6cccd6cd8d85f84b782eda98f","score":52.91937,"score_display":"52.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-09-30T18:53:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ac1ad386b9334cccbfa659158bc6ef6e6fd111200b2bfe2441318d073f7296dd","measurement_key":"ebc8927d522b2624e0010adba7e3f2a1848ba6b87af749239f264732e7fa2857","metric":"score","protocol_fingerprint":"bd1e1840c14c84d69971323ad13972c08dd9719d4b25701f7af54ad9f2c5e5e2","run_fingerprint":"b7b220359511c0fe8292ce5b4ac9ea2bfa23b0364a149e7184f5c05595a07d42","score":96.889,"score_display":"96.9","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-09-30T18:53:19Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0d296e2ec3c6a8cccfdce9282771e83865c594c47a3edcf8b5be2ce9908af84c","measurement_key":"ae937e4721b7fd90f8b8e50f31f26927a004c6046eec0aed391d8b11d528cf6f","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"540319f9cd2912df1ebc6d1937ab8770c99306c932446b17d1d31bb059694d6b","score":81.61566666666667,"score_display":"81.62","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":26,"at":"2026-10-05T18:36:30.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c0440234f551ecf8be7bfb951f07cbff7d1a8af1ae5f4751ab05304324d93e32","measurement_key":"b17d37b82cc934bac43883d0635b3efbe9653a1f8d29b7f19a3fae24a05f1d2b","metric":"mean_score","protocol_fingerprint":"5d881538bdfbf8798e04801451260b635fbe881029d76cf3e232f00b690eb88f","run_fingerprint":"bee2ce578d192cdeaf841cc552636205b56f0720b8b7192812fb6b4bc462a464","score":61.111111111111114,"score_display":"61.1","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1e3ab91a70e56bddd692fe4155285bfe5ad4cb667b6d5ebb0a4fbb22f60eb313","measurement_key":"e4a95c9e694de1b76c116ef9681ae5eec89c85330c460467fb6041dff7a9134e","metric":"accuracy","protocol_fingerprint":"9921d58127eeaee7b45d9b47f13c5c6fa578e8390356c58a0e2e3e2b423d1c42","run_fingerprint":"3caa28662f526b2d8599f1294fc07f8a1ae99d0bac9f781481113fa5085b5b2a","score":85.953757,"score_display":"86.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":32,"at":"2026-09-29T22:00:34.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"781b25548b23965319b54f0dc5d2e1036aa647f4de199b52cea0c4148fa10072","measurement_key":"3b14447502e9cda81405525b862c77ad0ef556b4024aaef81c03903f5c54760d","metric":"mean_score","protocol_fingerprint":"5b9da07aaafa7046f2395a09b4048ca4669bbb659b767c8dcc651f9e26ec7a95","run_fingerprint":"1833ccdc922c751e1070e5103cc85af255410cad0be6334870ad6e758a1233c9","score":100.0,"score_display":"100.0","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5037646c2374de70feeb79406e431ae3ab89a019d70fa375f9ba94cc5c113ae8","measurement_key":"219f5f4f2a5f4205392ed4f219da92ebaff6aaccc20722de4dbc6eb781b5b71b","metric":"fully_resolved_rate","protocol_fingerprint":"9d064e8c7fb4d86c8c99771f88cc81639f127d01ebce2af8f1ac720e8b5d3c28","run_fingerprint":"1c8af16e44bbb69bdfb45d75b91661c82514ccf914530bf6ec8c63e0d36474a9","score":3.0,"score_display":"3.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"974e0dec0661904b54a5e9897bf739176161a8541e84c555417b5dd29ad916da","measurement_key":"443b9506276c7ca7c4d7d3c8f3e2ade16d095d3bfc03d1bd57600a50d9dc7e4b","metric":"subproblem_accuracy","protocol_fingerprint":"0b83a8eb7770cd577823d10bd155718fbdcaa8a113699953e15607a69cb8adc3","run_fingerprint":"c3273d1ac5304520aa6aaf7ad13c9a84ee06ce979b6444dca34277bdb70d4a38","score":54.1666666666667,"score_display":"54.2","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":32,"at":"2026-09-29T22:00:34.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f2dd5977f5b73df643d315db609c420643bca36ce0975e713bacd9b3afe8150f","measurement_key":"627e4800b524c8bb85632c656ce39ec46e2026b2f4eb3b24656022d017782a61","metric":"accuracy","protocol_fingerprint":"f6b3a1b039acb21492a8c84d82bca5974ab8d86acef1fa62417b47cd67aeb27a","run_fingerprint":"322d270eb347c7d03a48f80eaec213674356187082574815c4a44f658c9790d7","score":73.9,"score_display":"73.9","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7b0ec6febd86a525d5fbf9c0e2fd0967498e545a59b6ac69904c31e6b2fccfc4","measurement_key":"694ccdc00f9b91cd9e34c342cabfc60369f64862ae8128c8e46347ba2a950689","metric":"fully_solved_rate","protocol_fingerprint":"7d2a28ed00d6ee5b747a79d0948a58930c2238d3e0c93f1a4b49e4ff84353eef","run_fingerprint":"fd7fa5253eb6ac797829361f671b9701bf8783b4863785c6c08663baea3ee5e0","score":50.763,"score_display":"50.8","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-pro-v2":{"benchmark_release_id":"release_d9b58bd286ce316ccf0ed891","benchmark_version":"Scale SWE-Bench Pro V2 public leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":25,"at":"2026-10-07T01:44:58Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3b88d1f28d380895652708684db5a4672afc14948dd6c5d23b797f7c76a3af60","measurement_key":"082a3ece29d4b89a8f240b079357e2f07b4b019b8ab134c54975c1c77f639eb8","metric":"resolved_rate","protocol_fingerprint":"cca389c42ef5abaaa08bbf82cd5f62244102fef8aa6b379b1b34c1efe3ead171","run_fingerprint":"349c3f5ab92dcb96500c5aeef3b8a049c6611aa2951eb4450897b882f57514b1","score":96.11,"score_display":"96.1","source":{"id":"scale-swe-bench-pro-v2","name":"Scale AI Labs · SWE-bench Pro V2","url":"https://labs.scale.com/leaderboard/swe_bench_pro_public_v2"},"source_authority_tier":"A+","split_or_window":"public-v2-642","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_459bcec00071cd59cf8454da","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2369a44e333a694b1077f238307bcf8c50fe5070a83e16703119249624e51a9a","measurement_key":"13f6addb20b23a9a8976f7756f03dbac89493754a0a8dffc78d1831636396489","metric":"accuracy","protocol_fingerprint":"6afe21581a06513b462b8119e0c1b4468ede7836d53b0e04f2144bdcf701b0d3","run_fingerprint":"36d63a23f595004e87141d8db9d1cb74f8d46c4e8cf73e7a6827b7c177432c1e","score":55.051,"score_display":"55.1","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"225aa22400e05396bcb6c788fe4c2789f11746a42b92e1f11254c9694b45d8c1","measurement_key":"eea9e15efc9c88c0d690e4019e3c46cb9612907c14fe09269ced8a09f0f1b8df","metric":"accuracy","protocol_fingerprint":"0f8ce86fa909356964117c1295b0616b2f5856795f89c8e261aaa8a91095728e","run_fingerprint":"d872d3a00cdd8eca8a0b47d44e642bac26ee95e55a992ba9dd4f54eefdf97aec","score":52.857,"score_display":"52.9","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-09-30T18:53:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"538d59f6221a23388ff97077a4577a9dec797f329f3eed4bf3528d8cfdaaf56f","measurement_key":"85dd4143ea7ebb8e41061c958344ba4f4295c4a934649379c731a10350ecda57","metric":"score","protocol_fingerprint":"4973493a3ee4b091413e398b03d915d192a4ab752497d5231d7ee119e00d73d1","run_fingerprint":"39d2965f3c737993ecf8fe9c96769dae1d5f437b0004bdb29796b9c949b316ac","score":88.931,"score_display":"88.9","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b39bf680dc05ec48b4807d695fa847874ae1f7b6c48788ff69fed124f29d4e76","measurement_key":"89240d509c60b0dc0f9f11d456df1fd1fe00de3da6ea40f341c2b736d4b52e5c","metric":"arena_score","protocol_fingerprint":"a0e12b15d7f0ba66d24db72fe1481e4959c68e3ffbc550105c7d4f27eee1a02f","run_fingerprint":"0ff905587ff975b45288ad36ec5d3984c60d61f9175b3a30ecc4795e9b586d5d","score":1750.568215754016,"score_display":"1751","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4104ef8cd84a9215477511fe","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c8a5a2bb1fd19e7239e259bcacf5768cc990e4d186c50435e7ffdfbe6337782a","measurement_key":"23bdec8925055e495002ece4959d8ced0d2b566f86f322f7e4e466d6a4dd7e42","metric":"token_efficiency_weighted_score","protocol_fingerprint":"686c8f8848fdd05629f4c1d78a419a7e068546e2456745fb63fb878603cb7f29","run_fingerprint":"f7dc18ae893d3bfeb2b97eb3e08517ca78628ebba89ae8b88daf248fd6e085b2","score":38.25364136363636,"score_display":"38.3","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_459bcec00071cd59cf8454da","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"openai/gpt-6-1-sol","model_name":"GPT 6.1 Sol","parameter_count_active":null,"parameter_count_total":null,"provider":"OpenAI","selection_rank":4,"weights_status":"closed"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6cb5605778e50c78e1be5f11ad04f85cd35bb4b76ab59778b9417e434d278500","measurement_key":"ef0463ff4f339e91439b72a805aaa1043c8a6d90c4b9404a38e449077e8599d8","metric":"index_score","protocol_fingerprint":"1c775fc17e5b9f8df64968c1f24fe97a90028397c48b50a2dd3880e26b87eae1","run_fingerprint":"f0871bb220ab40f9ad0e37064196584be97a257cb0c272525e42f88d4cf42175","score":54.241334,"score_display":"54.2","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:16Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5d3459670495c89ecba8015664a8ed56a3e71d5e22604405452ee1e263580cd1","measurement_key":"1d386b70a1005ab7022527f5e2b69be1c7fc27424517585d779a63d262bc560c","metric":"performance_rating","protocol_fingerprint":"720c31a81a42023e24e49c35e2b042b618ac030f394a64312e7e7e475578567d","run_fingerprint":"88cfcac96c3ec489d1e8fc9b5a87a64fbb875544c0190f525922b8e72afa1698","score":1819.12,"score_display":"1819.12","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_58c2b77aab1a8f5d917ece79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"77e129d73ab12f49050fa06cad811a14fc8cd5263882966a6094965eb35129a8","measurement_key":"2cf958c32342a95cee5520fe9145f38adaf5f864f96a7b5458270a0973875bb7","metric":"pass_at_1","protocol_fingerprint":"ab8e1c920a10c544e177e19708ef963e04ecb54fb4b6b66f7e682ada59371f5e","run_fingerprint":"169edbef85191bc3aaa57bb82084feb3bb2bc7d85174f19327038013959e6498","score":75.5,"score_display":"75.5","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:03Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5e5b73084b7d6dbb8356eddac1a6047454a90c35e9e6e7316cf26e376fc6c6eb","measurement_key":"8863d1bba3f36fc7615939ea437e32d52c3a183be54cd99065cacb6c9b3bcf14","metric":"pass_at_2_accuracy","protocol_fingerprint":"11aeb5821ef99877ee2e091a89e9596251f22782d05b6fcb012811273f71bcd1","run_fingerprint":"3cb99f97ced83182fdacd242bc7e01b4c6b9100852d6c67d54b03ccccc7705da","score":96.5,"score_display":"96.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":10,"at":"2026-10-21T22:23:16Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a07f6b0dc7f91f5bd0f3985f623a56fe2a84a80d4bcb1a18ef73ab1e7931b587","measurement_key":"dd0cdb263093ee5ecdd366ec53fc99d350e2b38d12207c514e71d81069a6756c","metric":"accuracy","protocol_fingerprint":"b107ba3fb62ce257bd87b3ddea05d727353371665b5fb97a169730e8c8bb8eb7","run_fingerprint":"b72d6a3c7f0a1df76de7dcf19ce05730291c9a0dfcb898797020f8404352e36a","score":83.88888888888889,"score_display":"84","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c047341bcdf46221302633c9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"802b776037082ce7e32a945717ff2d556acfe555540f56597348e3daa669743c","measurement_key":"00b07e45c7c785982b31251f84c27a56cd4c3a2b89cb8aef673b1029ab047478","metric":"ips_score","protocol_fingerprint":"5c15887b2bb803c0820a3cdad93c513eb24924b07f6b665cb2ba3a916d44e298","run_fingerprint":"5c1955a8f0caf4f0312fd184bfb31efe21a249b43f32f8c33ee0a2ade87afc6d","score":0.1383722472009646,"score_display":"0.1384","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"70a60c175a36a813387d408f0e65a87078889cdac6dca731382a06ba99090d5d","measurement_key":"347b7fe226de444500323b1daf781d0a6435f7121c5ce4b584100d2d39f48b92","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"ddd252fdbd9fd816ab8185813c992a3f0bf6d30fa8a86b9abdef8042967a0394","score":1477.1495460775536,"score_display":"1477","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c047341bcdf46221302633c9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:00:38.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"77a3e6db92c2bcd1c69ebe8d0149a16fb4ced19a7cf6bfdd09c4b9626bed3f2b","measurement_key":"fc040bd7531a9dd6d73999e7cd41fb8e9e395fdd7018d7b8451670700996e5d5","metric":"mean_score","protocol_fingerprint":"561b8c04383c8f9c20dda019b47f055033234ca9a8af2a2d2b0ff1c1c79fd3b4","run_fingerprint":"9131b8c10c0a2af295b692eaac110d0e654c804111f7c7672a209262d2aea778","score":59.0,"score_display":"59.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:03Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"26401a2d36607480fae57e101c10a998fb727967046f3646740be75265c8efbc","measurement_key":"00ea966dcc7296ea1968b673585bc85817278cf0c141236d89dc7473dae98a0b","metric":"accuracy","protocol_fingerprint":"9a8e6be9552e6c546fc2d64bf9c242d863e2ef802325e92e090bbadf9ea86d55","run_fingerprint":"63868f49baf03d3698ac2ada220b32c103d6b1e1b9a339815e5e574cffad7ce2","score":31.4285714285714,"score_display":"31.4","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"cursorbench":{"benchmark_release_id":"release_9acebd5b002e9c3f18a30606","benchmark_version":"CursorBench 4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"76cf8b98dccbee48a37b96687e344ca8a992af11824feccc29f8078c6e855be7","measurement_key":"ab47c73972b1a84fa3f9b65902882d2ddcfa5f8df7952041f6d5c984f85db708","metric":"score","protocol_fingerprint":"425ef424c3cd3ddba464844fdcca8a9ab839a0a814d8fbeeb9735c6d71015b03","run_fingerprint":"4da71e44e75fe263a8f77bfb48641d0489b2a22e197a013ed0505c2c529e5768","score":55.50000000000001,"score_display":"55.5","source":{"id":"epoch-cursorbench","name":"Epoch AI mirror · CursorBench","url":"https://epoch.ai/benchmarks/cursorbench"},"source_authority_tier":"B","split_or_window":"official-current-suite","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b7802ba767c4ccba35e1b73cd94d70d27920ad2709032e0b7d7ce679639a4271","measurement_key":"1271f2a6035983ac03fa3bea4280404f75e0ce3cb80d1b3cd6e78df0b84672ff","metric":"eci","protocol_fingerprint":"143062028388ab8f96c0a8e313d95fd93babcb5408afca71858f88353a6be75e","run_fingerprint":"ea720f580603c39cdfe37c0f3c3fcf6b67c083e06df6e36836f180bb35a07cac","score":166.74,"score_display":"166.74","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_79445b70144959c79964f01f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4177309dcf39ddad3ceb77cdd62ba57b6095de3ea77ba1ccc3e1fff9e7abd040","measurement_key":"abb88d2339f40db5f0aedd7adec5269badac358c21a9b4a3b8b5b5f3c45fa26d","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"3d7c5cfb1c3a83f418c179444db1a506184963910971b39d21696da7073e9e94","run_fingerprint":"c3974abb3f8a6e20e6f4bbc27c687d15c386d26979ec0bfadba794d97a4c176b","score":52.09,"score_display":"52.1","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c047341bcdf46221302633c9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":32,"at":"2026-09-29T15:15:14.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f888cf48c322de468cda21e087877d752687923bc04f494f5b6c550f794252c8","measurement_key":"e18364e16aedc082f6133069036a8c252b26472d17a0648cba21b9c07ca3b1c5","metric":"mean_score","protocol_fingerprint":"3be3e4d5ae97d1beafca7a96a0b7ad657325b3715a1928728c8c592421c78f2a","run_fingerprint":"c3e84c26146933e092886d23478ddc096e9a38f565a21ca7d5689dbc6d55c530","score":88.7719298245614,"score_display":"88.8","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":22,"at":"2026-10-09T20:33:50Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"21779bbf3799a59ea33113b39c5601977fbf848e712fef82cbc98a19f0a3fb2e","measurement_key":"74ba12c07cfc5d7888cb4676bea474038a94451a90df2e345bd0b857dafb8c3e","metric":"elo","protocol_fingerprint":"daf855b28ed3d26531ed17deebddeebea38317b0c8247cb9f3023251a6b44a4b","run_fingerprint":"422c113f97521fb3642a9bb82d534fbaa0a2516886742e74cf5a92c44c7a0a0a","score":1837.82,"score_display":"1838","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":32,"at":"2026-09-29T15:15:14.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b6b45dfa195b66274c167f7fbbc2575d0dbc24ef150d24e43dfb0ceca6c28ea9","measurement_key":"13070a29f5cd011d18cd8616ed8df808f30e33ad386d9d6105b7d912e931a241","metric":"accuracy","protocol_fingerprint":"4a1225d698508261ad8c8935af5017f4596cb88e40c0d3222b44ae5f62fe27ed","run_fingerprint":"d7098d469e5249bd3e9b6fe35ed6e9d4d9d5b716382bab4caa0e6ffb52ad178b","score":95.58080808080808,"score_display":"95.6","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_8817af9d9a0235bce0826e22","benchmark_version":"HLE finalized 2,500 · Scale protocol 2025-04-03","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":19,"at":"2026-10-12T23:23:20Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a2cc7e31029a2d13081b97228acf7d336c3a93b1f0af0a802063c495870bd47a","measurement_key":"f3127a6632f6dca03116b8189add1c60c07c62f5380fabfbbe42ed2dbe0870e9","metric":"accuracy","protocol_fingerprint":"eb20ea3792bf1f575ce9e7ba773088f1bc2e22631038bb5a28c1ac6bc49d8136","run_fingerprint":"f905aaf22bbefbe37d0dcfea3a9a0a772727b7e07a91a98b4c634186568c2339","score":46.12,"score_display":"46.12","source":{"id":"scale-hle","name":"Scale AI Labs · Humanity's Last Exam Full","url":"https://labs.scale.com/leaderboard/humanitys_last_exam"},"source_authority_tier":"A+","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c047341bcdf46221302633c9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e1c6716641f0656ca993e8f0bb91c26bfc6fca6bf29b9f2bd3ccf9c6823eb56f","measurement_key":"4f6099e75ae09fb1421a50b7a63ae3f38b1c7aa1d1583def2fa7f3fb6abb4ee3","metric":"accuracy","protocol_fingerprint":"340e2cd39df0fccda00b3edaa8ad0170939d4b185bc6d2fb1a80d184da0eee7d","run_fingerprint":"83e9b61598260144d1969fa1b07d3ffa313593f7c701d582579f1b942361b6d1","score":54.958295,"score_display":"55.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6255606218746ac71533938cc5801309585d9be266c34d698d000324bc405cc9","measurement_key":"8d1949f119194e7aabba664bdc7bac483f63103baf4616c112a76aec2afd8299","metric":"score","protocol_fingerprint":"1b78bf03f5ba3ed0c2a91a378163858cac3be88338879397dd5b6d36ca883bc8","run_fingerprint":"4e3abb35897aa4d3f0df79e07d9ae9150ac4c66b3593c89a79f2300cdc2643bc","score":83.056,"score_display":"83.1","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-09-30T18:53:19Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"561de4fc8e94bacac3cd657eda4b8f1aa7db0247922ea3bcb7b246ef0b236cbd","measurement_key":"9cc15b0e6328b5936efbd12031be5a44f2e230a0540aab7c6d3b38b68fd2ab30","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"a7b05f561a989f788466b3093a8ee4c8f5051fd43244727adb6de5d45f159841","score":75.67214285714284,"score_display":"75.67","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":27,"at":"2026-10-05T09:05:15.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"487c6e4a443aa00b259804e2baa9a677779803a42a0b796412808e616fe5c54c","measurement_key":"dbd6e58357f226823968bb719c262837d3d8f921cd47282b5e9b53b40070f048","metric":"mean_score","protocol_fingerprint":"4d416c3d3eb64050c2c82e2c58eb95ebd78f89712a32e76599eb45e81341dff1","run_fingerprint":"db14c60fdf03a970538c98a28839c6b261212558a2a37c62799564cff900ab91","score":97.77777777777777,"score_display":"97.8","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":32,"at":"2026-09-29T15:15:14.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"38eeca962257c1e216b4313cc6e4ea0b29a15718f100af5b90ca68272f842515","measurement_key":"2857ecaddc4fc253ec77bbf66fab8abd84f595a4243eadad4a955f9bfbf136f8","metric":"mean_score","protocol_fingerprint":"edce3ee4cd626f35a9389beb93d9db7f14028e8cd382a514775b7b542e2944e5","run_fingerprint":"7772d7d04af6f74decee8cddb88de41ec4ea7b2708d7ce8bd65954e578bb10a7","score":100.0,"score_display":"100.0","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"20e362401668ec7b12360d4627efdcda91a436e05d2284395287aa27bdad5a5b","measurement_key":"4c2ce20758333d032ab1820563c97f8c87e87b4870520ebcbb2477cab6e94670","metric":"fully_resolved_rate","protocol_fingerprint":"86e7e097653d8a6be93c6bbdf319e275034fdeffda75980c374006c9d747dba5","run_fingerprint":"777fef7ceb238f2cd4026cfd8bb67f62ad7f45ebb6c60eca1dc309542905bce4","score":6.5,"score_display":"6.5","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:02Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e0d46942e3465858a3887610bc835c44f2326cdd169f5f1371b89eebedab4231","measurement_key":"dd6c61278bda6faae8e2c252f860e95a6b3c82ac9e08916ffe74e295ae4080bf","metric":"subproblem_accuracy","protocol_fingerprint":"3077b19518f6047f5119eebe79fb42140c7e78c4b0406c99a125fd532354b80b","run_fingerprint":"289fce8c377deb8cbac33ee93f17df7bde743e18a403aba50edfcf5d3d8918f8","score":60.9953703703704,"score_display":"61.0","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":32,"at":"2026-09-29T15:15:14.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"aa5fdf947fd38c12937cf127c39e47dbf772c7b3154ed51f66caf80c99bf1e21","measurement_key":"38779a4712e372b116854d4cd24efdcf0563cb9cf3b32a1f449247c84ae7b439","metric":"accuracy","protocol_fingerprint":"24eec68deaf023f9661f8f974a8fe5deb3efb84f49f19ed44801de89e1b56910","run_fingerprint":"a86e3ee068926c16c8bb2c3f8f345d434da29eb250cc8b33d9c7d162ff7b1b42","score":46.5,"score_display":"46.5","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":34,"at":"2026-09-28","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3b86602123b277b25f40dc8aa5aee4c39febb3fba6c5d75a03a93662e059dc49","measurement_key":"2992010ae120a75dfd42864dc8ef82019b4cdc3d3787576992cd6788ba55e0a2","metric":"fully_solved_rate","protocol_fingerprint":"ed74b9ef8fb58928ee988e2ed43ea06d08fce4c23a6f9879dca908dcbf27916a","run_fingerprint":"fa5b138af7eaa464c0bd8870b2761f6fea490384757208a00529a3a8cd2bc1d0","score":30.153,"score_display":"30.2","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-pro-v2":{"benchmark_release_id":"release_d9b58bd286ce316ccf0ed891","benchmark_version":"Scale SWE-Bench Pro V2 public leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":19,"at":"2026-10-12T23:21:32Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4425ce7b8c35d6019dc9b37dc0ff4a9f3e8369742033bd2b217e3ff7820e6527","measurement_key":"d5a80efc22e42cbc6d77eaed0726f28feeaf643ec893900c667d179358f33ca8","metric":"resolved_rate","protocol_fingerprint":"2857f6c83d0dc60148af5fc5a61ca678936195aa5484d02d4cc0464b7f4524a7","run_fingerprint":"7106c4daaed1813f9d597ad439f16163b8aeb004048f1170d8d1736b9a1b4fa6","score":95.79,"score_display":"95.8","source":{"id":"scale-swe-bench-pro-v2","name":"Scale AI Labs · SWE-bench Pro V2","url":"https://labs.scale.com/leaderboard/swe_bench_pro_public_v2"},"source_authority_tier":"A+","split_or_window":"public-v2-642","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c047341bcdf46221302633c9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f59849db2ae3ae18bb354f9d333fcc9f88bf5254a085180051bc3303d56069f8","measurement_key":"102b5e44f5c03e4447e67518b138cbd481541b975d4492af6f68998471e01d30","metric":"accuracy","protocol_fingerprint":"c0e27a13632b8492ee11b340f2dc6f72361f6528d66020a33218c0534e02175e","run_fingerprint":"3040c62d27cbaa1dab54e8a36b84352afbebad674b89ee6f1ca14757394d0998","score":83.146,"score_display":"83.1","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_58c2b77aab1a8f5d917ece79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7e9d00a7bfbfc9d494a50976b2d7aeced73a2093132b95b6528585dc06a3d45b","measurement_key":"d0a28e209d643e4b8ae42e77be10e714a4c7a63092e708aa5bdcc91e9ee62e76","metric":"accuracy","protocol_fingerprint":"1e968cdb859adb68b42754ff99c3d73a1263ddc8eb1751f5d44da031b34a8c68","run_fingerprint":"ba8b517b5ab1e26a293c82db547775861c6df784441432262c6745c024e72dd0","score":64.141,"score_display":"64.1","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9222cd585cde507f32997000379dc9f217bb189541efb6e54f9edd42ffd4d91c","measurement_key":"3a2ee93c1872dcd100d2c7023d69ae5c8d752ee8a73b63497cab6a033ebef73e","metric":"accuracy","protocol_fingerprint":"add3474fde34ea3212b531a0369c0b154c3e8c1e46dfe972c36d3d0651fe9bb0","run_fingerprint":"7e6fdb87350f6587013574c6d01359f6c24432dada5cf13f64971643d8dc9105","score":47.143,"score_display":"47.1","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:15Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"70e276184e1e0e0cd03fb9727151c4245cf815718c4b972736ad36bea62a76d4","measurement_key":"b423925fc1b76db51af218e6b89bf95017cb900409a1468110c26d33cbc8b3c7","metric":"mean_final_balance_usd","protocol_fingerprint":"e98054f2aa4577339574ab6d680a555bd1279f1ea4f32a37690727aa0ba9c9d7","run_fingerprint":"f1b677217f39d2cf03b970674a22655c22b3ac9212b5fbf0c66d825b20aa4301","score":11165.27833333333,"score_display":"11165.28","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9ed9bca0cc3f77c04837bf35","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"463ac7607438a0a11499b28ecce7601030614704ca028c7eeb2cf733a83b81b3","measurement_key":"274bce05faa2a0047550c820a0c0d55b9eb15489fd3165e0791711a88d3d24ef","metric":"score","protocol_fingerprint":"df91ce5a6e052678fa8c25a5e100bfc2d5500eb86f692eaaf06bcac40f00d6be","run_fingerprint":"644ceb16faf9e402ae20ce04b4cebc2820a6248a0ff6c735e8f7926288ef347e","score":92.392,"score_display":"92.4","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_fa49f2bcbf15eab57b062ee7","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"541c77f238eb13105ededdc974105de5eca21014c536402eed2cd68ad82e0336","measurement_key":"7154904b68bed16f4a6e0b876b06097fd9e881345298cbe6b14aa10429309690","metric":"arena_score","protocol_fingerprint":"7a5ee389c0130c4132b44ac64700d06daa93f4390a593b23574f490f39b02d85","run_fingerprint":"46fd331b4a8407ceb52fffedff203f621a0e3c674f45b77e427f0ef78bbd6673","score":1769.7283971913196,"score_display":"1770","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c047341bcdf46221302633c9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c150d5d6b5b1ad68e60c9a86d0838020d21748db3b11ed95b9b37ceffb7d2c3f","measurement_key":"ee9bf2f0c7ace2e67dec6df1e4600a8d590e5b355e973bd50c893a45521c1a93","metric":"token_efficiency_weighted_score","protocol_fingerprint":"c5065a9004b8597251058508bf51d33f3ca9640f5b95529999482ae6f8c9a673","run_fingerprint":"159c1e286f6e11fb70bf90a1824300d9481434058ec99238a55d19a725bd04b1","score":19.940320346320345,"score_display":"19.9","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c047341bcdf46221302633c9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"anthropic/claude-sonnet-5-5","model_name":"Claude Sonnet 5.5","parameter_count_active":null,"parameter_count_total":null,"provider":"Anthropic","selection_rank":5,"weights_status":"closed"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"577c81c91c1e32be33956e1d72c89ca7f29ed105cab5f8910257a77ab2674644","measurement_key":"4b623839da33aa9393323795d6cdd51bfd4faf81d463ca2a2a4d136004a06b67","metric":"index_score","protocol_fingerprint":"87fd8b1d9d72a3f67a7d4be4fa0b5c63ea0f6514af7d98e7de1c5cee1db5082f","run_fingerprint":"986f273b28652fb06f4eacfce1bbaf7298e0e089deff602d2001cbd172fa5fa2","score":49.010212,"score_display":"49.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":55,"at":"2026-09-06T19:02:23Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b91224ec986a5e653c62ec511402e02ffad5b8a762a20e4ca0dbf83a3fc45447","measurement_key":"3a134f97245b17f038b84d6906e8d0524406dacdacdd8344603160c91e97338a","metric":"performance_rating","protocol_fingerprint":"f88ae9977055b650bebbd66d326e915ad29134999b41ffa6ef9db480a625e519","run_fingerprint":"8935d305d67eb14ecaef3e0aec77cf89ef203aa54b4051da2f5a4fb96642472e","score":2143.2,"score_display":"2143.20","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_0e5a1af41c411d83363a781e","raw_label":"high","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"21f0038d2e04e91f5b5421d4a429fb58b1fc13fee84afe1a61519076e81744b9","measurement_key":"eba2c0927f1926e03cc492067b2ac37214bf1aaf4064490a4fb2a572479265e4","metric":"pass_at_1","protocol_fingerprint":"243df3de6e4f75baf131bbaf50a3d6cc1afb196c0993d501016330db009df235","run_fingerprint":"c8b53564fe22c29fb04d13466852708f9b1d857cddad41558e1389844292abd7","score":59.70000000000001,"score_display":"59.7","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_0e5a1af41c411d83363a781e","raw_label":"high","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T21:27:12Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"063c9e6403aae9c56607251e619768bffe62c5d2e219b42817dc81a1d9f09cda","measurement_key":"da779c4f7cac877d629afbcfd4087d6e45404fe08dcda0622a3b41093e3de81d","metric":"pass_at_2_accuracy","protocol_fingerprint":"698663a4078ad821dc00c6db456b1c588d0dd1db5c52ee8a1b5aeb8dee0a4397","run_fingerprint":"3944401d9acd344152aac7d25680e2dd155486d13d3f4b1a8190567d2d0dff46","score":97.5,"score_display":"97.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":59,"at":"2026-09-02T13:33:02Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"66995baf5ed6aeaa4ffcf4a067c0da5b2fae86ee747a915623cfbf2358eea0ea","measurement_key":"72842d2a03c5f2f1d52886e50569162ecabab97e441f0bcecbeb90efe03c9cf1","metric":"accuracy","protocol_fingerprint":"7fc618538143bfc630a5e98873be0750b7be8cd7799576d0787347fbd031e46a","run_fingerprint":"2031f4add5e65b57bc2c7f1f96df8b1dd12602d9034d008b08bc57d36b6581cd","score":90.0,"score_display":"90","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"df949d8468b4f33e73cde047633eb89fb15cf49ae2d0e70bc8be41645ed3c028","measurement_key":"fbb2d5c303904a02a7f7e7c9363c0c8e50e50f3966131311aca057a9baaeac25","metric":"ips_score","protocol_fingerprint":"1e41116758bddd295832bb912d0fa8b371b05905e1dbd090820b95623d012a1c","run_fingerprint":"a6e21d727d920e23dd3c65fb7ebaf91daa32d98ed58186b858a8c3aaa36d4874","score":0.13352329228313464,"score_display":"0.1335","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7c6f0a28f5a90914e505ea3c45c810c6b9b1195e6d3f2061adc87329fc407a44","measurement_key":"ac41030e8e99e0385ab35490d27868e70c225856e28555956e30e47891bf084b","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"3a35771755e922634aa961f17d716876582abb88c862d3ac6fa8761e1801273f","score":1504.3663236556554,"score_display":"1504","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"automationbench":{"benchmark_release_id":"release_587f0dd1273360ff4feb0c7f","benchmark_version":"AutomationBench · Anthropic launch evaluation","comparison_lane":"source-specific","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":61,"at":"2026-09-01","last_confirmed_at":"2026-11-01T07:28:22Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dedad92829a77f50ab1f77b5ace815f589a16a499d3fa805a4fff0a9e988c52c","measurement_key":"7737b4e1a48d647c664e3b01c080691bc04810251739364488640818f193a3d5","metric":"success_rate","protocol_fingerprint":"084f67c3372e48b8119eeefcec7afc736f1e0d48febf04de4be378c047ba9c45","run_fingerprint":"cd36c72be2bd4128f9c213c5900fcf758ac60f5f120dc446c7738b51a3b1a1f2","score":31.4,"score_display":"31.4","source":{"id":"anthropic-fable-5-1-launch","name":"Anthropic · Claude Fable 5.1 launch evaluations","url":"https://www.anthropic.com/claude-fable-and-mythos-5-1"},"source_authority_tier":"B","split_or_window":"provider-run","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c52c1ffeca7e4a640a86e739","raw_label":"reported","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:13:06.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b8c66e946c372f5929c4c683ba96757997328157813af7740ec4f63df5e2f53e","measurement_key":"57a3b4290ce6da3781452596d68971af9281c2fe9bd3a83d32d9872e0fa9ad83","metric":"mean_score","protocol_fingerprint":"a4ec588ce8a1d30d31b460ed1fa76cdf9e7512ebfab42302ba3ddbcd32da5497","run_fingerprint":"38cd546fe8ff19a5d348067ee9d22c77463c4b202117be1600f8db7f99d7cd58","score":48.0,"score_display":"48.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:03Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d8e1d9763fc874b4df67f1b160c857e9ae386f98b2d85abc028a090a73c8d87f","measurement_key":"b8c61c7b167a3e5d7537860eba178345d7d7bed58c0b63637a307455b40bd705","metric":"accuracy","protocol_fingerprint":"cabb65b1023c8688bc23d3eb2feb7764697e7a39921edf05375f613c9c28c7ce","run_fingerprint":"1b4ab72bf34fc8571a8d3586b386edad8af882c9972ed1206bec1d9d04bbf7dd","score":29.714285714285698,"score_display":"29.7","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"cursorbench":{"benchmark_release_id":"release_9acebd5b002e9c3f18a30606","benchmark_version":"CursorBench 4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6b2ed94396fb335fb813f1947c8318b745d89679930a72a014b4c6823445971d","measurement_key":"e936b6983db0ae253ff0eae5293365729da3782ab296137ac56ab4e3443f0822","metric":"score","protocol_fingerprint":"8b82e753b57fa6a00edfa32784004eebb2f66a80416a7353dadae9424bdaa4c9","run_fingerprint":"38cec6c9a115454dd03e12ba449779a115cc11b6ede612c827077dd4354faea4","score":51.800000000000004,"score_display":"51.8","source":{"id":"epoch-cursorbench","name":"Epoch AI mirror · CursorBench","url":"https://epoch.ai/benchmarks/cursorbench"},"source_authority_tier":"B","split_or_window":"official-current-suite","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"82c4900a13b3bb035c4ee6dd8a0c8bf537fa1233538a408bcb8eb8275f10e348","measurement_key":"6ce526cfd06953c3368b1b9559b018103603679611f6212e5a47501f735260a7","metric":"eci","protocol_fingerprint":"4e9a33cd9422610f148c4d65f3da9d59dcf1ff9837ec4e4559aec3564a6e2a66","run_fingerprint":"3a390a14b4067b1d69a58de6d49c413222f9ffefc71649251507dbb780a62eed","score":166.36,"score_display":"166.36","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2d5b4becde2ddac8a06f851c","raw_label":"reported","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T21:26:42Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"28c7e8269b0084a1e83d9406929b323d26707ff16bdac277608a21d7025504c9","measurement_key":"1bcb99feeccc5eadc49352d437931ee5f1cc26c8914c6890d4398bc47833ee7c","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"e8a4dc91b42d7f893f4a18b6b6fe531a9dfc9da8d9120206ba12d18a3130af04","run_fingerprint":"7408df9d49628bdec0fa4eb1446998dc32842635ef80fe511f77170a2eecc9ec","score":50.91,"score_display":"50.9","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_74602224514915764af40888","raw_label":"medium","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":60,"at":"2026-09-01T18:38:24.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d90a16dc51340c3dcb813435716ef2051e9aa6c0d56204b231bdb91308ec319d","measurement_key":"07862b32995ded9dcbb3338557cdc5f767ce64543e605c127996a030e55c770b","metric":"mean_score","protocol_fingerprint":"14bcd4f8da0ac33a2bb0638ecd047edaa58024aab82dbe53bdcdf9bea305f45d","run_fingerprint":"2ab32cb0f74a50ed7f63b9c026b32093f962de7ee39150b9d8b06bc5bb5fa60b","score":90.17543859649123,"score_display":"90.2","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":60,"at":"2026-09-01T18:38:24.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dd35369376d7825353f6e1ddcba4c9a09ce0805dbfc7c0c41a961bb393d07101","measurement_key":"a02adff3a155a02c4e75c95bba2f2c4ac251a856e3b133e2da06f5cd30297b7f","metric":"mean_score","protocol_fingerprint":"fcd0c753c48d67aa1457fb58f84ecd176bf9f909c0168f7ca1082626781e83e9","run_fingerprint":"fc23b963a297744139396bb4df11bcb3865044c11403ac7218c0d341baa57d4a","score":87.8048780487805,"score_display":"87.8","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"79587497e46d520118b1999edfea4466960b15c244fb6f2164c93432d315f1f0","measurement_key":"7881aba4b4e6735b9699dde8dfc6cbb4c5ad80dcb65fe2c301287a4ab0f88145","metric":"elo","protocol_fingerprint":"82fb140a5c92ca7db06101c5e8643c75aa52a2922550626df04eb2d37df341f5","run_fingerprint":"9db219377f0354a30e650c20260c160d913c190705c01b0b8d3a1ac0959f4f90","score":1763.29,"score_display":"1763","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":60,"at":"2026-09-01T18:28:15Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4c392182efb325adb9a30008bd1484c3f30dfad2848298e43d04e2ad4442a0fb","measurement_key":"afd7a94d5e24e7d6ed2da0e48a43f591fbadd6ad3d01358efc1f6a8f92b8bf91","metric":"accuracy","protocol_fingerprint":"f755439a1549e2e0786a24466e9d9a05274ed6e379fc8ca962aaa8ec853c2cc6","run_fingerprint":"e8d047e58f339cd1843d07d1f511a2155deb26bedefc2484f6a5a741010ee169","score":93.434,"score_display":"93.43","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gso":{"benchmark_release_id":"release_176f07ea4e9e0b8dfeede990","benchmark_version":"GSO current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":35,"at":"2026-09-27","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7a2c57c3934fcace58a065231da88061108f198855dba21357ccb8e1d673a118","measurement_key":"f813a69cd87489b46f1b0de6286d331f3cf0e6863f8cf48b0ef3b1139f98c7b2","metric":"opt_at_1","protocol_fingerprint":"3efc26960e1fcf1d87d9edfa0844ceccab8f2b5b2ad359b68443100de02fe22c","run_fingerprint":"91151bfe520bd6f00db659d2d1c3a4d34fb827b67de1921159299ebd844e5fe6","score":88.24,"score_display":"88.2","source":{"id":"epoch-gso","name":"Epoch AI mirror · GSO","url":"https://epoch.ai/benchmarks/gso"},"source_authority_tier":"B","split_or_window":"official-set-opt-at-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7f837c92d0ca5e97d510d67f","raw_label":"reported","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"hle":{"benchmark_release_id":"release_8817af9d9a0235bce0826e22","benchmark_version":"HLE finalized 2,500 · Scale protocol 2025-04-03","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":58,"at":"2026-09-03T18:22:21Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"94bf99a6d4168426f17a6026bcf0da8ac6188814c3a6eeac82a6fbdd3b038799","measurement_key":"6d7f1d1033df6ae9522449e9f6f5fdc32507bfa5a122eda1ccdc3f50d8d1dc9d","metric":"accuracy","protocol_fingerprint":"75b55307cab3ee6959fca025f39e37b795d89fae6f76bf8a4b86f08619100c3e","run_fingerprint":"b76890cd4999754f9d51087cc5f716398f96b196e5f07bb1af0ed145851bff55","score":46.5,"score_display":"46.50","source":{"id":"scale-hle","name":"Scale AI Labs · Humanity's Last Exam Full","url":"https://labs.scale.com/leaderboard/humanitys_last_exam"},"source_authority_tier":"A+","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_b672f752d3f34b6d6a8558f1","raw_label":"xhigh","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3328c8eb28ab27ae020a8033c1f99cea5e65036a91bde15d857ec8d5a859dcc7","measurement_key":"3c400c93f9596cf32437f59b73d6a68f634dcaaf46aea4814a254ffcc25e3abb","metric":"accuracy","protocol_fingerprint":"268259924e8b82cb39eb317c915a9f410a0e2a8cd02195f1d809716bf9ecabaa","run_fingerprint":"1b4b9324ddc872ebe531f791d5f2caeed657c2430c46fdaed33b308d35afec6f","score":59.128823,"score_display":"59.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a577001c65c5dfda1807f39a22af204a9078438760537591e524b30b8fbef87f","measurement_key":"b722fee335b585ba54f25fcd1f1405aaed509cc74869202369c1cbde3c639993","metric":"score","protocol_fingerprint":"40886ec6d0fa07f0512adb518ce93f7a3b2bac4d510a7b22739b0952f5b78afb","run_fingerprint":"ec843d0223bc4f2342a9750022ed143c3d7eeca66da07bcb68f66b3a0e8faeef","score":90.778,"score_display":"90.8","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":60,"at":"2026-09-01T18:28:14Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e9da22bd58d0345711d0ef85f1a7fd9e047221969180ada297613e2ac8aaf9e8","measurement_key":"124035f3fc6601160f23742a266dd5de4f38197e832e01f62c1816cb324e5dbc","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"9946517e5d4d581247fea5f632168da1099e0006ba711bbb632c68d97e634049","score":83.41415476190477,"score_display":"83.41","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":61,"at":"2026-09-01","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5d7b51294bf599b918b0135006efc66d053959470e3b36d7e4fd1c6358cffb00","measurement_key":"cd44d420feeaad5a1a8061a51d0556382e279dc3429eef377a4609e7c98ad4f1","metric":"pass_at_1","protocol_fingerprint":"8a37c1c62b912038268b5e5af08ff7459a8ad551e3f1bb0b1a87256419ff6036","run_fingerprint":"82ea751f1b30c25dd24fe8405e4f8b930866982f8b63cb21a66ec79387ea900f","score":90.515,"score_display":"90.5","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":57,"at":"2026-09-04T16:47:29Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9afbf40e9fb79004b6d1fc64a3be0bb38115d507354fde88a7430959154e3199","measurement_key":"70611a024314fbb1d11b1e6b5f831bc62fe413e11373a50684771133be3c730c","metric":"pass_rate","protocol_fingerprint":"40221a4cbe497f158f70b387aa3a15b985cd3498f3bae9439a4e09d9f6e9c519","run_fingerprint":"a058f30d08fd0b34a2e36e1c2b1b83db2f1ef141592af069832fe9a053be4b10","score":87.2,"score_display":"87.2","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_86f113c90273b2ebea19246c","raw_label":"reported","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":52,"at":"2026-09-09T19:09:49.777Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2fbfbc2ce603c0d9229c876381675c0ddbd32f264d258a1c0b2d06758550e8d9","measurement_key":"5efbe44160878bfbed822b1ab0de98e810f1a27c7c07db1aad69b0fb7ac1c61c","metric":"mean_score","protocol_fingerprint":"8fbaf6a169d62a86d13e6fe21608cc208bcc7833433bea2f38afdd0ad3ac1256","run_fingerprint":"a1699e79fe31ad5a30f695d7b4bb5af385378b08bc7cb6413e9c01917dc534eb","score":93.33333333333333,"score_display":"93.3","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":61,"at":"2026-09-01","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d9e6ede5b341d1d59b39b4b90d0b006c79456a2d0c4057108060473940023b60","measurement_key":"8bd28527024047a85423985bc9da1e7a05debc98101ef63391f7df93c41966ba","metric":"accuracy","protocol_fingerprint":"a0e307527a063cc4ec26bc99b0cfa74b7d20cc8e610f8959a86a1e57ba472327","run_fingerprint":"d4e8ba742d8abb62a9ff2fe70f728683a8768b0e9b22ca1738ca284fdb4b167f","score":92.375,"score_display":"92.4","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":61,"at":"2026-09-01","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e4170000cc9db5d08073196432881709b0799d09d03e7dbb42208ee1e4e4fc27","measurement_key":"affc3f6a5e0d71e77bdafbbcdf4c89cbaaba72f767a17d35a8e9fc52bfadd162","metric":"accuracy","protocol_fingerprint":"c8cea3dbb47b767bdf9177b5440f57e840833e96c49b383ed38c82afc74ea195","run_fingerprint":"f8a98f5df3eb70c877f887ea2079bbc0d878b5329028974decbea1a428471e41","score":90.636,"score_display":"90.6","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"osworld-2":{"benchmark_release_id":"release_e7bb52b116c9e290ad684e60","benchmark_version":"OSWorld 2.0 · August 2026 task release","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":61,"at":"2026-09-01","last_confirmed_at":"2026-11-01T07:28:22Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8b43ae1653e6cdebd93f094dce6ad764a0733b3ba7cbcc3c93dbccf2879d68f1","measurement_key":"c87946d19a13686519ab8188c55112c228f45ba2a511b4f9e5db90202bb41722","metric":"success_rate","protocol_fingerprint":"11c5b8da7d1625ecf3af992e92a5a4e6d66940a641dc52fb3ea9dfa50428f88d","run_fingerprint":"833c2398e1d964938827187b07cf5459f9615f30633f4d5a5bd8e7af036d8667","score":77.9,"score_display":"77.9","source":{"id":"anthropic-fable-5-1-launch","name":"Anthropic · Claude Fable 5.1 launch evaluations","url":"https://www.anthropic.com/claude-fable-and-mythos-5-1"},"source_authority_tier":"B","split_or_window":"august-2026-partial","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c52c1ffeca7e4a640a86e739","raw_label":"reported","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":60,"at":"2026-09-01T18:32:00.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e79fa1b39d5ad6d5d1f466c137ffbafe318aa1156eaffd2fa6cca04887cf8308","measurement_key":"15952b1ce9052bc4e3cc8c6de4750a6b7a2f2855ded1d891d8ca41a635976eb9","metric":"mean_score","protocol_fingerprint":"db287715e5e4ff598049f787f8ce4dd10a0501eded5d1d5d2ab14adecb1d11c7","run_fingerprint":"3cb7cb5ac298311170f22ff04d187349f5003bb7561f00266f84b7091561da8e","score":100.0,"score_display":"100.0","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"88a4165cc2e382fba472927459b57a0626f06555aea70e3c9181e6f4eaf7f411","measurement_key":"a0a6efce8c29ca4d685f6906d78a0789481e035fc9228a53e4b55fcd43ab6668","metric":"fully_resolved_rate","protocol_fingerprint":"afcf365e679f6bae5a3db004db3cb7d5bae11d1a9eb0194b03dd93bd1571ed5f","run_fingerprint":"d2825233005db72268aa05dd458eaf18e146e26f3705cf232f0aceca1065bb6a","score":7.0,"score_display":"7.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:02Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4a6ee64b57048502a8b7a7fea33c6e30d9abad6118486b0ad6bbd53fd0f0951a","measurement_key":"15578b3fa8d17dd64abc36d61924c74058defca1e60860c06cc8de182fa2ea1e","metric":"subproblem_accuracy","protocol_fingerprint":"20de680c4bb29e88259c541f2c32c497a4ab76de8e9c3539720cdbe55b2d3d2d","run_fingerprint":"bdb055ffe320a5bb730e82043d5da2138814a17df1ed6b1a6ad1163910de9fbd","score":63.078703703703695,"score_display":"63.1","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":60,"at":"2026-09-01T18:31:59.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"761aa2b0231e7c595e67dff9650b4de6fd616e1ae4620c094452e790612f98c9","measurement_key":"7f3437996eacc61fc5ef1fda030e382351674e79271b066baba268a4a9041084","metric":"accuracy","protocol_fingerprint":"37bef27d5bdce691247742e00286686d38e2dcdb9b6fb961c64286a4c91aa07f","run_fingerprint":"aa1b6186968a2ec8b69cf1561bf0cfb04f2674b48d7057ef2286b006c7f6725c","score":70.8,"score_display":"70.8","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c9fd5fb69116cc9472a4d297053da2811fb4e994389a7211cc655432ce270ff6","measurement_key":"660cfb906f6f86efdfc5be8e6f1525d7eb785f2e9c489db5024e67faf198695d","metric":"fully_solved_rate","protocol_fingerprint":"f98bcb1924e8c3b0e86cf418ea4bb951790d6d558e22e9981b76ef800cf54c53","run_fingerprint":"51e9c55c19d0ae46b09958055e9570e17e86f2947fa0f27df85b2c24c1290d65","score":22.901,"score_display":"22.9","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-pro-v2":{"benchmark_release_id":"release_d9b58bd286ce316ccf0ed891","benchmark_version":"Scale SWE-Bench Pro V2 public leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":25,"at":"2026-10-07T01:44:58Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6595a69826244a8b1fa0b3478526541f2c33d20e57343ac9909471a2a5ba5d21","measurement_key":"1394d57caf20e8fdffab9400c36b2a8c9014c1a548c9bfa431934e9740a1d194","metric":"resolved_rate","protocol_fingerprint":"6eb74cb74a16f47270e4a2795760ec7d021111ebb189815c23ca50f64e62f489","run_fingerprint":"1e16ec14a65b4bff2f2436b201d596afca0df34c3a1abef43086aa9ce9c915e6","score":99.1,"score_display":"99.1","source":{"id":"scale-swe-bench-pro-v2","name":"Scale AI Labs · SWE-bench Pro V2","url":"https://labs.scale.com/leaderboard/swe_bench_pro_public_v2"},"source_authority_tier":"A+","split_or_window":"public-v2-642","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_0e5a1af41c411d83363a781e","raw_label":"high","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7b768f670f239e9bec91a3661a853562f37850c3847bca7d85fb4db236c1e760","measurement_key":"5b3a0971b5499209c2a0e7da0d9608214672449049cb5c56d40b824da7329a9b","metric":"pass_at_1","protocol_fingerprint":"86566d80a5dccef4aafa8a7f57e1b22a621cce8eba4208ae622904092551ad3a","run_fingerprint":"1b7a0443eb422764569a4d12fe7fa6c5c6a29850f406ea52d25d6599c6c2d533","score":47.216495,"score_display":"47.2","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f664f74732324d8d6b3b6b24023c427f88bc5971118eafb2ee808fe0d628f641","measurement_key":"54437081981637d39030ac00d12cb49c21911c1b4721124de66aeab9110ae001","metric":"accuracy","protocol_fingerprint":"6929623740bf0e9f6d86bbcc09d072f9dec734e5a138d1d19191baa09fe5ed1c","run_fingerprint":"5f713e0cadc1a23ee21e89e4e9df1013adbf6027fda9ab7e757e640b2c56741f","score":85.019,"score_display":"85.0","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_0e5a1af41c411d83363a781e","raw_label":"high","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"70ee188a2b5fb5c100485d0ae5d2f25a8ea2461de4de9135f463b1e8519743b3","measurement_key":"5929188e8dc59c70590c4a32448f5d3ab393d788f07fcadb9386e4f641f934e0","metric":"accuracy","protocol_fingerprint":"b15767a450642a13bdb290399c737c70043262dac841ba4553929159447b6c7d","run_fingerprint":"12281a418756d65494aadf30cb5261867e40d5b4326a4209b7b8ef95e7152eb3","score":58.081,"score_display":"58.1","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"841a7fcf12d8c70bf48de536e5ff86a13f5f33bb9b2350b0cff944e6e0f86e9e","measurement_key":"f67f311f49da61c6cce406b595900b5da047b1d8bc809cdc25fadd835ebf78cd","metric":"accuracy","protocol_fingerprint":"4e37844bb946c3b256b9b13f6de67e3dac2b3658501fd9e4610848e97e618893","run_fingerprint":"4064342f1db8988b6e75d3b6ea1ae54762ec8c59442ff94b89d217411c994a24","score":40.0,"score_display":"40.0","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":55,"at":"2026-09-06T19:02:23Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"671d1042eec863892d5d5cca323b89f5c072b0666f1d6525e4e71531f3e2a779","measurement_key":"9bac12ca6b04b911e47277588675c52e1aea795d839084f07c4a379aa90f6d0f","metric":"mean_final_balance_usd","protocol_fingerprint":"93c8c86cf424031291284c60fca053346f36cfd3a5e4fbe6d612ffe5a6219bd2","run_fingerprint":"b17184a19a086e160b569b62859d3af2247d6c09a66c582a34b7d484bef8109f","score":5421.556666666666,"score_display":"5421.56","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6dd039f109f0800f20553ee1","raw_label":"reported","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1bffdf9585757ec98beac2a456fde7454fdd4219c9f51baeed159f518147f7d2","measurement_key":"8074a5e3efa6cb4e76805b6ea5f86da8b70210b9caeb01645e696ba9514afafe","metric":"score","protocol_fingerprint":"0a192c199c16bdf84dc145dcfeded1fca7f25ff7545ab24df4daf10450a7c7a2","run_fingerprint":"80ee0e6c6fa8f8a3dc773449506fad6f0c65b05ea99d295cd0d4a74cfd4562ce","score":90.263,"score_display":"90.3","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7e719c59b3dd54c0ba98a029fef64310da9a8a20fa797f4a54e3b67d8247a4c6","measurement_key":"2c2f416d899e5406b0e2c5e9f35116c731fb8ee8f74608624a47cc3b06217ea0","metric":"arena_score","protocol_fingerprint":"a6eff4345d48fc128fab6d5936509f95eb3d137859284fafb04ac71b5aa932bc","run_fingerprint":"77a9244958d5d20c0e08c98fe95c9af23a95107ffe1c75bfeafc550d0e489063","score":1745.8518267992542,"score_display":"1746","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":55,"at":"2026-09-06T19:02:22Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"488873f6d1353f81dfce1c6a2e16f1f6697437f29ba1bcfcebddab35d03de016","measurement_key":"3a3fb09e6c1c29dfc95cdae96b1b08a2a9c3a037ec181022b654ab537e322fbe","metric":"accuracy","protocol_fingerprint":"34530ceafaa84fb9bc61398ac7f4834324e260c9d0882ed93f9fe0aa2f2f6843","run_fingerprint":"10318188f10ee8ffbe05239316cb13f425c93d58001317a88a793a224eaae320","score":92.9,"score_display":"92.9","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ccb7cfb699f3e49429f43ebf","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7460ea7c37a0c6be278946998df9725859810c0c1a53fcc3620402c0161195ce","measurement_key":"0592a364a597eb34851b1f0ace4c736ae3a84a6e6b4e78fdb27949ee14220886","metric":"token_efficiency_weighted_score","protocol_fingerprint":"81824f0520d15d25a22527585671a8b99abc17d9dc2aedd724574663c6a0ffff","run_fingerprint":"5921c69dab78065741901cadbf1e7feda41d7722494bc4b444e3cba3ea96e9ec","score":25.970212727272727,"score_display":"26.0","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_b672f752d3f34b6d6a8558f1","raw_label":"xhigh","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"anthropic/claude-fable-5-1","model_name":"Claude Fable 5.1","parameter_count_active":null,"parameter_count_total":null,"provider":"Anthropic","selection_rank":6,"weights_status":"closed"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0e5035791a4edefd00f4644390c6121f15c79b3c6ff1a377e746d1dc01984b91","measurement_key":"29dd2bca11718334592b5bc975f34ead8027e9888f69b1a3ae6343cfd4b5b5cc","metric":"index_score","protocol_fingerprint":"32b68bebf9c0bf08b11360fe1e701a4e49e2a1f9fb41a6356122c6da033ed532","run_fingerprint":"d67304fdce596fd70d8b74bd6862ddee3958fccdd0711d36aff63479af822fef","score":50.412194,"score_display":"50.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":12,"at":"2026-10-19T22:24:18Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a1bd32d8fd1dfd5ec8201c3dce67f0a940e792f1d0b249b2f7a1f7fb0cf8bed8","measurement_key":"6f31b6d77990420767fdcce5db9f0598c06413485e80e7ef765d00c8e49cd714","metric":"performance_rating","protocol_fingerprint":"9cde006f9bf8041e1911ba33fa535723ec88f1f80ab0b2eec89b2bbdac8b38b3","run_fingerprint":"9902f81c60546cda59c6a86c319941e076b6c92d7b5cb6c5f9c4690b89400cb9","score":2100.1,"score_display":"2100.10","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b0e7caf390ce08e63ad5f7c9e3a99ac08bed3a65b5ae783dc8084cc2b2e1d280","measurement_key":"5ec963a841439a12fea65297b34a57e806b3e521c2245d7ee8937de3c91f16dd","metric":"pass_at_1","protocol_fingerprint":"c51ea81fb0bd43daf734c456feb0a0a2ece36e84d111c2fb28fbd589ab59b5b9","run_fingerprint":"ae5b5d55100706d6596353edb8e464f67b705f90f38f06fb007a9c2451c78a26","score":82.4,"score_display":"82.4","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_88d8753549159481a7ae44c6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":12,"at":"2026-10-19T22:24:17Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"693ba0b7a4ec5782d44524e7f27946eef47aa3516d119bdb27cf4d9b61ffbaa6","measurement_key":"04a91d1bd21d0de7a360aaa72c1e3ca50e6341c033c4f22ce0380ddb6928a0bd","metric":"pass_at_2_accuracy","protocol_fingerprint":"c8fade6d8de8a2ee6d3e84a3272be7ee289917fb45c5a589964003c61ffdabad","run_fingerprint":"fdc8509057cae5509564e16d8b33881c13404624f47d19094b9f2c500724b739","score":98.5,"score_display":"98.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":16,"at":"2026-10-15T18:19:38Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cb3959d6826dbb0139defbb18ecc0e468ae659e5b0c231c9681a218ddd31a2ad","measurement_key":"71adaf492dbace48ac874439fbf6e03884e2aaa1bed09fd92c4b067a189f6d26","metric":"accuracy","protocol_fingerprint":"ca829b83ba736df84b0d42690b8fdf5d335f17160a6c1fb4034209c38c9c11a2","run_fingerprint":"eac6346987f2ee5621d0f633f76f941222729ed4b95326f40c5e66fb3168aa69","score":91.25,"score_display":"91","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"28e75ef62c1a520dff887c8d56d6d564fbbe1be1b7026339954bb6cc30e58d7a","measurement_key":"7466d373f4f2dea4ce4575eaff16bb9ed64c66be654d6323395940dc98a37bdc","metric":"ips_score","protocol_fingerprint":"54137ebd27d7f2d145e32a28df61d4963b65f5642674011854beba33cdb46402","run_fingerprint":"750dc66c5385fe45d26b14c20bc20e7aaec0e715101395190df4560c43dd6cd1","score":0.10727188431308599,"score_display":"0.1073","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"41a0e2fdfec3cc955cb0985fc826e368e2e15566c6301748d204c53cec116924","measurement_key":"87dc33a22553c8c34201b3128925d5a5c21f987fb4618de2d9d7b7f655b0bcbd","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"fd7d92933fa6139bdc149aad6f04593b20e0674dfdcd37386448738716567729","score":1520.254646597456,"score_display":"1520","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"automationbench":{"benchmark_release_id":"release_0e98d905ec617087da8bc4a5","benchmark_version":"AutomationBench · official leaderboard private set","comparison_lane":"source-specific","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":19,"at":"2026-10-13","last_confirmed_at":"2026-11-01T07:28:20Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c0d5e0b1871a4718bb68cfe3e9991f4a36b3cb928b464b7e1e58f383e62abb7a","measurement_key":"0737106d0cf10261d6f6d0c288397144f0bcd9e764922caa87dc3f69e8c16075","metric":"success_rate","protocol_fingerprint":"96853ff1b468d93051f396e775a1a7d9a0cf86ccba3aea71068ba91fcf4b5a3e","run_fingerprint":"366ec9ae87fb412650fbf5aba6d03ce8d38332d9ddb097826e5b70d73b9630b0","score":51.3,"score_display":"51.3","source":{"id":"google-gemini-4-argon-card","name":"Google DeepMind · Gemini 4 Argon Model Card","url":"https://deepmind.google/models/model-cards/gemini-4-argon/"},"source_authority_tier":"B","split_or_window":"official-leaderboard-private-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_31e1c3f95866a70589539280","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T17:15:18.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d462a1afbe9e43e39671aa888704b349ffc11b9e1598e074fc2b7f22ba57638d","measurement_key":"cc30e9258a3b6e4ccca4c9fe58fb25c00a7eb2d69858ed4376bd0829b92e011b","metric":"mean_score","protocol_fingerprint":"593d4ac84a5e773c161de45ad4c3f8fe1294c75342486875d1ac47a75c9539b7","run_fingerprint":"0c2d2f2514b4a7b0d34db417c75761739061e9c57d017b3509df8a393c2ebc4e","score":59.0,"score_display":"59.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5212a92697c420addc51b40bbeace36f572558146ad36fa1e9afe3a7e7562311","measurement_key":"c5c9206b4224bf59585486ce4bb249ddc9bd2962766895a64d09030f1be1cf9d","metric":"accuracy","protocol_fingerprint":"3bbd3ee9062c5777efaa7a20a72a8fd62079ff597fe8b7690f28dfea0f985e08","run_fingerprint":"4e11548fda6a4fc2b37263feb672cd9366bac66dbf131c1656ba33c986d09bc3","score":27.142857142857103,"score_display":"27.1","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"cursorbench":{"benchmark_release_id":"release_9acebd5b002e9c3f18a30606","benchmark_version":"CursorBench 4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:11Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"da8e76103e76194f94010b0e117b57daa1d955f95a53f9fe24e354be24e3d76e","measurement_key":"0e13f6ede88fcd10e09f0d11b3e5cbf9bc11267c38f6a0eca70018a733668670","metric":"score","protocol_fingerprint":"b17dc5812f51c58f6597cf0dabe7d7888f17f0f3823affe5bbf0ecb38af450eb","run_fingerprint":"ade7739c3063f5ae6dac1b0f0586f1f2cae944946a0cf6429b6d125f597316b2","score":52.900000000000006,"score_display":"52.9","source":{"id":"epoch-cursorbench","name":"Epoch AI mirror · CursorBench","url":"https://epoch.ai/benchmarks/cursorbench"},"source_authority_tier":"B","split_or_window":"official-current-suite","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_12e8a62d68d933c29dcdf020","benchmark_version":"DeepSWE 1.1 vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":19,"at":"2026-10-13","last_confirmed_at":"2026-11-01T07:28:20Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bc60da63a84afa46bb438fcc68cc9171d9e1d5c0b1c0dfcee13ee7a59cab4da1","measurement_key":"ff4488911b52baf6ba4b6ae7ce3471565652c342eb008643af5dee91c3008eac","metric":"resolved_rate","protocol_fingerprint":"7cc192befcef15af5483c5f2ef32156eeb6489f75d15f93ac8576d1001e08a8f","run_fingerprint":"7ca21514ef0f05048c3245fae40a64c28a0c94f3cda4615d293ee3ff8c53e80e","score":77.9,"score_display":"77.9","source":{"id":"google-gemini-4-argon-card","name":"Google DeepMind · Gemini 4 Argon Model Card","url":"https://deepmind.google/models/model-cards/gemini-4-argon/"},"source_authority_tier":"B","split_or_window":"vendor-model-card-run","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_31e1c3f95866a70589539280","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a8c16afb34f5e1cfe240528c141c4d8dfe0f5bf0d638c5a93c3471d058627baa","measurement_key":"712944f41ab2025c2b6bc10920c0c579fccc8bc838c738961fe33de64cf75813","metric":"eci","protocol_fingerprint":"d8b3e1721f5010228416f62b6a87a36f17a3fbbc778b03e935ec33a2ea9f2ed8","run_fingerprint":"4e2f6a8bfd89efdb73a3079f11e7c9df31c3cb33cbb5cae52b7d1757c2c3b8f2","score":166.07,"score_display":"166.07","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6bc0dda6b70136f61437b9ab","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:01Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ad5524d876fdeefcb4d869cc3fc792f9ef20011313690adb1943a4dcb09e8355","measurement_key":"310b5b70af5a6331aa42f9cf7b299e2f4cc177dbc2cfc67522d91a91463f6bb3","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"d9420a0001ac4d52bb3a9ab2abb497f88338950ec67a761eef9db1fc229dbdec","run_fingerprint":"0384539aac00dc5622f9bd67e9d4c171e80c0157a268622663b2b9d65b1a1ca6","score":47.55,"score_display":"47.5","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_9d3f500136d0b273203f54c0","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T17:14:57.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ef0117d25262ddadbd4f13c7dc345baa406ddf6b8e0338a2fb77234009d3c94f","measurement_key":"e6cd2f629e35d2431fd9b17a985edc20b3474672127d57c9727497263cc328dd","metric":"mean_score","protocol_fingerprint":"24fa26dc27b6119b2f23dccb7c7da348884c4145d0cc9d02f4674ad281476673","run_fingerprint":"acbf7c56fc4ef7463c9ecd6b3c0b9769f600b7cf89596c0dd682e51b8edf7612","score":85.96491228070175,"score_display":"86.0","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"44b8be8cf89a254003d2453058b2dc484c119fc8cad372d78732e64325ea0ea9","measurement_key":"be0e92506d044f16f1fb9db7d9e2fdf0bf360dd4bab88c1c033d32b9dc96a2fb","metric":"elo","protocol_fingerprint":"71c04dbf23b2eb31f190eb5372ff4c90a359b3c945c1ccd5c8e7271299b530ee","run_fingerprint":"e22fe13392e187fd01d43b76cc365cb3d9d29394d3b11654fbb9fe8886339651","score":1630.66,"score_display":"1631","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T17:15:08.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"942d1e3e3cb86d53e71db4236dfac74c8028b79ad9e6c202ac764897c04b494c","measurement_key":"d2c99ea76811046c9e2bc5538955738ba946476ee10ab4877a56bf4c9353b6ca","metric":"accuracy","protocol_fingerprint":"b9f9437fcfbe7d191008e292cea0e920ad99813aacb47cc16787fd687f0fa77a","run_fingerprint":"3605e4be7b17d1ca02e7d9eec73c3f40963650e9b84f39f9b2555b397afd790f","score":96.40151515151516,"score_display":"96.4","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f46ad3fc6765e18709cde449fa11dac57dee8736f47269d5a1b770d7a45a7598","measurement_key":"d4d10543fbc62aa8f7f49013fff2fd31d062e444b91e652eaa87af6042107f1c","metric":"accuracy","protocol_fingerprint":"f0c32c6c54026bfed9142febb947cad1213b35d1212c85c136055a19154c0267","run_fingerprint":"7faa333dcfd75f920cfda03d9059a8009c372c9fd7cadf0068258c7ba3f5f62d","score":57.089898,"score_display":"57.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T19:24:33Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d73442638043fbc652f1818fed6700cf4bf7f8a814e2201bb51851fca6b61b62","measurement_key":"2576604d1e5a78847749d3c5fbbcd88a6716d659a7e777a630592f5af9739398","metric":"score","protocol_fingerprint":"3e09044ff0dfe5b65bf6bf00c43446298ac1023e77dcc215504a78628545d45a","run_fingerprint":"19040fb900226cedd7cb49ab89f3aeb284be0e23653ea0d9bf4ae662b9ab5ffb","score":100.0,"score_display":"100.0","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":17,"at":"2026-10-14T10:00:34.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"634003393a66efc3036f689328c9f5983a5be6f8c4795194a9c8bf93de93576e","measurement_key":"3b99b4dee887daf2ca819f730907923bfa222b2e83e33b581c7d04fc4e3eeb44","metric":"mean_score","protocol_fingerprint":"f3c792e2e350897524ce130389403b01078f6bc176705d2f90c8857cb9417369","run_fingerprint":"ab562a05bd21f8dd1c02642fcf256737408112a28d74a1635ac5171a28f566b2","score":58.88888888888889,"score_display":"58.9","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T17:14:57.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"49dab35201d4145d47c970c96ac0a3a408f86a49cc0b364d627d6a87090bf0fb","measurement_key":"5b55ce91970c21876fb462d0135525c5f0b4239f7ab6ce9558193b3a5c816e06","metric":"mean_score","protocol_fingerprint":"e2199c913d23a0fd6c1053b929330bb596fec8542b3d5e7aeae4f789d87fabe5","run_fingerprint":"51be0c0cb0e8436bf3a55c6ac42e70978d45e15dc14917a1dfcbb00918c7b6b2","score":100.0,"score_display":"100.0","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"95b9019a140ca8df41390cae58efe167f4ffbd646a25f1864c3e53d855a30f17","measurement_key":"9179869bead5cfc1e67f0f1619ee97a6084668af944e9737106508b1d46e38ca","metric":"fully_resolved_rate","protocol_fingerprint":"186e0b0f922ce72c966821b283b21dccc813c1552b6115d47b78cbaed52b12ae","run_fingerprint":"5f3594a351fa09eb1e52471ba8e33cadc2c6e865b7ea10c07a6d65669b3f5e41","score":2.5,"score_display":"2.5","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f9fbd84ed17d8d654fb21447bda0e04683ff0d7cea83caa647d29f862386df9c","measurement_key":"87deaaef04abb62f413dc6349a8cd6c4f19b8b2a7611053df5539ff3dfad8052","metric":"subproblem_accuracy","protocol_fingerprint":"b9a690d5875d207c07df50139a8b4350a3e2296f506e3210e323dc88107e3569","run_fingerprint":"f85b9c2ac70884de215e722b7bbb4c7eb2a8b2fe1f8521ba5be7ddfe0d0b7a6f","score":61.8055555555556,"score_display":"61.8","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T17:15:14.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e42457ab3eae666fcdd578ee756ce552be605c7500ae7ba8fe889c6da5aef70c","measurement_key":"c9ec05f3198b7964553fac744074e78a1a30a9cb89012f60cf2a8c4045ec1ca7","metric":"accuracy","protocol_fingerprint":"51e663b336389d574c8880e0231f6ce4803afecdfd2e0be16c2db60169d9a747","run_fingerprint":"4b42dbf1a77298fbf58d5d6c19b346674cbf56aa26869db298f4a83da55b2d8c","score":76.0,"score_display":"76.0","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cdb5c28fe48242f3f111f8441f30f7883fbcf33c3b51a8e2cb53df2cfa6279f8","measurement_key":"36db4f1ba9f77c9c57ec00dcc7008e0eccb7afd6d41ccfbfa129fcaed9f7500d","metric":"fully_solved_rate","protocol_fingerprint":"88fe646d7e267129dd890d44eee457ee14883b807f3a02c4133704ea122d099a","run_fingerprint":"75a5741cd5673547462e450e683be6b30448184dbf61230a54ea6493a9738396","score":44.275,"score_display":"44.3","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-pro-v2":{"benchmark_release_id":"release_d9b58bd286ce316ccf0ed891","benchmark_version":"Scale SWE-Bench Pro V2 public leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":17,"at":"2026-10-14T16:34:00Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"df1c251ca0b3b52f2881311e00a7e7a235303d7de584466c789ce2ac1d5ecf1c","measurement_key":"ed3ef658045bcc41bcadb2b3450199821405b2b0767348ba8be048879b965c20","metric":"resolved_rate","protocol_fingerprint":"79e5d139b1d4523d0ad3c96a701cd6aadb89b470fc41443030c618045d8245a6","run_fingerprint":"ddc85a2482b4d9a07c849bb5c7aefdbecbed95f556b20e300a5ac127dfeec45a","score":99.22,"score_display":"99.2","source":{"id":"scale-swe-bench-pro-v2","name":"Scale AI Labs · SWE-bench Pro V2","url":"https://labs.scale.com/leaderboard/swe_bench_pro_public_v2"},"source_authority_tier":"A+","split_or_window":"public-v2-642","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":5,"at":"2026-10-26T22:05:28Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d5d93693bc9a72915d0d01623878672da4f686038dfa464039ed069477d640a3","measurement_key":"370a7c45188d92dc7f07b27a252d7103b4f4024811f5157a952c47ffe05565e9","metric":"accuracy","protocol_fingerprint":"bdb80c3a4768f033af8b48b02c804e607ea4713041d354a06757cd83750ee2df","run_fingerprint":"dc5a81d5b1899a7efcfb990d69249f72a2454f4b278b8b7433052c5ef83b181d","score":57.678,"score_display":"57.7","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e9670b81969a9f02ee242ee4cadd7fe213752919c846014355f97abfbd224898","measurement_key":"5785fd0ae098465333af8cb28b1144f2f351636f83d8dcf65aac1d568557cdc1","metric":"accuracy","protocol_fingerprint":"60d2549c79da03f7d575e554a4a1118890196bdbfedc204b1e290939fd5c773d","run_fingerprint":"034b4f00d4108f17940502ad41627b93d93f192396f4d3fbedd01c2065a5ba45","score":57.576,"score_display":"57.6","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":5,"at":"2026-10-26T22:05:28Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8e3877e37cdc012ca8f84a0801568f74f289705df3c06eb73a11bfbfee50a056","measurement_key":"33c65066561643317cf47e9e61bd0afd7e348744e4beb6d573d98e6c91d32d54","metric":"accuracy","protocol_fingerprint":"bd9432e2786811a0d3deb21d1c36bb11673067dc745543e04702f727d19c77b1","run_fingerprint":"295e099530979fca1ef5832e566b3a3a646d5d6629fa27bad62c7cd9d1ec960c","score":44.286,"score_display":"44.3","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:14Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"05118678e5933c7560dbd3f43e95e16e9f9fce157c06d0bae3827473f67109a5","measurement_key":"92c50e1b1763e5bc7caf639a7ccc17cf3d2fe2c221a84bcd52dbbf973dffd954","metric":"mean_final_balance_usd","protocol_fingerprint":"b0407e9e0a27cd895b67f5534f82db3be2e20b3c723f2d5c4729ff209af96a23","run_fingerprint":"9314bc5673ec5cc899e801ce14e1c6f5d29dc3abafa9262fbd45e634153c17b7","score":13718.158333333333,"score_display":"13718.16","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0db4a2e4aa983274af2ea61e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"31545f5414896bdf0fd5113fb5cbccccd6cb392872c0e9ad858d4909fd4a74ad","measurement_key":"9c62485fb3f267407429ab82b74ab49586bdb6a93c0ef9d68d4cf5478f5d69bf","metric":"score","protocol_fingerprint":"c6a98a5c0d2020c6bd69fddbd129a50d8adbff22756d0f87bc89f0fad9ed22ed","run_fingerprint":"a1aed8b102f6b6682b8ab5ba3143e24123376d979f9b7c78414549a3a25e8a40","score":91.906,"score_display":"91.9","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1cd00b8b3a6f4ce5826a128da224cbe100d784ac842bd3f8b34c839a778e1a26","measurement_key":"ece573f001f15f4b8fd748de7f0d3fe4ac98101293e57f89dd8a5ede31838596","metric":"arena_score","protocol_fingerprint":"bc0b5ec665b2e642520063516135b8702fd7c46e36ccce33136fd3adffad9533","run_fingerprint":"b43706dee35fdf1c938e16bc42b49d2f03b5359cda4bbd2b0517a1fcd4cd5910","score":1679.2118291253184,"score_display":"1679","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:05Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2cc79e5c7d9b4894b52f34ae8d3538bd8998ebd83127663477b4d2b287096676","measurement_key":"460d58935e2d59a42f27c62a699cf70221c3555b831005bc07c082ef06d5df4b","metric":"token_efficiency_weighted_score","protocol_fingerprint":"a8f04c285e30e485e3941bcbfa28c41fba5dc2a6093d65e0148d7a16ecfebcda","run_fingerprint":"288d450f372d25a72872863551edd96b74f005da0e89d99069c9b197d4985e65","score":20.096489621212122,"score_display":"20.1","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bdeb2b4867ec518e7c0919e0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"google/gemini-4-argon","model_name":"Gemini 4 Argon","parameter_count_active":null,"parameter_count_total":null,"provider":"Google","selection_rank":7,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"56aab26add6a820db189af4a3f80f85dbb66f2f35a163a98239f5e921cd45adb","measurement_key":"9fa1f68c47d867ebacd8e3ab50ead8d21dc6354658449b53033869d93ce9dfca","metric":"performance_rating","protocol_fingerprint":"f5d0d49ca2d1395a9572a75707f8f175364d159218fff2ad97b2fb9f4823395f","run_fingerprint":"adba2ca9d3cf1a4502e9cf9104ba6783ea646a7fb2ac51b49e1d1c8f1bde6138","score":2164.57,"score_display":"2164.57","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_39a30289a15f1db029022e6c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ea83dfaa4fd08de872a7c9d6716e144c9a994337410adb245aa8303362c52a7d","measurement_key":"fd36035eb8c07a335db745f6797a91ce5bbb2d8a81fbf569a8bcc6b94f36d6bb","metric":"pass_at_1","protocol_fingerprint":"5515c94e4576ce43c29b263701e65432246a210f2bfbb399e75c317c22bcaf9c","run_fingerprint":"ac85192e0846a1660e62bd5f98a737ed6d837b94fe380b6e62a87790fcd77e61","score":65.8,"score_display":"65.8","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"71e45c35a7dc614cdca26eac505e5527c9d928cb91b3565378fab2fa19314191","measurement_key":"0f5d8525777939cbfd2de78cec9238510d92de25840c427e3b2fe4be9281d1b6","metric":"pass_at_2_accuracy","protocol_fingerprint":"b3ac1059018444402272d7dfd2f3ca5040faf0501c3b838bc2934dab3b7ccd96","run_fingerprint":"ff084937372d7fdb731ca84f03c8a24d133f8ce1f46d291106260614bfd375c8","score":97.5,"score_display":"97.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":59,"at":"2026-09-02T13:33:02Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a3c4daafd9411c35884f6889981b8fe8755d0c681968a77fe06819e35f34f0db","measurement_key":"535536f31b5323f3c32b16b04caa2566c969b7a50697d2ceb92a740a4cfae74e","metric":"accuracy","protocol_fingerprint":"e4375a17736c8f613f4c9ef2a1a2c24cc839e2fc69691eeec35e9a9796c2841b","run_fingerprint":"b47713aa60f93c953c7dc3ad93a307a14f1aed2f7085cd87da6dd47d7137ad70","score":90.42,"score_display":"90","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f8d674c296de7f6e33cb8d87092a5d8cea64ab6769f19daa52ca7232cdcf97fd","measurement_key":"088e07aa319c4a51179e0c5ffc2494f0a0957bff4a3e20c3a39c482748d3e25d","metric":"ips_score","protocol_fingerprint":"702a85a2ffcc161882fcd9663e2ec294bb4de0d98e9d34b97d302e6aa47cc730","run_fingerprint":"99ecaae24f05bbfcb012dd0a9e874902f02acf13843689d9896b88bd448b1534","score":0.07565942758202185,"score_display":"0.0757","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2038258535c68c2452d8f04585730b2d292f048610b6e86cd9fb9b1bc7a5f52d","measurement_key":"291d0d8983646b899a47f33696b8c80a444a1b0c8dd3524c53293332feb94cca","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"17fec020e26c4795c461221a4426cebff1c295ab8f879dffed5a837aad7048b4","score":1490.5040398730391,"score_display":"1491","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:19:00.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8a82c900f324fe3e3d4bb60becfb564a9af722a4a61cb2818f66d6493e66ce42","measurement_key":"ccc4e63e78025807612aebc7be6cc51232c59f01b3eec62d7dd612c6d76be4ff","metric":"mean_score","protocol_fingerprint":"fbfbf1dcd93a5a55dbd3fcefc26accb3ce1f04972e0f558268e7da5ddb3fd9d3","run_fingerprint":"81064f5fa7c3f56619fe95c6b4c34f0e8c8d48f5ac72e18188cf9f1482e9ff2d","score":43.0,"score_display":"43.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:15Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e0db2cdd2701de0824189968923f0c4060f65cab29a42108258f6d2653bb18d6","measurement_key":"3c50dad0bc455c2e632faac0c65b9de33fa6434c11a90832f17870405508ad97","metric":"accuracy","protocol_fingerprint":"09b05cc465e646d9e64a872d732862c4548a4d4ca19620c3b74478c312069c54","run_fingerprint":"9e9d2e6ac44cf398b5314d62ccf82b672e63ed6b43733d30bcf50626bb2c4d65","score":29.1428571428571,"score_display":"29.1","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"cursorbench":{"benchmark_release_id":"release_9acebd5b002e9c3f18a30606","benchmark_version":"CursorBench 4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"96e0288c9311432827165d9a355993f8add87f38f14584ca23efeb076d7194b8","measurement_key":"471faebce3fa9e326a8f3105705a9baf36f1348122c8ceed8a921a517e48bbc1","metric":"score","protocol_fingerprint":"c570eefb08611683c6cf09a39aac7758ac0714c34f4ecb5ca51d5e4d29150a83","run_fingerprint":"73e716b8e1ca93c4308f6d60f2b5fef372800f5e9583d888959b2cce3fd1b01f","score":46.6,"score_display":"46.6","source":{"id":"epoch-cursorbench","name":"Epoch AI mirror · CursorBench","url":"https://epoch.ai/benchmarks/cursorbench"},"source_authority_tier":"B","split_or_window":"official-current-suite","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ecac36582e53fab2d8740ec8a0e7393c1d7c6f47e82865750f540e14d66a9c15","measurement_key":"546f654892a5e5ba0a142209823d23aa4c59958e30f2ddde363ba9a6e7db7630","metric":"pass_at_1","protocol_fingerprint":"ace259fd68d7198838f969ae1b26d71e836fb71ca059c1b781a51b215bf35605","run_fingerprint":"f3f86ae4fbc2ff3e6d57e2bd3839536265a211be3cadcb7241268bd4a09778e7","score":73.64864864864865,"score_display":"73.6","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a01cc19331a49ec66e30dce41687be3b8b9870558b5acde6f3baee9282c9d5bb","measurement_key":"cb50995796bee3fc7f649e8b0e7dc949b1035f935257b68848e3397249522dcb","metric":"eci","protocol_fingerprint":"ea46c241710ed2cddb9f9e7d74b8b827b77077865d2796ecac5efbda0fce7bdc","run_fingerprint":"16751bd920e4864675d3b53ae751cf0a1f61e541c2325fbc3008cfa0bcc8d1f1","score":164.47,"score_display":"164.47","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_564261edace44339c4aa1271","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"62f5a0cd4b228cb5aedc46843d62ebb6585683def5a4bd7add55e8b06ea01879","measurement_key":"37222eb0a86ea45466d8f1959a22fe9226bb45a1a4f8f10dfffbd91e4c9d48bd","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"e0feb047845803ef3ff53270763eb37c74610e5ae13172e2119df2cf213d49b3","run_fingerprint":"83fd3f0f1f59575a2ebbd4de32bb8d79a94bd80ef10082f1028e99e2194864b7","score":53.38,"score_display":"53.4","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_7755c5bbeb7e47ccfd5ac6c4","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":99,"at":"2026-07-24T19:54:20.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f5d71d252043fbe2ab87da47308a2e53287b7f1add4da2ddb0f89dfdcb0ac622","measurement_key":"2a0f5e77ad50e30a2509f70e55c5525da6033160bb6c837c8071d2540bd378bd","metric":"mean_score","protocol_fingerprint":"e8950252a5c51330728bc6367a249c0cc704fac117b382f6fe9b1d068b0f8aee","run_fingerprint":"16a7ef48859029a41795bcebb37f84562ca06a1dbd75992ca3ad3b2818efe93a","score":85.6140350877193,"score_display":"85.6","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":99,"at":"2026-07-24T19:54:20.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7b52f695de6f48cf0ff1ed1a8bbadf39cc4a03e211961ac94802b81e1f396629","measurement_key":"c127d5895f5d98be4025ad65e48f3b736c3d48fba19504db965d64d7fda9d9ba","metric":"mean_score","protocol_fingerprint":"e3cf9103efd2521f7be4eacfc07310d73b84b17da7d89c4f1b7663c6396f3cf7","run_fingerprint":"eb3228eacd51a5fa15ae45076fb9c0053909413ee24229f0854630f56232a451","score":73.17073170731707,"score_display":"73.2","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bbe63543467b5bf2f01362f25c4c373ab5b5dd11f36cd27f17f671d2146cb17d","measurement_key":"50ab4d0f72310c44f10a9d4da70f16e6d227063049e3d623799fdf9f90d7d019","metric":"elo","protocol_fingerprint":"641d7cac73f40b65ebc19088af68fa9f03b1c1d6b2f7cc17e618b857d6173af1","run_fingerprint":"08ea9618f37989828ff2f5b43af759b08916e65307ed88febd4ae46db152f049","score":1729.9,"score_display":"1730","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"19640dfe822bc6b29d77c4a1e1498c42b7f2a7248ebffe113710074a34c0c53c","measurement_key":"1993eac2ad13c48f289bcd61ad3f61cde4997dbac7cbbedceacff531ca156dcc","metric":"accuracy","protocol_fingerprint":"d3777f133bba23744b1423cf6a2451a2cf11a061e1b5c5ee1e57940741baeb43","run_fingerprint":"612a2d94e1582732f9923f5f37c7f002d6fb2dd4ed1f56f7a9c20b9254c3c992","score":93.434,"score_display":"93.43","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_10853c414d0b2e6927badce7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_c1afb6c54b8ceec8bc1f121c","benchmark_version":"HLE original full multimodal","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":100,"at":"2026-07-24","last_confirmed_at":"2026-11-01T07:28:19Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5b1803aa53ae37b78e775ac27f61a658a307f6e77b3e139dc08d064e7ad296fd","measurement_key":"b11564492cbc0c2186727e0376fee621070ce87a2c6bc9adc248bd856a78af56","metric":"accuracy","protocol_fingerprint":"1d000b8ca17f30a20519c0fbea4c0033b69f0c618060fec604365eddb311a0c7","run_fingerprint":"5a69b22b38dbddbd17a3674fb69aad64338d3e3f2220461284fccd7ce033265d","score":56.3,"score_display":"56.3","source":{"id":"anthropic-opus-5-hle","name":"Anthropic · Claude Opus 5 System Card","url":"https://www-cdn.anthropic.com/ceaf5c7ff2783855203fde8208ec311252dced5b/Claude%20Opus%205%20System%20Card.pdf"},"source_authority_tier":"B","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_54c2373720fce61d7d0d3fab","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-17T14:33:50Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"446b5ca3b4c38b02715fda2839030a7f1f1df4d5dbde32e17330be3b9da3cea9","measurement_key":"6fa826c02558209cd77d6b9e3bf549e7e147ce57e167f94dcbc70e2880b1e1f4","metric":"accuracy","protocol_fingerprint":"1e81256caf684d8eec577c6a8080a1e254f3004233c6bd143c67daeccd176ec4","run_fingerprint":"b3ae8bea66dc042b2a7b0e1933fa4b35b469026c406e585cd0477dcfd9e94013","score":54.865616,"score_display":"54.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f5e20de2b8c2c1608413991238e73b085ef75a671e81a636296ff00de3b1ff5d","measurement_key":"c7dbdc7565aa8a7daaebc69f71020b4fb85b61b3bee63c8ddb49ccd7f0690b48","metric":"score","protocol_fingerprint":"7a4f80d8916be3d88fa02c0f398788a026eaf7a1396b4e20784cc5a5cbe5c798","run_fingerprint":"4291d8fd245bf4e8c82692959c4fe208061771c89ec2165c6ec7938ec2b6a701","score":84.333,"score_display":"84.3","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5804e2d7e5ec1a1f5599551d3400bceb9897dbd45bf7efba5732ba11ce522fd4","measurement_key":"204ce052949f28b4f44428c42da44e729e72609fe3e0fd08ed1d525c1f3f50cc","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"27c26a3ef66768a6d5fd32c1259722b1837eb4b670b2ae6f860c2a51bab7756e","score":80.08497619047618,"score_display":"80.08","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":101,"at":"2026-07-23","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e6bf68c5c7f139e05a6aaacf58e0c7090e6f1290e11bb2dba8b7ce4740acec58","measurement_key":"e1bd8b49802dcfc33f5f7d90f22c877cd5d0c25706bb946bb39d5bbe7347b4de","metric":"pass_at_1","protocol_fingerprint":"5ff8fdb52cc4957ca9d9313f813773f22df0ffb3dee80a5f1369ac967b689aee","run_fingerprint":"ced82a3135dd3360d0d0a52e42358ec222ffd48305627f98db910d7babaa0a0d","score":89.033,"score_display":"89.0","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":89,"at":"2026-08-03T15:52:23Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a1bddee423f78627facb0bbcd108bd5d50145a3fc91b2208b490b517c3a67977","measurement_key":"1675cebc7efd1894b32cbff87e8d5730794ee1a003b512e3371463f26541b86c","metric":"pass_rate","protocol_fingerprint":"483b27fb5c12f6fb34d5d067e675d6c462770bd2d68dafccaac5220dd8b7ea2c","run_fingerprint":"aa0a630b333e7e56482edd38f653a0c768862366c5ee7f3ddd2eaf0a1e007b54","score":85.8,"score_display":"85.8","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1f510fcb6cca3743ad871cce","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":11,"at":"2026-10-20T20:32:21.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"59f89fb10cb1ec882a01229237eef30e31e47d86f7ca49ffe4ebea045c2c0d37","measurement_key":"910281340b4e7ba2d0eda17ef02a2c55ca4007476dc7dee95c5c460edf36c577","metric":"mean_score","protocol_fingerprint":"331a82c06468adc747ff58df364d74ffc2f7fbe2b5d6ec6e706cdcc5f2336ecb","run_fingerprint":"1a70bbad68e6959182c78917cbe70e067514d8ea0fc2dcb1d3ef91cc9055d749","score":87.77777777777777,"score_display":"87.8","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":101,"at":"2026-07-23","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7f7e209eb4ee1611eb628f96a63fc4e17f6c92bcd1b922f598d9ca06c8ed9cfe","measurement_key":"11f967fde3ebac1ef7a1fc8d07e57b85c362b6c4b387b3c6b575eb618cfb5d8c","metric":"accuracy","protocol_fingerprint":"b9b1fe4354da8dd8e5959b0fbd0f6af45b8632e77afe9df327d774f9d2dc616c","run_fingerprint":"eded7438ac1d156b0b01d6df0206d538d566ad8a51d27cd40bec4ccbf527924c","score":91.591,"score_display":"91.6","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":101,"at":"2026-07-23","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8d036e718cc8bc18dffb44cb8f7663d64e981d336244effaf5c7ea11f7f0afd2","measurement_key":"08ba323cd1272e381b7b5c59f0033e2fb4260f1147fa3d7a7345ad0472d9fdc6","metric":"accuracy","protocol_fingerprint":"f37d2f335aec4e908cb99d6013875ce9e43ebbf3f1114afafbf6f6b07913d035","run_fingerprint":"a8b84451b09064fd9fba5d3668fc3116a2854c147dfc6112e82e6921c70ab6de","score":89.884,"score_display":"89.9","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"osworld-2":{"benchmark_release_id":"release_15c5525fe39f33bc181dfb69","benchmark_version":"OSWorld 2.0 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T21:27:40Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e0fd9a210c3ce382239520db26581f54c924750db93b25bb31dfd17c908febfe","measurement_key":"298e5156bb7e0392de2ffecb020fcd87f25193f73a5fe8d3c7a8413dfb2ca42e","metric":"binary_accuracy","protocol_fingerprint":"7b8b7a1ab940a3e15ada25e67e664fc8cc3cd93e799a1174dfb120fba783b039","run_fingerprint":"a17b69654848b3cc40b8eb8a1c36997abdb6f461a1385fb93690f55c0a926c9e","score":31.430000000000003,"score_display":"31.4","source":{"id":"epoch-osworld-2","name":"Epoch AI mirror · OSWorld 2.0","url":"https://epoch.ai/benchmarks/osworld-2"},"source_authority_tier":"B","split_or_window":"binary-accuracy-500-step-budget","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":99,"at":"2026-07-24T18:40:39.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"36a7cfd23cdf5d76a4b852b810ea6a98fe77ad4288676e299c3b0caca9cea503","measurement_key":"74933b31df0a422911e8e1a6e42c7a001f1206faa3e51aa15600410cae8f0189","metric":"mean_score","protocol_fingerprint":"a9d9b4fc68968f9abe8cf470be2c363f3e52f5d85ac66dac5e30fc8c98d92115","run_fingerprint":"8f7ee8e98117813caca0c1c92a8b46158defa354343f0c8937fc98797c83d6be","score":98.88888888888889,"score_display":"98.9","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"10d2a000a1b6795c95a7e16f72e6cecc66774b653e343a920b45f14b5d548ca6","measurement_key":"d76f1c2536ce882b75ed87134fa70679fbd617265053edb684229fd0d97b0edc","metric":"fully_resolved_rate","protocol_fingerprint":"86f22b6a3209094afa1cd49f8c0aa87ffa6a73fb2c6b1d5590dff894c33e5945","run_fingerprint":"727772146520f09a3280c5bc3e87ffe64b045116a913615e528a781a856d3373","score":3.0,"score_display":"3.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:15Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"49dd9702e4e69984ec4ee37a5c743c3db7b22b84ce8806efec896cff99d0ebe1","measurement_key":"5d599c98ca29e40c76e065af524d4d389cd53c03999a3cc03f334ddc567871c2","metric":"subproblem_accuracy","protocol_fingerprint":"cd9e7560d85a0322d3b34a586a289f41e6311f90632278fdc833038056ffc518","run_fingerprint":"35e0121a42bd54fa26aca412698bd380f4c2fb0f2f5f3e41f9bb26ddda9a6982","score":56.3657407407407,"score_display":"56.4","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f4a1394950dec513d8d27cd96bfa2813780e293c7daf53404107339f6f8e8f8b","measurement_key":"65be55fd1cb5b01f5840fb3600162d520d6a90f322d5b444b9f0b8b4f7eceac4","metric":"accuracy_avg_at_5","protocol_fingerprint":"45dbeb835a69df9d86f682a1b1ef7127e521f78f7e45acad94d8565d9d92bf83","run_fingerprint":"39d0c5fa268349b1c52553059128bf3bcc8b0614f34b221b365cae78e2ac5c75","score":80.6,"score_display":"80.6","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e69018c538773cbfb94889c7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":82,"at":"2026-08-10T23:44:04.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d17c208ebddb7f596810111b5df5614d261a6fa6f9fc1924009880646c74e412","measurement_key":"aa517a230c2792f9947d98359c716f7320a330ccc589aeef530cb6fbd465827f","metric":"accuracy","protocol_fingerprint":"fbb17761ac6cb9182bdfa96233250087a44472d8d76f545b1bcbafe7cf828e8c","run_fingerprint":"7077b7de72bc989e8953fd3023e4bc62813d19c92ea57d361d08f44ac39b6895","score":59.9,"score_display":"59.9","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a2c28f2560197339892088092179f16c6af6ece271dfd9006affece86c05e4c1","measurement_key":"749c4d2be941f1e182d98c0caff834f52ca7be2d21d66e8b9f0afc23571b24be","metric":"fully_solved_rate","protocol_fingerprint":"aa4ea5f3bc4684b3f5e30a236b21d41ffcc0166fa5f2639024953fb121e050b3","run_fingerprint":"07dde57d1f5502c2d4a5e00c93359a47d8e8451ea3e756bc7d8b6028f34709c7","score":12.214,"score_display":"12.2","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-pro-v2":{"benchmark_release_id":"release_d9b58bd286ce316ccf0ed891","benchmark_version":"Scale SWE-Bench Pro V2 public leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":25,"at":"2026-10-07T01:44:58Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"283f940fc4a4e5ed434303e7dbc286ab0cda5421548ba16ae668e289b92d0ab0","measurement_key":"04608c7d6ffc8390feffcb45d0dcf5895b98c434dbc9d1d2c25267cf475eaef5","metric":"resolved_rate","protocol_fingerprint":"521f840941d0bcdd2952385a122ccd07341ed5af0d88670cc38c72a7576eefb3","run_fingerprint":"44934f8e7ee78ac7426b96cc93e10504a3092b47c4877ecfdde1e356c2a3b454","score":99.4,"score_display":"99.4","source":{"id":"scale-swe-bench-pro-v2","name":"Scale AI Labs · SWE-bench Pro V2","url":"https://labs.scale.com/leaderboard/swe_bench_pro_public_v2"},"source_authority_tier":"A+","split_or_window":"public-v2-642","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1f510fcb6cca3743ad871cce","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":101,"at":"2026-07-23","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ea7569efe1075f992145a9a17cfad4a510fb290a3f9bbfdd79dff3d4a04f246a","measurement_key":"1b5c2ee3a23f6ccf61fb200108fd3d6037b9d90bae60877f3500372cb3b6bfb9","metric":"resolved_rate","protocol_fingerprint":"99d9805a5246664aab20ecc8561bb9de0b7d37ae92eec218f614c2601eba72f0","run_fingerprint":"fb5197d4d2512514d1b70616bb46b70e2b43f2902b8e3ed454150e47fd584ac0","score":97.0,"score_display":"97.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_37b9c147fcce0c9004cd857f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":{"benchmark_release_id":"release_ed49ef6cb40ad079db5a0835","benchmark_version":"Anthropic 500-task evaluation","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":100,"at":"2026-07-24","last_confirmed_at":"2026-11-01T07:28:19Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e6dc434723dc6f372c9b6b4e5d2d52ded60edb4f8f02902409e770e0c9771c42","measurement_key":"ffb5bf46d7dfaa287fcd99f27d06e73d0878dd32a20e449b602a919d6a1582c3","metric":"resolved_rate","protocol_fingerprint":"5b00a05592ee416553a42a6423ee1e8bd6262a1f79c843304dd591526b353420","reporting_origin":"provider","run_fingerprint":"37384fe11c13a520278be8f249dade2e2dc6a13fb4106847fd8986db8c4081f5","score":96.0,"score_display":"96.0","source":{"id":"anthropic-opus-5-hle","name":"Anthropic · Claude Opus 5 System Card","url":"https://www-cdn.anthropic.com/ceaf5c7ff2783855203fde8208ec311252dced5b/Claude%20Opus%205%20System%20Card.pdf"},"source_authority_tier":"B","split_or_window":"verified-500","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_54c2373720fce61d7d0d3fab","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":101,"at":"2026-07-23","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ea7569efe1075f992145a9a17cfad4a510fb290a3f9bbfdd79dff3d4a04f246a","measurement_key":"1b5c2ee3a23f6ccf61fb200108fd3d6037b9d90bae60877f3500372cb3b6bfb9","metric":"resolved_rate","protocol_fingerprint":"99d9805a5246664aab20ecc8561bb9de0b7d37ae92eec218f614c2601eba72f0","reporting_origin":"organizer","run_fingerprint":"fb5197d4d2512514d1b70616bb46b70e2b43f2902b8e3ed454150e47fd584ac0","score":97.0,"score_display":"97.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_37b9c147fcce0c9004cd857f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":62,"at":"2026-08-30T11:02:42Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"18b0518de7854e79588f71d6580b3d07a186ebee8c2c382620e227ddfdb5710f","measurement_key":"d1592adfdebef0c2d9cf3c4c2bb5e0021cba6c66b39174bea3e422940fed98a7","metric":"resolved_rate","protocol_fingerprint":"7486ea3b687109a351af3f6f316d3157c470fc9b0cf20882bf67adcc9119d146","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-05-15/2026-07-01":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":62,"at":"2026-08-30T11:02:42Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"18b0518de7854e79588f71d6580b3d07a186ebee8c2c382620e227ddfdb5710f","measurement_key":"d1592adfdebef0c2d9cf3c4c2bb5e0021cba6c66b39174bea3e422940fed98a7","metric":"resolved_rate","protocol_fingerprint":"7486ea3b687109a351af3f6f316d3157c470fc9b0cf20882bf67adcc9119d146","run_fingerprint":"7cabdd002693a3078961d470f44b203c8c256b056487041f92cdffdd3829242b","score":63.42342342342343,"score_display":"63.42","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_39a30289a15f1db029022e6c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"}}},"run_fingerprint":"7cabdd002693a3078961d470f44b203c8c256b056487041f92cdffdd3829242b","score":63.42342342342343,"score_display":"63.42","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_39a30289a15f1db029022e6c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":90,"at":"2026-08-03","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c177741c149a615691d2676f1bfdda13b33f6752f927c3bdc8df2418e40c46a4","measurement_key":"a659aa9994de9e7ece38f2a782e2d475c1787d300559291470da4dd837966e0d","metric":"pass_1","protocol_fingerprint":"b506c9b684e54c4990e42c89c90ca0191030f4ede4e7efce735f197e2f9ed3e8","run_fingerprint":"5c96e3eed570ee8ad72d91901a71441b7b130ce45bd307ad0595748d884f288d","score":48.71134020618557,"score_display":"48.7","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-09-17T14:33:50Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5c31dbbce5666d07e723fc4f9b80fbede013c406fefe193e98d06b65804bfd59","measurement_key":"5dfcd7b731e3af0de7ab93b48b5fbdb7c277be58a16870b040bc784a97f7b9a1","metric":"pass_at_1","protocol_fingerprint":"154f156c90ea702c55f0088b80f24f0bc7774ad5213995666b58947943052ec6","run_fingerprint":"29519ff8c1a2f1c4b11ed1a5ba1d6a524f05d7ecd4f3484ccaa730503d9b9391","score":42.061856,"score_display":"42.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":101,"at":"2026-07-23","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1c61f901c2556734dc534377074c34016966775866c9e9f9b36a1db4d00915c7","measurement_key":"cb2bced4d77be6ce6c78f491b9974e6e69bd3869f69353c15264245a4af8352d","metric":"accuracy","protocol_fingerprint":"4d15304576a02115cc358aa707c120be20d7564e2737346c0d7a69b2ab2bcfe9","run_fingerprint":"847ffe07ce22b665b4d6506e02dbfdb23d65eb667dca9d568babfd9da2a1ccab","score":84.644,"score_display":"84.6","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_39a30289a15f1db029022e6c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-3":{"benchmark_release_id":"release_ceb36f25882d8cea2c9d084a","benchmark_version":"3.0 · b936386b-4afd-4ad7-aa7f-6b52bcab9853","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":80,"at":"2026-08-12T22:08:44.699364+00:00","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c3d9b14837df09d99fe6907ac42c1da03a61d742061c11370e38024406950436","measurement_key":"5f45f5cff7218bc889612b669127d3f9f40e96a9256abeb4bcd63e84db219a62","metric":"accuracy","protocol_fingerprint":"5131b7fcd81347976de3f3afe9b5af9ea833e46f36bafd8cdc477f8e699e3974","run_fingerprint":"6871dca2fd8dd990bd67c2b29d8582c79618b751b4aaf7858a370ab31ad98dca","score":42.7,"score_display":"42.70","source":{"id":"terminal-bench-3","name":"Terminal-Bench 3.0","url":"https://ofhuhcpkvzjlejydnvyd.supabase.co/functions/v1/leaderboard-read"},"source_authority_tier":"A+","split_or_window":"official-74-task-leaderboard","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f36d2528199738ac88394386d15c53b26eab6ccf73bb4250719d3f5d25a282ed","measurement_key":"78c93c18086ec4d8d91c5bd393bb878194bcd3a00a6e04e3f79d079a572e9123","metric":"accuracy","protocol_fingerprint":"5988374bebca1d4a685e6a5a7ce86a373896d268560c8948d3c339b7c600152e","run_fingerprint":"a63ae0c93439c5efe64c6b0cc39942f10155da922c4b5998da83a4c051beadf6","score":53.535,"score_display":"53.5","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e16963f2d47b8bf2f6bd54d9e4db52a7aed69197dc0099aeb29480724f918cff","measurement_key":"840e5d00bff18939a42a307f147b3c5d5935439a28fa2c576ce443beee889ae6","metric":"accuracy","protocol_fingerprint":"44ff308b1784fdc20491c360809c9b64e80834fbd42894c4ccc08a9a65e97dc1","run_fingerprint":"6f36e9bc4765b8d572ecffa89ece1e05170a8d014260409c093a384c4695da58","score":27.143,"score_display":"27.1","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"26d2fe2921b04a5858580a30ec05ed0c17cdae5c2a91613da3c9d11364ea2258","measurement_key":"4495637f08e1ad07a5cfd5489bab51059516aee0017e978aa6d66095694ec780","metric":"mean_final_balance_usd","protocol_fingerprint":"ef5249d0c3264aa5f421a764813869371b4d544ebde5029afcbb4ab79490bf64","run_fingerprint":"0de88fef3ff8d1446df66f86740b5722d8bffcf442e6f1b6b0e3e80220347ad2","score":11181.87333333333,"score_display":"11181.87","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1e112a485e54e7367e8e34df","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":101,"at":"2026-07-23","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"98c4ddeb8d354c4b8df09717805a7c7f62ff4e34e0d64fe9b99f124c32fe0371","measurement_key":"97acc9094e8469c61594fc42d68277d9a6b59aa0ed086a59c2709cc46c6d033b","metric":"score","protocol_fingerprint":"ecbf2c6f455534b1098adf00c37ce0bf5466f0c96902095e7437cec06808394f","run_fingerprint":"8e44f161ac4d12d30044e6f82edab9d84bf5ac86744d8d17ee99fd01253f9a28","score":88.404,"score_display":"88.4","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ed92784a3a69757d5a7d96f7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"45206f0e5175578cbd241821c362fa5b02101f8206cffbfd45e99128e9335f22","measurement_key":"2d6da0bf431f710113081507adc9210a2a0e424be4342bbf99746f73b7eeb3af","metric":"arena_score","protocol_fingerprint":"4a21fa8bfa35e740283ff1fb138e267eefe15e1b1075757f3af9478970704d8a","run_fingerprint":"622696cab4e4b65cddc0ede9bad78e63dd28402bd2c72e5d875752145923b64a","score":1690.5239169555273,"score_display":"1691","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5ce07bd36fc8b21acfa77c083d8e9c0df894e8d4a927123480d0c05ddab32bff","measurement_key":"26a90d1363dc97f611b7ebeb10c5decc3779b7e5bf7ec2554f5cc6b85a39e919","metric":"accuracy","protocol_fingerprint":"329bc9c59b122dd43f418ca50148d734057d92ea5b39e2b294aa783aeba0d7f2","run_fingerprint":"89b627bc672914d2a2f7240a5cb783d18ee0d5d4ad9dfac82abbbd8c5d416c3b","score":91.78,"score_display":"91.8","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_892e19ae915f3f7411f86632","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c9d7eb78a63d9c3c28e15e5c2e673f3e57732b390ec9455787de4d469e35d8c3","measurement_key":"35cab77f4114d89953edb1da6cd96efbc2857e2ce7c45f5e383b445e7f0e053a","metric":"token_efficiency_weighted_score","protocol_fingerprint":"913ef5fa9976cef286ca0eca6e352de5bf70b90e94e06797c7d7e94c9957ceca","run_fingerprint":"3866d08f40f87fcdaf0ea2eddcf2735d89114be79a96808b099c591e5d092a9e","score":19.01117537878788,"score_display":"19.0","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1f510fcb6cca3743ad871cce","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"anthropic/claude-opus-5","model_name":"Claude Opus 5","parameter_count_active":null,"parameter_count_total":null,"provider":"Anthropic","selection_rank":8,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-10-01T00:44:58Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7c48dacb549def427c32bcd8e68599e4296babf6c78b54d14826b86bc749d14e","measurement_key":"4a0369ca4e5744a613ab825ad0ac3f64a88bf60c13a96fd65f8a63734af90863","metric":"performance_rating","protocol_fingerprint":"6a34c99c14532b1f26a2789f7735f72f05f0d81749399afa6ba4f8498f756292","run_fingerprint":"4c0dcd04b726dead1bff926b078b3e2349ca2b88693ac48d4679adce0975fdbd","score":2462.0,"score_display":"2462.00","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-10-01T00:44:56Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"23b269301e2bac5e92cbe0075e6c8c7158aa48d043a783f9ce8c050c64fcdf30","measurement_key":"edea3338d7227426f9012ce23a839e254bb88c7895c13c202e234d1bbc48d31b","metric":"pass_at_1","protocol_fingerprint":"5fb09ee23e7bf8a678bf030d728afd17392fb8685d8a87a3c5b0fb2a8c0cf47f","run_fingerprint":"9e759779f0d14b673dd0252433334d627ed66ed0f55b7d6ac4ab9bddb12b9ac5","score":54.300000000000004,"score_display":"54.3","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-10-01T00:44:57Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5fb29d09da01e911fc3ed518dff67029d7ad0ec120a9cf13a9aafc57a45d36a7","measurement_key":"203c6017445a088f1257bdde526df5f034fa0871e55ae033737e57c226a2124a","metric":"pass_at_2_accuracy","protocol_fingerprint":"d7b031deb2993c493ad55c165aa96a6e265dce5585f86616aed811a10d6834a5","run_fingerprint":"1529c71477cd7c8ce70e7e47e13bf4136463c9f85782b06449eefdc4f0aa1ea7","score":95.5,"score_display":"95.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-09-30T18:53:20Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9fdf04a679bd41cc2f6b486b0adfcb1b0b835b5430f6efe3d5d2106421a700cb","measurement_key":"1bb612405a3d3d1e73296084fa697428ff2a2dd75ab4a48a180d71a06a2a5dde","metric":"accuracy","protocol_fingerprint":"b4e761fc2548ad008906036cdcdeed912c2582cf7697a517cd71e289a02236d0","run_fingerprint":"39140efb96e55fca94135b09d5e0cf7c95d48ca39d1107f4122f74caed23f42c","score":89.58333333333334,"score_display":"90","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e2a14bc236153b4c3ecf9cb3eb9cb675c7e40275ad6e256afe817d5132ea5331","measurement_key":"23dc03838e1afec0a5c8d05dcd454839b0b96eae35c8a595abbcacc55ad4dc08","metric":"ips_score","protocol_fingerprint":"59d7a985c1839c87874b3ea22d374b32101c9b6bbf15a60b51dd9ff0cfc07fad","run_fingerprint":"1a9aa689d877250955be43cbe0f24ad3a445e911393ab3dbb4c30cff5541ae3c","score":0.07955487093669349,"score_display":"0.0796","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a5456a9a2ebd58c6ac8fed2e4ef2fd909e145f0829c1f47ba6359288eb11906a","measurement_key":"d1941ccba4f2801797f180ea30c21fe86299f801569d3f0dfc88c7d3e4895003","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"2c01d7c091206de4df601825a473716d7c70e5f4f03b71a4aab92b66f1abd99d","score":1458.3170296467606,"score_display":"1458","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:41:42.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b7a6c914888276f682cfced7fc5353b1889c37ec4dda13d2a8cb03ea676b3901","measurement_key":"45e64c7c97f255b4c1df1b007a35a256675edcc0e3e5b012fa4d2edef4c48072","metric":"mean_score","protocol_fingerprint":"3c040d631f24d8ad59bd5d84fa318c03e503eefbb0a7fbc628ea7f614e16c8bb","run_fingerprint":"22856c382e973e3f0d52d6adb53b1ff0a761a1c03ee1bb742ff8cb1d589b51c3","score":56.00000000000001,"score_display":"56.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"95882c395dc0b0ecdc7050cf168efb0dfcd46409fa04499f73f8e7ceaf671e65","measurement_key":"40d40df9901f4f795d3a509c9fc2aef61b03034c0f5a415d792842469ba626c6","metric":"accuracy","protocol_fingerprint":"2783ff7922e7de2fa7cee83e600eb567df40742698601a4653d1786a43930ef0","run_fingerprint":"0d7527306ef3428b7df20fa42f553703e6a55a7ce730e6aa565b508cd9e676b2","score":30.8571428571429,"score_display":"30.9","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e3d281d5ac4ac8355e4bcd892f1cb6c9f12c35677519b6254682a4475d28348c","measurement_key":"d073324969a024f0880ea383bca30b86ea5b22bb4bc6bb4fd5b9eaa007fed609","metric":"eci","protocol_fingerprint":"bdf24cef4a55553ba7ad44003445881c756bdc2d3eb4950c44b500d538ee1b18","run_fingerprint":"004df49752e45c2bf0687444d1e0c9a6cc87409d10e8c132d65bbaab4d4ca91b","score":163.78,"score_display":"163.78","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_adcf9c2d99684658e4bd5117","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-10-01T00:44:56Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a0b09988d9298ba09e6455eeeceb3c18b4b9453bd9c7137a813a8547d0ff538d","measurement_key":"b1a531e4d6fee7d8bccee9eae8fb7eacdf0c99443db046b923a75fa4e73824e6","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"37ba1673ea5b1f77ea7bba1408caee27aacdb2cb0784d7417b3a75b89083fd5c","run_fingerprint":"afbf3304d224c29c81a42f295a05feca766f134787366078729d7ac89b3a1f67","score":49.27,"score_display":"49.3","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T19:59:24.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c54c7dee8d2a1e235d78636c59d44e236ac2efb542d9574c9af04e9343d298a1","measurement_key":"27933c0d2dd2f83cf8b24a2daf3bc381432c8f6e342b38ee60a6f7f661f830bb","metric":"mean_score","protocol_fingerprint":"c79b1fe7255a430d7782a3c82799bd0574be029d6b4d8fd89c716a787ac624d3","run_fingerprint":"ff44365e6747a66d27f01de30f303fd60b7b716da22050b7720959e35063da65","score":89.82456140350877,"score_display":"89.8","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T19:59:24.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2d5892a79155363a655cb6a2c0e1ff7018efe96fcc22fc338d610bb59eedcd2a","measurement_key":"ae597113315e85cf57c31050dc3860b06619060243f49161ee2ca0c0c86f1cad","metric":"mean_score","protocol_fingerprint":"5eb0d83a930ef1849d72bf9941be0f428443b42ac0a1368b3d6eb934ecde6f2b","run_fingerprint":"a3ef1c5512bf41b161fc2fad979e0b618817c9553107376550c3c8be58896863","score":90.0,"score_display":"90.0","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"98111d7c58eb02860f5f30ced617af33c0542bc2cdba9385013a2eb8200696f2","measurement_key":"6f458f7bece46205ad92f00515c913fb4155f9f4530660abc92845f9a8cc247b","metric":"elo","protocol_fingerprint":"96ab81ae4b49713f781b89250902ba8a9d4543057b4d5699500f63c5d986d76d","run_fingerprint":"d6ad707dcf8c247fe202d2c6ac68384dc5aca2be2e786214d280874500cc0c9d","score":1515.88,"score_display":"1516","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T19:59:24.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"84225bde21e78759a5d942d1b662bfb0b4024731a221088036085adb3d26d764","measurement_key":"7e6b86904f715e694f02dabda8b4611988799170ff42fa54990d80f57675c41b","metric":"accuracy","protocol_fingerprint":"a810ed65ab93af76f7fa38055d2734f05182535f56d8816c76257cbeeceff2e3","run_fingerprint":"ca7151100f115dfc1763d200ec929f006735e6281bbe33f6d1e241e623845e11","score":94.31818181818183,"score_display":"94.3","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-10-01T09:31:57Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e9809ab364843d5d9315b8e2d106ca69e6b610c41d53ce1f75c934248acdadcd","measurement_key":"8381f6c17aaf0c9cbcdd0248a786e57ddea37f135117e1432765056812da1f18","metric":"accuracy","protocol_fingerprint":"6dc7bf79d149cc8a5b818bcce561f84eb258ebfac9bbed142a05f737636ef2f2","run_fingerprint":"c70db6e58813023b7a184601283a3c6e50b0f18ee3235ccb780c2193945ef9f5","score":47.914736,"score_display":"47.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-09-30T18:53:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"65463fb2ec2cde32887d52eb6cb97bdec3ea6fff550d8233438d7d554b0249b1","measurement_key":"65dd50a1f8a56adaf54cb568627f2a3b8a156bce5e85525d10f87d40df9dbc35","metric":"score","protocol_fingerprint":"80156255415b1247c4be1849e3b1fb406ca75e82ddf3eea4f1395bcf7488fb9b","run_fingerprint":"d6d585f7d6367de735f6a904a56451f87f876db1b3c87ca5b30ee7ebb40cd67d","score":82.611,"score_display":"82.6","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-09-30T18:53:19Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d9525f8df900b6199ab887afa0fd236512c462e2f492a50e8d65cebdc7400124","measurement_key":"537a024434b1ecab8c3043fb73f95243ce57c23aefa817c380228a72010552fa","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"0cabeff69b5c782657de8ee8dc87cce2e395912adfe956159cbdf96417f739cf","score":79.24545238095239,"score_display":"79.25","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":30,"at":"2026-10-01T09:31:57Z","last_confirmed_at":"2026-10-01T09:31:57Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e6397fa5d1870b8e5114a60b82cf83fe325cbaf63486968cc049ea580012eea8","measurement_key":"27fff98dafd052cf7cceaeac3f768593ef9d4412047df2bac600a13ed5df8099","metric":"accuracy","protocol_fingerprint":"79d7e035e0b2097f236b40d1ac9970abf0f6442601c9cce7248e27665d4b93cd","run_fingerprint":"dd89003585964b02290da255b09e95414f7a8b6b844a49773c7f35ee9a65950c","score":82.947977,"score_display":"82.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T19:59:24.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2618a8d6a667d4af1ceb34799b11b013e2386a9f103178672e63b282cc65644c","measurement_key":"f7d15bfca66368103e43b4757c6ded44c5e3dabb73dd5b354e177145657358dd","metric":"mean_score","protocol_fingerprint":"c54492e9d4068e094b3ae279760a6322c0ae91c104cd7424160602b3e18c3af1","run_fingerprint":"537bcc9dd80885b8a8643cac6e7009c4ee0b827cafa53eb89e53095580f2ac18","score":100.0,"score_display":"100.0","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"361b9834ce7f7f16a15b6d2a14799b9bfca41cbe6aeceb4865a1331cfc94c66c","measurement_key":"c14b6ef4b48891e984d6ae21c1edef8fd69f45dcfd76ffc92fffc8b53f8e3610","metric":"fully_resolved_rate","protocol_fingerprint":"2d69e437314107049b8a8f122568434c145e2f95457508769195e6734d362d5b","run_fingerprint":"52b1abe327f6d2168b4dd1256fff69d06c5850dff6c152d07c0acb78b68910f7","score":2.0,"score_display":"2.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7546a9ff8d70375c497c4e13da471fb04bbd57945c4c59fcbf457635211c5913","measurement_key":"82ef9d0f6d15164336cab9ef39b3a35e17dd4fb744f44071a57904fc57092fd8","metric":"subproblem_accuracy","protocol_fingerprint":"b1dd6ec6a74cb39581a5891ec66a630e5ef80ec3d83b405f17bcb8c5d6ba8ad5","run_fingerprint":"80210d9b0aa0be271172d7f70ed21b181acfaf7898b6afe6d29541b4f07f4091","score":57.63888888888889,"score_display":"57.6","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T19:59:24.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"97b2de31efd3dbfd86fd5466c06f6aa4f32936b5749510a7d1626a59e9511583","measurement_key":"9d4b7ebca41feddfa631e217ec8702eae5bd0e460f2c54aaaa72d89156ba9604","metric":"accuracy","protocol_fingerprint":"418b64e983ba024c19a2a130b1474da08ea4b1b41b7e78d42b4539f491bb8e98","run_fingerprint":"8d8eb39ca3be7cc3977ee9c5d09f74ba263e67c22dc966591d5b1cd58c8fbe84","score":60.699999999999996,"score_display":"60.7","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1dfe5f1a04432d2168af5d9a485a0b3d80d9b2092f1c56dc934842a44fda3529","measurement_key":"373c0623764e192a2ebccf0d3f70ae73b19efbd3e8708b89f78edd5741cb8856","metric":"fully_solved_rate","protocol_fingerprint":"a775b1bc6703fd69152a1c474c83c16a95c6c5d107bed0679b0d963d93b14849","run_fingerprint":"e47715644fd7ee45d7697137c30e74f224dfb86b62819abd915821dd88e4d604","score":30.534,"score_display":"30.5","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-09-30T18:53:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"10dca70dcfe4d86a55dc0d6e9d509a4180276282036317a67eda3194b44e9a50","measurement_key":"c56b75273a3ce9623c13683e70bfd5e7b2d1e28389e0f3a88c1596a1b36b4892","metric":"accuracy","protocol_fingerprint":"fa669073d6a18d088b8ab262478d6f98c7c3bd89d5eb10ef1faadebc265f4eed","run_fingerprint":"f1d23c1165958724218fe0510ff40551711e58bad011c1686edfd006a56c64fe","score":83.146,"score_display":"83.1","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"274eacb219740fbf6d1ce2dd9d886cb5f2d22bcc94707f4e55d12144bf87abd7","measurement_key":"806522614d5d4b0f8439b2cb52b56d1d55253d8eb9b748a30c04420b31b5b289","metric":"accuracy","protocol_fingerprint":"6a9533a9bce842c13ab4f29ccc0b0e5ba4204f8ccb45cdba17396144f587d10e","run_fingerprint":"7258543ab0afaa91e60abae3f5847e3054b87f561d32904e075ac4494b3e723d","score":44.444,"score_display":"44.4","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3b125a955d5600f2d3611b147b635a7f6da106f52f7d9bef883b92f956ae8e3b","measurement_key":"b8b8260e8e11be46f6e64f3c9beb4e6270c0c18c7d50ee19829e3a8f56374e28","metric":"accuracy","protocol_fingerprint":"e2101a01d343a76b89923f742b04b1d735c638a914cb1c533e46805b1b5f549d","run_fingerprint":"5dc90adaf96ecddbf6f44a7f92db62358798509f3102c76eb8093f1cf872f9a5","score":30.0,"score_display":"30.0","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-10-01T00:44:58Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1cbd0c84728c7867807fdda58ecc40a4b56b0cce3874295bdce0e7207478c254","measurement_key":"5e5fe7435192fd741e6a0e5f496a143d87d0bd99d504a4cb249f7339cf1df23b","metric":"mean_final_balance_usd","protocol_fingerprint":"b9e3ab661cfd42b634c3fa7df2ed91045ec8e64a4189ddc39278315065b437b1","run_fingerprint":"6b31cce7f31666869aa6dee2400785a838e3935b3afb01f857e85a7b9e02e410","score":14427.848333333333,"score_display":"14427.85","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_88460deff22c56bc1bda18d5","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-09-30T18:53:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e0cee9745926206e901514fd00c17d0d864fa9f7f8e529a57a41a2339ff81fa1","measurement_key":"f54df9a2dd58260af15ec2090c659f7992dc8142241346c61de7187fea1426dd","metric":"score","protocol_fingerprint":"88ac255e46c1cc0fd20b4bbb8726af866f425e99124ddab7c2f5ce436ac8e185","run_fingerprint":"0a22a48f1711103205aba1f923958db8e12047965496048db5a7f961d00e04ff","score":87.824,"score_display":"87.8","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"15a6d51a6a8a7553ff3f323b950652be7540b156e5aa19eae0069c67899bee59","measurement_key":"a50afb349cd7362ac77e1e8eadd58de0000ce1fcf31e53bbdff8abf49cfbfa68","metric":"arena_score","protocol_fingerprint":"1225567aa529b62bbd6f38b05533dbe341af28360297bd7d34ec05327e5dd885","run_fingerprint":"a0adb61f9edaa8533c6c139de6c82edac670167984578dc4892ebbd82b797a42","score":1678.189584003976,"score_display":"1678","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0734f29421da39f59df77231","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9f1d29783754aa23b636cc6a4eb23e0c54d8498432b6e36f9dc2925c0b434b90","measurement_key":"3f8bf2e12cde8bf59042e4a24af07d3b2f0a3c794ef26ba0ef7ca48d20f569f5","metric":"token_efficiency_weighted_score","protocol_fingerprint":"bc6f0a429300b2e2e4db650e3325212c23861b7e6e9d29c5caa45ddc4c53f91c","run_fingerprint":"d4c01701f19235277d67e004c7df07fa27c0397b2ce44a773be4de8c82ffcc7c","score":19.731756666666666,"score_display":"19.7","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_95ca0426927f6f7637753fdd","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"openai/gpt-6-sol","model_name":"GPT 6 Sol","parameter_count_active":null,"parameter_count_total":null,"provider":"OpenAI","selection_rank":9,"weights_status":"closed"},{"cells":{"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8710da348a66b97032b97b958134a7a6e95be688e7146336e73cf3d6a6389284","measurement_key":"3e3c0e6f20e4c72aead73cba40bf06c6a702f84425d7e2856ce7c2c1648f6adf","metric":"pass_at_2_accuracy","protocol_fingerprint":"5c55a0d14a562b4baebbd7babd6ce742dc336a3fbf3083fd945dff3182317256","run_fingerprint":"3af7a9c17d4432ab033f0c7e1d9cb67adbd6a76c9bd66e3b171db2fc956e6554","score":95.0,"score_display":"95.0","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_52423dacb65ae6d97e85c24b","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9ec4f8f06ce873587d292566fcd4e9efb850ef7920fe1771b57372ec01242497","measurement_key":"baadd3bb7f1212e0994757383e5fe73a56afaa405c56cab799fe379d891a73cc","metric":"accuracy","protocol_fingerprint":"5fa4ab1dc988b73dbbbd3e7038300348d2ebb3420f14d96e9a745555386e7758","run_fingerprint":"dfeca26d988392632d6002ac2c1e0834ca2ff835c804c907fa247095d174a493","score":84.16,"score_display":"84","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_52423dacb65ae6d97e85c24b","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":17,"at":"2026-10-14T09:56:16.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5864f6a0362d5b410247534b44a66588ba3676385688fc5f830e2dfbae297b90","measurement_key":"30b1028b3a3378666ba306bcea5acb9a9eded5754670caf9f6ac8cd1358ba9bd","metric":"mean_score","protocol_fingerprint":"3051903b77aecca65bd9bcd122d735964e437a40265bf7dc07f8dbc134633314","run_fingerprint":"57310a8b975e256b0fe6690f32bf83ec8ae3f8b2881ff16adcb63bb35255d489","score":62.0,"score_display":"62.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_52423dacb65ae6d97e85c24b","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5c82b2c0d9a0c98c16452c07ddb851dae9db759aa7dbfe0c033fc66a91381a45","measurement_key":"688ecc91146ce2767ca138ee22b3e48215831433ec7c9d1d408afc10679f4c4d","metric":"accuracy","protocol_fingerprint":"6e9a72ec7b397b00d716faa7db3def3b0a76a46eafd9967d76071b12b785492c","run_fingerprint":"10a8596cbc9f7f66d9b79942c43af9c0eeafffce228b0e49742ee17278a74109","score":30.571428571428598,"score_display":"30.6","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_52423dacb65ae6d97e85c24b","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5b1ffe11a445cae3dc5588bbd66733e77920469951712b00cfe4baa131e00919","measurement_key":"4a7f636d3b96e6abaf50e2e390b034b9dbcf21e4efcf9c8e3cead530fe867b74","metric":"eci","protocol_fingerprint":"055fcc4b56e82207bf014e80f2b95e69d3ef0484b8c4a1ac93eb9856f114e5ee","run_fingerprint":"0acb1fbceb9ce8f138a94f5c7d9c3598eb55c4e65ef002a9d4672f91eef47ea2","score":163.11,"score_display":"163.11","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a898b81cd13e7c0a7333367f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":141,"at":"2026-06-12T21:33:12.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"21c731c4fdf4aef80bd5b6cb25898c2277e629983ecc1edd38d5718c4ff14c28","measurement_key":"f4afd5ebeb06b49dbff7ab991f32ba6adaf87ffd63cc19c9885034754159729f","metric":"mean_score","protocol_fingerprint":"4f7bfe326c1ca2ae446294e4eb0445dfa7589ed6b6ed974b7c4a84b746e164e2","run_fingerprint":"8cdf4bce722a77b01cfc475c6adf99c645d55da156a798b1b37340016643da29","score":87.71929824561403,"score_display":"87.7","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_52423dacb65ae6d97e85c24b","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":141,"at":"2026-06-12T21:33:12.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"eadb2fa4b724fec14345cc7722b0664900b218e48120520ff8a46c3d03222086","measurement_key":"b7bcfd2f51c8e5ed9249dc2e45c700773f443e1f6384a258a55edcc19e4d833c","metric":"mean_score","protocol_fingerprint":"3413c81f5619400532d2201f988104f1eb7009ba28c73c1888d3e790ea055219","run_fingerprint":"66503e0d38c8c1aacfc897e45e2219dfe7f780a0925234f4051fb80f39280d33","score":78.04878048780488,"score_display":"78.0","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_52423dacb65ae6d97e85c24b","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":190,"at":"2026-04-24T16:01:38.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"e5c459e323bc9a77cc9e7c866ee8958e8f29ce1d7a7024dfd2b02eeff32e28cc","measurement_key":"23998a4e47c015b6a42233e39d0977dafd5cd8ac7575373850cdf425769858a6","metric":"accuracy","protocol_fingerprint":"8a796135e8622378052adc7a4bba7c6aca7c1487fcf5796012bf357caa9a8c02","run_fingerprint":"94d4706c837da852af9a62cc6f6137513f07c5a7616584ef1ad492c697fa5b85","score":93.92135642135642,"score_display":"93.9","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_52423dacb65ae6d97e85c24b","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":190,"at":"2026-04-24T23:38:07.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"901ed971c51a7e914aeb897d5cd9d1f33c949720be14bdaa98506448ae91727a","measurement_key":"b4f6d517ee07d9b4c56834cb76507dec5e49bd0ab35fc2e8f200a691ae8a023b","metric":"mean_score","protocol_fingerprint":"30d980fc451103bcdee4e637b703d5d5481608163460c228f5ae952e8a48d05c","run_fingerprint":"0b7655b7251b61a6bc23f928d2ac93c3302877e3180abb38cbd0eb7cd165974a","score":100.0,"score_display":"100.0","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_52423dacb65ae6d97e85c24b","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f9d8078f687855dc332e5f72dfdf1385389c291a35d420d584c3407f0655dc5d","measurement_key":"a297398119bfd2f0f80f18cdfc2cc75a2a7b292497f2d2b96265ac154c28b490","metric":"accuracy_avg_at_5","protocol_fingerprint":"8253bf31f96ae1c9afe2d99ed7682acbb2c7f46187d7f9ccae405ec8d28f9861","run_fingerprint":"48be932c458154928ee621e9ef067c9a08105ab221beffa8311bdec4f2e29f25","score":76.9,"score_display":"76.9","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_2ed771acdbb41d4dbb230330","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"openai/gpt-5-5-pro","model_name":"GPT 5.5 Pro","parameter_count_active":null,"parameter_count_total":null,"provider":"OpenAI","selection_rank":10,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d6d6e978ae1711d45ee87f229348faada3d49bc0af523f683ffe600fdce3332d","measurement_key":"75cebc75210c55bb50b52bd1f2a06108e5757987b5180c633211a6171a0f7111","metric":"performance_rating","protocol_fingerprint":"dc8244642f7f31390dd20058e4f48b24ed9d0984f3ccb1e5aa415514fec7f53c","run_fingerprint":"370c9da7d673bef9427e32e4baac5bd978fffdff380d06232035e8659a4055a8","score":2041.3,"score_display":"2041.30","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_7f9f1833ebf92e99cdabe7b9","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d00a31214a47a7786f92de3f34ef1ce0fec57b62df7efd09807b8693fea481e4","measurement_key":"fab121874ea2fe7bedbe1351adb23143d79dc073be85789525b5956b7b992476","metric":"pass_at_1","protocol_fingerprint":"bc9d110ba473cb81753e768dd9fd0b3af54ad95a51dff0f750af7c5449f42f6e","run_fingerprint":"8f1be2860bfca6dada768506ebb7539706ed0eaa5ac18c7d941f455a522ad965","score":63.6,"score_display":"63.6","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_482e02f0349d00ca23df8127","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b28615ee2fd53429cd2f16bd4c3b5eaafb6f6570ff5e5520892404553b77b15d","measurement_key":"c6c0dd146034956ce3322119838e57eae032803b8836b706b168ca9388c03b16","metric":"pass_at_2_accuracy","protocol_fingerprint":"b0414f41aaf342e7ff1cd853c181942869f80751290a1146b532d5a39da93666","run_fingerprint":"e78c228ec434f1dda728ed0a68263f517e48adda2dbc29bcc79fbfe48337abdc","score":98.5,"score_display":"98.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bc9050dc40ffe4292ec5c712bac35291635a433c0ab478faa5f55c8a9739a7d7","measurement_key":"193cb4a428c329e2f06379f645f4d8a3991cfbc80ab01fa17f03da83b987bf92","metric":"accuracy","protocol_fingerprint":"e024ca81ea8330bd940276ccf8b5472630fa8413936da5e779560a9ef9b5e720","run_fingerprint":"86c783962ed5229f01d4a83cad71d2b548a21ab4559d34ffd4bf0ad31692c24a","score":89.16666666666667,"score_display":"89","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d10f60f4ca8abc579f2fa28eb3130f52c1453f6f4dc4630745995db3c8d1046e","measurement_key":"57d680f5a4a864374fcfd660220ad0cb4341da1e63ffae488ef55bccf5f84787","metric":"ips_score","protocol_fingerprint":"b4c953ead6eb790e90823c14ebc6e0ffa52b04ab7304a88b7cdfd2431c31dc93","run_fingerprint":"01cc162403b81fd98c1cd5f76259694a40405a2a68e68d586e2d7b840e261472","score":0.08037071257211915,"score_display":"0.0804","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_7f9f1833ebf92e99cdabe7b9","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"31fe857d42bae7ae4de811e75952bfe51b4aaaa9ed08d35cc3646dac0f342b10","measurement_key":"5d8112e0c1f3c414108c9050e8900fcc3f2672010c985ce4e146cc39bd0c191c","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"8b01dda50b2f80039d4a344fb16b3297ec4d2614f0fbd2b18fb9a2bcf3e0ee25","score":1503.8924288671988,"score_display":"1504","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_7f9f1833ebf92e99cdabe7b9","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:34:37.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3f70dd1b632a3bdbe5c86a033a56aa2bc0299b452649b92999054799375e5684","measurement_key":"f9dd8376207416f080d30ec82ab13caac2c7ba144af1f0d6fa38dad555b63a17","metric":"mean_score","protocol_fingerprint":"43db1cd9cc34c69e6119c2d8ac08ce75a756303fd384a46ef2ba5811050bfd3b","run_fingerprint":"9bdd3724c507c825a5feb0eb8effafbd5fdaab4bd348c5363c109f3c7c684cfd","score":47.0,"score_display":"47.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"75cf8b806ecf25b79a7804ef1b70525ae7188182be6f2d26d9fee123a4a51a3d","measurement_key":"5cfc82387b07596fb83e59c327d1ccfd2467fce1f24bb3bffc373e7d878cfbe4","metric":"accuracy","protocol_fingerprint":"4321d6acc6abfdae97c5ed803648924165747bc8b7ffbc9b9eb203d02a56e7b7","run_fingerprint":"f4032edccccba4f202a1d96907ff7d2deb1f3decfd3b18f31c6982b8dd1a48a3","score":28.571429,"score_display":"28.6","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_a31432cd65f025d42eaa2c1e","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5b1d897a7c8933b8bae3d1c20b81de5d138d82c98396909cae93ca1da4ff362b","measurement_key":"421db2de7b1e39ff577b9d968b156ba0693e30e57101865448c77ee400d912a9","metric":"pass_at_1","protocol_fingerprint":"797587c900d28819d65b1a843e000619b9085a9e51651fc1d82f041d9c7727b9","run_fingerprint":"be6c80ea3b852479be8ca41f35808eaea58ee510f26dedc16d021569f3c6fdea","score":69.72477064220183,"score_display":"69.7","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"221c0ff8fc5c45d99e6eb1b0c8329843bd60e7c90d1b492767f4c73fb742916b","measurement_key":"b9b3642411037a7322e8d68baf54c1ed47241ce273a6a832f1ba258138a658cd","metric":"eci","protocol_fingerprint":"324b4325735f95c565d5a1a034e1ffa643ab72471785ab07045f4222d00cd63c","run_fingerprint":"716c8e1564b51f9289a164f8fd0a2c6bd61be18769931691e3c94a468dd5863e","score":163.02,"score_display":"163.02","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d040556a661041609251c38e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3a8de3d7aaf29402002789ef80fd73da1e0373192ed3e4f018aab6804295f90b","measurement_key":"5a70e0db3e1dc96a4b1064937717446e5bc1e53a7823a1c6524efd1df29f835e","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"6649cc8bb042759199d52c18d26911120b5def9ce97292c82302590f034245eb","run_fingerprint":"3d3f4b9471aad9b4afaca3b5c875956f2b9a597cb4be02aa464a5c5709d1cb16","score":53.480000000000004,"score_display":"53.5","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d52a4bf6c494a0166f10bbfd","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":144,"at":"2026-06-09T18:12:35.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ed6aa8345d7580907ca034c9b56ab79516d1d540a2e658d504f0268daa5b7b4c","measurement_key":"82db9f8280f26a89b9ccc185a2294bd4f278f4ba1ff8d44a323236ca77883c0b","metric":"mean_score","protocol_fingerprint":"adaccfbd9ea3dcb2d9587a3303b17523448277ed37e5f06e49625bb955229994","run_fingerprint":"c929e99fd95a4b559b49015e1b9a0d46f43607bc7eb9885a5dd2c95b800ac7b9","score":87.01754385964912,"score_display":"87.0","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":144,"at":"2026-06-09T18:12:35.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cebae25c4f386b6a24f04d1469d9d45cd8df6c59c339330019e6c5cf3f47868f","measurement_key":"2b0e4ce4f8d2d3c88ff842b7372e2f0d4c22ff1f54147217e8f3762250882f67","metric":"mean_score","protocol_fingerprint":"d9161e1a1af891cceac563616939e3f46ecce6fba54d98fa4deab1da7477b514","run_fingerprint":"da03052d2f15863b97269a475d7a8edc145ca193c153f14db75c3ea9d25662e2","score":90.2,"score_display":"90.2","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"77f500e3bc81018c55f2960bad09d23fd915c898cd652d579f4d0a69a593585e","measurement_key":"f176e108d814e95b517f621ed9acaf2f29e769d6e30da6fbc789a54edf2b0189","metric":"elo","protocol_fingerprint":"2a57587dd2216d99248636487bb8135182d6c3ec78357b399ceb07e09ac23b03","run_fingerprint":"3ee5f8f0e3bb5cb81bd066d7d9cb5b2e2b91cf8acf999b0fa8570851ee579d64","score":1618.39,"score_display":"1618","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d9794a0dd88a7abac5c048bde866169291cec0f0b9ca662d192647cce8141655","measurement_key":"030b82044423e0a1cbd39535fc1548968d81fefd19f6f2a5fa5395e544064b7c","metric":"accuracy","protocol_fingerprint":"fe3fb05bbde02acd8022f37a2cccf1d48a4f185f7bb091dc994e6f4c743279b8","run_fingerprint":"82b592c1686593ceca9de9f8b3ececc0bd93f349c8cb32badda1624acff9a1fb","score":93.182,"score_display":"93.18","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gso":{"benchmark_release_id":"release_176f07ea4e9e0b8dfeede990","benchmark_version":"GSO current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":35,"at":"2026-09-27","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f7f58d9bc83a727e891f76aa0e73d98df759d25b1cc23519f79f80e9f59c9c85","measurement_key":"cdeba1b1471306c2648aa0074946e95c7644030b43eb7a66439593c709e79a1e","metric":"opt_at_1","protocol_fingerprint":"314f8356da5124ab422275fb0fbc03290e1c215845de19928ebe8cd590f07d2f","run_fingerprint":"dd7170d127d603f389104988b09d45a96a548fd5a6ae83477ef1457d90ee52a4","score":78.43,"score_display":"78.4","source":{"id":"epoch-gso","name":"Epoch AI mirror · GSO","url":"https://epoch.ai/benchmarks/gso"},"source_authority_tier":"B","split_or_window":"official-set-opt-at-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e25453435ebb1777deabb6e8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2585b6de202eb81c8943d932ee9c03e813bc668e8d4536bcb98e3b8fdd98f2ce","measurement_key":"1b988a4be0d21612d32803576e4365efc83575e4a55bca38da5b6a48dca98be6","metric":"accuracy","protocol_fingerprint":"2b66769f3d0af076fa2b929944b6ca4b078d46e1e57f4168d926863422698241","run_fingerprint":"e41d0e4fa6b05f1fdc571b507b34bcfc035a7e4397bf1413ced61acc76c36886","score":55.468026,"score_display":"55.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_a31432cd65f025d42eaa2c1e","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f7460f69f93a539f7627e27497035c15e9669da7f52b9bdd4c0e0be4e1c9a817","measurement_key":"a2c31082196d5eef20a72e8c98e5907201f5473c7435c8fb3dc32612ed4384b2","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"15c69e1219b1415e5afd39663ed36602806329b2ae246d5ee3c3e3dbff9a747e","score":82.97079761904763,"score_display":"82.97","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":145,"at":"2026-06-09","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"612136ad236abdc9a8f82670f04aa2d3ad352ab7374b05f76cd6cde5f9788762","measurement_key":"f4af55b5cba063d60bafb3a8fc2cadbbdbe1cbd6d10a5621bb20ea4c895751c7","metric":"pass_at_1","protocol_fingerprint":"187a360b796425992516b601a57c2f1bff0c12ce6153c655c3d651ac69408342","run_fingerprint":"5139dede1544028a465a38ed57ea2c5ea44f468377a1c0cfd484eb13e62f041b","score":89.778,"score_display":"89.8","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":144,"at":"2026-06-09T17:51:31Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"95c55db928e7b5d00249bc6dfd1031aba837100a27131e071a5fd87c1e8f326c","measurement_key":"b8f15fb6013256c4e72eb3614406535b431c47199aceeeec1d578e0fc52cbe4b","metric":"pass_rate","protocol_fingerprint":"26eb4850feb97cd710e1d9171bbc599e2c63ffc8ea5f2fe0178755a4acca02ab","run_fingerprint":"f3ac72480ee3f492cae8170401ce75e426f932635eb0717d6815db44235c9c23","score":83.3,"score_display":"83.3","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_185ead53e002c3c1ba45c533","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":82,"at":"2026-08-10T16:12:44.227Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"086adf5fe9ebb9142cf1be3cec72569eb5049a8fc66d93a97d4ef9d1f1b1c54d","measurement_key":"44dd03f721a2f5fbc58a7544d2d68d3349f6060ebc5f15a34499f8d7fd2c72ec","metric":"mean_score","protocol_fingerprint":"a41ce8d08c70f058547b71d087fd53b98aaffd997c3316745d4a2fe42e4ddc5b","run_fingerprint":"335246bd498a881e2e69787d33857e5eba3d1c8be0d99e2dee5600f6ee4a7c87","score":63.88888888888889,"score_display":"63.9","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_7f9f1833ebf92e99cdabe7b9","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":145,"at":"2026-06-09","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"606c865b70ffbe1879fd61b033da64b6fcaaa1be5a4685540f5f021b8b697db1","measurement_key":"64ec07358135d4cbf380bb3b4bfc82d3f745b37c360e95dbf224469da411aa4d","metric":"accuracy","protocol_fingerprint":"f0eafe717cb93e184f2fbb0c67e69380e42a15d2cbdc22a3c212310a4e25ab74","run_fingerprint":"f65eb658fb9a49746906d8d29d943b3def35cc36409007fdc7f3092a5201e4d0","score":91.502,"score_display":"91.5","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":145,"at":"2026-06-09","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"056b0bed7664c884b25eae46cb89245ee5745876849676e52008d206ba32808b","measurement_key":"af3047c7fcb14b704b65be6a239a764fd3dd9fc274dc14ee5d6806d51893921c","metric":"accuracy","protocol_fingerprint":"822305123f4223f467e76361ce1d27e661e12fd04ff00d7dd6a6739bb6637f38","run_fingerprint":"436a443418bb61bf68118de3b87cd9cc97a528275fd1c510f5abcd69d9059add","score":89.306,"score_display":"89.3","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":143,"at":"2026-06-10T20:03:17.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2b832387d2c5e77130cdcab23c5e2f41e5632d91d131a21e10d53d529dd6615c","measurement_key":"33e8b026025ec3c191122009fbabe8a7306abaff80776b14c032bb698d46b850","metric":"mean_score","protocol_fingerprint":"9c3130e76aa52a956a1a814788fd50c9494371f314219961e8c31b3012597ef6","run_fingerprint":"6024580f16903303ad6d7f99803eaa177d4b993251ec5ae830a56d80e376ad64","score":99.72222222222223,"score_display":"99.7","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3690fa58346cc3de8c0f6c35a7ccb4339a1677cb549328cdff0719c6ae4c26ea","measurement_key":"4b437ce04a380b07ffde06cc94bd52c8bb59f10db1420b636b0d291c2a8c9674","metric":"fully_resolved_rate","protocol_fingerprint":"a80a410b47671a3bca6770bb811c696be5737a6347cf52551bbf98e70f127b47","run_fingerprint":"3eadaa8e9dd6c786a225d5f1ee2c00e3ebaedb0755d5b98d6800447c50834d39","score":2.0,"score_display":"2.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:15Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f96f2c061e9f5dea51e38cd08db8bb7ef0d6395200875a030f9bdcb866ba06b2","measurement_key":"c2264b36da7d5d40f0f3d81625f31cb5405847917fb2135ec7660adccb37ce71","metric":"subproblem_accuracy","protocol_fingerprint":"e0b2fcc0787cb427754dd973e5b44c18fa280fdf3ab70a7c7fd0a385185b901b","run_fingerprint":"0bbadcffdcaaa03a3d9cb5a63ec3fb517c1a10e20cf704109bc603ab67006cf1","score":60.9953703703704,"score_display":"61.0","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5655ed7c02718c2dc1c44b9af2b65b5bd16900e30f32cd2505a6f31877179fd7","measurement_key":"ba1d91e9b5305e5aa9dc02339b70a9c71adb0df5e6c976dcebf5203adba254a5","metric":"accuracy_avg_at_5","protocol_fingerprint":"cace3a02d8f4471dfb6c4003910470ea84db930ebd09f70883858ebf1beabdd0","run_fingerprint":"5f37c58d88e999fda5598b61e7a96e9a1c356580855b6a707e6ac1c5be78767b","score":81.9,"score_display":"81.9","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":82,"at":"2026-08-10T23:44:03.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"64d30b0ed98e5e453287401ed7d069fe1e8f7ace12119be5d4c13ee8b55d3161","measurement_key":"066aa68f11519a2a1abb511aea35c24576170f9a8ef44eb1674613bd6cfc69ea","metric":"accuracy","protocol_fingerprint":"049ccdbfb7201fed22bb9df66ab7dc0362db3395fe5f74a70bc801bec87c0e59","run_fingerprint":"ce4df78e069ee0f8a84bf848bcfc48dcad31fbc3a6503a02baafd3b81722d79e","score":70.7,"score_display":"70.7","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d52a4bf6c494a0166f10bbfd","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":145,"at":"2026-06-09","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"641a0f27e970032cb3eae7fa7e6d5cadd37dd9c1ee7a9a73614f3d1105b5134c","measurement_key":"3dea049c6bef3f23774ff7bb00b49c6f38c8870a20b91339bc555e347cae30b0","metric":"resolved_rate","protocol_fingerprint":"f3f679c38c4297732208f6d5430f7d18296f89b8fccbca3ad7ee937a89ec37fe","run_fingerprint":"c2052f382cd9dfb85645d50ddacde3a03342ff051ec8136ddd047bbf36c509e1","score":95.0,"score_display":"95.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":145,"at":"2026-06-09","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"641a0f27e970032cb3eae7fa7e6d5cadd37dd9c1ee7a9a73614f3d1105b5134c","measurement_key":"3dea049c6bef3f23774ff7bb00b49c6f38c8870a20b91339bc555e347cae30b0","metric":"resolved_rate","protocol_fingerprint":"f3f679c38c4297732208f6d5430f7d18296f89b8fccbca3ad7ee937a89ec37fe","reporting_origin":"organizer","run_fingerprint":"c2052f382cd9dfb85645d50ddacde3a03342ff051ec8136ddd047bbf36c509e1","score":95.0,"score_display":"95.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"contamination-risk","conflict":null,"directly_comparable":true,"display_role":"contamination-warning","evidence_grade":"C","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fba1a8e8e98f75f3a3063fd0bdbd751a2b81a9e024ed34400ad1a5635f53d733","measurement_key":"fe879d1adc5be0632f8a8cc386b535e37050672695338823c25eaf9f7ffde792","metric":"resolved_rate","protocol_fingerprint":"cfac8de7b5efb6b9dcee1a89f3f6693f4a7a3571e3f28a7533a9fdc2276816c0","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-05-15/2026-07-01":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"contamination-risk","conflict":null,"directly_comparable":true,"display_role":"contamination-warning","evidence_grade":"C","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fba1a8e8e98f75f3a3063fd0bdbd751a2b81a9e024ed34400ad1a5635f53d733","measurement_key":"fe879d1adc5be0632f8a8cc386b535e37050672695338823c25eaf9f7ffde792","metric":"resolved_rate","protocol_fingerprint":"cfac8de7b5efb6b9dcee1a89f3f6693f4a7a3571e3f28a7533a9fdc2276816c0","run_fingerprint":"c819e155a7400554ba965b00d4cfefdcaa0893cc6b18d19b1bfa23360fd695ff","score":64.5045045045045,"score_display":"64.50","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_7f9f1833ebf92e99cdabe7b9","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"}}},"run_fingerprint":"c819e155a7400554ba965b00d4cfefdcaa0893cc6b18d19b1bfa23360fd695ff","score":64.5045045045045,"score_display":"64.50","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_7f9f1833ebf92e99cdabe7b9","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":101,"at":"2026-07-23","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"60b4a94b1b4ac2871f182981698f44b98c6dde5860c32db82aed5f929d8bed4e","measurement_key":"719b15944592a1d9cb9c7f5c927bde642d2f13b97251fe38dcf4daaad7207e4c","metric":"pass_1","protocol_fingerprint":"bc63906b45498a36c7f69245c165cd52ba114e01c9ead5912d9063301c0508b4","run_fingerprint":"f5547c68c93087bd8a320bedf59e0a9fa23a0946cedd05d0a0cb0e0193ea4596","score":39.69072164948454,"score_display":"39.7","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0941db866f6e93362126c4d4e0d9f735806a2bc7a0e5e2831cb2d745822060b4","measurement_key":"6cbd052198d9a77cb8b2d1ab5755a738dc0df14a36eda21f7d128f78d361fec6","metric":"pass_at_1","protocol_fingerprint":"e4adb326a2e894634f4ff7a2de41020240efa24c3a32d5fc523ba0d4d01f753a","run_fingerprint":"456c888cbf658073978a21446424a83f647cf48c8f079ba2163f141b9d29a973","score":38.14433,"score_display":"38.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_a31432cd65f025d42eaa2c1e","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":145,"at":"2026-06-09","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6cca0e3a967f665dc49a23bf8c2f7c14bc6312fadeeca74747b41494a2ac881c","measurement_key":"38a70fd00c66818196c140bab027715c78986390f152a19974bc90cdf7f845e0","metric":"accuracy","protocol_fingerprint":"de0e7b75cffdd9188f364c94fe0801b76d661dfb9410d3f8cc226b4838f2fd40","run_fingerprint":"b4fe0c6b38248412eca8b3c078ab32b7a79a9ac87def38c2cdb0ea0f8bd9860e","score":80.524,"score_display":"80.5","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-3":{"benchmark_release_id":"release_ceb36f25882d8cea2c9d084a","benchmark_version":"3.0 · b936386b-4afd-4ad7-aa7f-6b52bcab9853","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":80,"at":"2026-08-12T21:39:34.661007+00:00","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4a3bed6427323f5a1cf334d3ded74c3caaaa3c1d033cac8072648dbcd43c4927","measurement_key":"f0b78f751bd9975b5cede19660766da544b97858cdb0440f855e97618870f7c4","metric":"accuracy","protocol_fingerprint":"3d11a4e7e9474b518de9518ea5ac6bf9a0167a6e45624d8bb01ff8cf092ddc04","run_fingerprint":"5318b343d3979e9d6380768d401b794c0b627f039360f56c1f55963367e2e965","score":34.05,"score_display":"34.05","source":{"id":"terminal-bench-3","name":"Terminal-Bench 3.0","url":"https://ofhuhcpkvzjlejydnvyd.supabase.co/functions/v1/leaderboard-read"},"source_authority_tier":"A+","split_or_window":"official-74-task-leaderboard","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1e12d65fafc8b599913c7e7202292f8127a88e7a65cf0a670c890379ac880c7b","measurement_key":"de6016fd627ad8082b6905d0546a2f67b35e84e28c0bf2a78725efbf214e4c42","metric":"accuracy","protocol_fingerprint":"08001d342ba8886a610a6f719c17c934469d9da35ed21be61b993f67a76d1316","run_fingerprint":"9c3b0de1312235a5015ae8aaf86e6bc491c2af84651722345b548841561bc4de","score":41.414,"score_display":"41.4","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"41c3e092017d78d6eee712678054e0367de5f4d54131a86239c73b0268d6ffa1","measurement_key":"257fc67bc8e825c3ec552bda4414b530182231135341f6c5e91706e2fa9da1be","metric":"accuracy","protocol_fingerprint":"be9fad9622f1f12c7ab66b7b1d9d0aa23e2c20fddf0fcc4418b0a7a409679190","run_fingerprint":"0987b684e171e36c46c54380e8d966753541fa1a7ab768819c6cc118d044d22f","score":15.714,"score_display":"15.7","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4fe7edf7cfad33cf9f2f752e83650ac94c82d550e904bde32a91bad5e7939300","measurement_key":"7e8ef31f4597ff6ccb413e1d6e5936ef7fb739f8fc42ec6f28347ce549b900f7","metric":"mean_final_balance_usd","protocol_fingerprint":"e24bc75ebde244e669d9ef0cced07b951a49d50bd35095b9e3d95253c8198b00","run_fingerprint":"e759c9055f5b5f1be891748b171881eaf01ec0f480c551f95cb854bf1845ea25","score":4966.639999999998,"score_display":"4966.64","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":145,"at":"2026-06-09","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0d93757af2f6546896262f85eea3b361881535aeaa997492dfc7baaf35d6e865","measurement_key":"f6bb4d1d50b379a14ba76984afe0b18992d5f4bcde7e5c6437099d87288906d7","metric":"score","protocol_fingerprint":"5238afb805eb35940ad63a588a9b8f6154ee5957c0b214bf4d0e77e7c79a90f6","run_fingerprint":"cf2cb69917a609e7faee2c6c9fc26da410e05353138cc06e97b033f99dc236e8","score":90.352,"score_display":"90.4","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7279f34d75e675c9dcc09283d88cca598f87777f2d86b9522d8347bf62d74f27","measurement_key":"1f97551e12d96d7bc95ef152c4d38a6b55e4008f9069877b9ce940e24cfa3ea1","metric":"arena_score","protocol_fingerprint":"9f5506b2ee113a17f88afb721cca43bed0ff31c761a8eb2eba8b8791d5637e8a","run_fingerprint":"3f812c4f2d20c1caeee18f20c16d86b87656f986fb21e05a493afe48e9279770","score":1624.082589402146,"score_display":"1624","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_7f9f1833ebf92e99cdabe7b9","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8f82af622d0a55008b0de0265ef063550e105d22b906fa0f947ac98b1609f611","measurement_key":"7ea4401a90c968353b4aa246be0d53fd1ab203f64868b33f29f2ae0bad8ad4a2","metric":"accuracy","protocol_fingerprint":"b9e36ef7392f80cf55925733544effa6dfb854521664ff9ded2b243e4b70e2cb","run_fingerprint":"4ef9b6993286921c6a9702f8ee8e8323cbec3889360455b8c0bbbed825fe8b87","score":91.94,"score_display":"91.9","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c6c9b7c96eb814bc15191e40","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9f07d20b4dba0ad213cceaa382a8d6b31717c372ea56d765a4eccb81cbe8abf9","measurement_key":"03af8c45beb26b054227bb1fdb253aa80ea11fe7dfe1242151c008423c3ece40","metric":"token_efficiency_weighted_score","protocol_fingerprint":"14eb5a8f690d40554db17277cc54c53e11418051175176f6b3e0c798f451b527","run_fingerprint":"29e0616d95e0fc9630037351b294fdb14c9b81928fa7c6645d5de4d91f4feb16","score":15.586933333333333,"score_display":"15.6","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d52a4bf6c494a0166f10bbfd","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"anthropic/claude-fable-5","model_name":"Claude Fable 5","parameter_count_active":null,"parameter_count_total":null,"provider":"Anthropic","selection_rank":11,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3c4057fe05624862ab6a0312e53e399523a133cfbfb6828f93035412440c3e61","measurement_key":"99dfada390679e6b4b94b0bdfb9e452e6c9f6b1aa6d34f9bc407f4f1e79b14a3","metric":"performance_rating","protocol_fingerprint":"66845a98dccfd2890bdd6dca1ad15dcc6200b9ed34f3c49cc1f835106236352f","run_fingerprint":"52e36433e72d7cd101b5cddf1e6ac66cd0ed82dff4353ab3fe888d234b06d699","score":2176.88,"score_display":"2176.88","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1087a1b2d0d5ce1414aad1e5a0de8919844e6866cf4de25aa4451944b5221118","measurement_key":"ad564cccad975776d9aa383230851debd762ec17309b9d810ccf12b5cb56f029","metric":"pass_at_1","protocol_fingerprint":"a551a6bc117a9e22f47051d86001b74a59a0ad7ea702f3f3b4fb268d87983bed","run_fingerprint":"90b3ad1175ddeebfa02c5781b1a7d16eaf6ea70cd6edea0e1746165af040faab","score":51.4,"score_display":"51.4","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5b08caf0ed1fe8e60fdf47bc11746b8b8dd435949c01874e2dbb75797411206d","measurement_key":"6e1cb0aea9ec700c91a6afe282989bacb1a17249142f7e797b0ec9022a84f714","metric":"pass_at_2_accuracy","protocol_fingerprint":"ec9e359c509b8ca4781d0a7f598536b151c1e22afcc18af93c0e4413ebff89f2","run_fingerprint":"d64d66ed5d9ebc3ba9f1350ddd6e978e5bf3b57021b013ee98d6188756006ac8","score":96.5,"score_display":"96.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":59,"at":"2026-09-02T13:33:02Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ebcc2c9064c24ba1302febbff1b5702543b708c5babaa809986f7f93a38fc549","measurement_key":"5eaddf3a1ca17c823a11e41f5c552d6828f9008ffd492d8cebba2282c45a2f90","metric":"accuracy","protocol_fingerprint":"377ce036d8d437ea9dce0284130749a9714e2195ff5b9f063a11d87a867c96e4","run_fingerprint":"e279f93c86a0855ff81c42d7e263599ecb9a760dd6b24259304aec009d9af800","score":92.5,"score_display":"92","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d18135883c0bbafe1b5211b7eed3debe5a2e6fd693b8db434fa00edcfae7ba04","measurement_key":"d5654a8882ecc96bd11dd865328e96339cecf81115bf68caa1dd2b87fe3c4385","metric":"ips_score","protocol_fingerprint":"69a242e74339a17be1e03ea77a55e848e882042879a26593cda2d17331b38012","run_fingerprint":"8e2c84ea64a960fd2e6346ae30be77abf8a611c69f223c45ba211d3ec863acdf","score":0.04790625499047256,"score_display":"0.0479","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1b56e52cdc1b51fa09ca0421","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"abf3b554860cc56b380cda4b63e65bef9f83485ecf2f2a16abdc86f7f76f6564","measurement_key":"e11f505a9fe7cdf0cd24c7addae220a173e2f917fbbeaf23a6e374a2085d4fd9","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"6df5e16d512312537c83c224f1ddd989a28f3b646002c5946cce7696a1a93dc9","score":1484.910477373644,"score_display":"1485","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1b56e52cdc1b51fa09ca0421","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:50:12.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"770312960fcfffd5ae7cb335b2ac9481ceb5762646fa2ea755251342be82d41e","measurement_key":"1e8191ecd98abc28d6f41bbe663f342ddb5f1e3184806cb357c8f548b2825e95","metric":"mean_score","protocol_fingerprint":"ba490b4237455700d3ca94f7f00da4bcc0b9dba1ac87266e2dd21a86b7f1fbc4","run_fingerprint":"39da4e0f90b55cd168c38cb5cb59e0be32e7c2b9927a29f2d7f9ba76999dc463","score":59.0,"score_display":"59.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1db47950e0dcfe970e7d456bddc9b1553c715c020f547e2eb249b10df160caa4","measurement_key":"caf0a0088cdd973f7e03f5338b18c91b5b70df42219f131600a105ed9557c92f","metric":"accuracy","protocol_fingerprint":"e048592ccf101949136e65dc219058a7e2e1b81302bf05bf8f6d193d0ec9d1cb","run_fingerprint":"6ac99c4989f0e451f3e5e65636f5ce02522c45ae8ada1caee7022f6b78d51f3d","score":32.2857142857143,"score_display":"32.3","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"cursorbench":{"benchmark_release_id":"release_9acebd5b002e9c3f18a30606","benchmark_version":"CursorBench 4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4ba1e9f7ab6380d36d1bf0d4f6d34d497cf3e70d2990ea1f7c7076bd9837287f","measurement_key":"b2d36c77ca44356daf3922b1f02d613ac69f6e2b0900759173d400720f514d9f","metric":"score","protocol_fingerprint":"5084ccfa853e6ab353f6a9b29cba903f5d14ec61d985f8f20cf9045c0f774061","run_fingerprint":"712b7fc0d98ef601bef0a9b1ba4bf31a5d896214f3c0a1705d4621d0676fedab","score":41.7,"score_display":"41.7","source":{"id":"epoch-cursorbench","name":"Epoch AI mirror · CursorBench","url":"https://epoch.ai/benchmarks/cursorbench"},"source_authority_tier":"B","split_or_window":"official-current-suite","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2ddc513246078876bbb8f0dd3ecbc4fb0805cc1d5a78b1773874f253b5429e37","measurement_key":"166ae3e802ce8d2f285dbe387f07eea5c1898913f2a186f27d43c2c16de4c4a3","metric":"pass_at_1","protocol_fingerprint":"a712907929a4595a3adce2f6ebe5586fc1817c713049c58fbf69d2094cee7ffa","run_fingerprint":"367118f965c334b7db4546c11f83474c41c3f1666cff04c2e78b63a752e82c30","score":72.66666666666667,"score_display":"72.7","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8c17bdb44861d0a6955d1a374e2eb0ebe044d0bf83769e3577ebf78955736c92","measurement_key":"41620a218f546107c1b000c3e9e379ade0f8a1d063b10a90a39cce6911de2c6c","metric":"eci","protocol_fingerprint":"c8e5556998763c108258ee04b24a079cd62a63ab7da86e135aa4b94c37d4944f","run_fingerprint":"3f9a5357e63c49e6b3ebc59d9cb0fdba3211d501764d52ae4340c9d38c43bc98","score":162.55,"score_display":"162.55","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7ff85e71c65ccc9bee850b2e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a5856d977fc9add892e75efc436afd14c043a09f7ffccf288801cbf848af7fe0","measurement_key":"52c5bfc4763888af2f8ee2b8c0f7bf9c3c7b71278927041da395a941a2fcce52","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"0b4a3eaa2469018bd79fde26e6816f088ff1492ea6488ebd93af3954346ad7f7","run_fingerprint":"5ca9c0aec3b4c578c2e60900b63e75c99ac2741bbd4eebaa5634c0117c2dc808","score":47.49,"score_display":"47.5","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":115,"at":"2026-07-09T02:45:09.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8f3979d351455e10edf3b7b6f9f5a66a9cd4191d8e5d18f09141c1a8cb5941c5","measurement_key":"bb17a5a8f0e84e9315938a26ff294b6e56f57b2f38b7a9df9840c0bf1b88ca22","metric":"mean_score","protocol_fingerprint":"fa566697fc7062a3f4e2935fd2d9854f3b2afcd922216eebe37ea31e3d64830b","run_fingerprint":"4b16fece70b6ec62e4607f13e886804db90154a11f68c3c494784ae7f6ed8659","score":89.12280701754386,"score_display":"89.1","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":114,"at":"2026-07-09T20:34:41.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f6967b428c569b07e8713bd630a1b26032144b8960485883f03b8a584f60718e","measurement_key":"818c0b10353dcdeac0b98d155715cac8902edcb39920de368d1659fc511b396e","metric":"mean_score","protocol_fingerprint":"aef2c1d1a352ae61e4d0bf1c566c81c6a875a6e899fa72e7197aef2bf59b2c49","run_fingerprint":"8f7dd20c587144e337400d95702c586418723f546a0f63c22f85e12d2459ecbd","score":80.48780487804879,"score_display":"80.5","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"04c6d8f13ee59d9b42920a8106c6c88453746e7262c8abdc6dca444556d9c672","measurement_key":"fb398b80bd20b793387ffdb6471b8a40e2d45cb815b5caf37ef771f748001193","metric":"elo","protocol_fingerprint":"c92653d70a8c89a293b9ce89481917d7769209238282863c8c436dcba752d99d","run_fingerprint":"ad98070c82a1804bc70c8062cfbe6698baf149fea00ab62b7d961209ddd1efff","score":1617.83,"score_display":"1618","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0335b5d5c743507b11f4e7cf953b33cbfe5e35c4d6ba4b0fedcdcd07c3db1883","measurement_key":"d8af440d5cda0f8ffe32212b66867590c7f75541d33f13f49a885a8245b25d62","metric":"accuracy","protocol_fingerprint":"4bddc35537230abb9031166776429e9322e24a865a25aff9070109b412c02d6a","run_fingerprint":"fc6f12c41fcc9a2064098aa477461175e3f10fdba0639ee7c1e51bedba0db320","score":95.202,"score_display":"95.20","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gso":{"benchmark_release_id":"release_176f07ea4e9e0b8dfeede990","benchmark_version":"GSO current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":35,"at":"2026-09-27","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"caf4483a41f899171f50862a43a0482191af464657b6d90c4903e63a9af55824","measurement_key":"48786a4a41a834e970650497831d81400b06a9bda333d298b9de0fe5879a8817","metric":"opt_at_1","protocol_fingerprint":"d56a9e3960eeac9835fe6bf5d46fec8eee07c6f46714ca5e4375d7cee7786f97","run_fingerprint":"7d11cc30ef56755f51347809f41eac3bcc600123e2b05f124cc1be4ea87c2671","score":76.47,"score_display":"76.5","source":{"id":"epoch-gso","name":"Epoch AI mirror · GSO","url":"https://epoch.ai/benchmarks/gso"},"source_authority_tier":"B","split_or_window":"official-set-opt-at-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_965070fd41fb1df7f04b6bfa","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-17T14:33:50Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7936b1605cc77d0fd0041887375e50160c751a5d71af94929e373b9d4b2b43ec","measurement_key":"fead8c08f0fe143733984c4adb54cb53c1ce550fa0ffc8e6d5bfbf906dcd09ce","metric":"accuracy","protocol_fingerprint":"db96fb25810622597f236f437c027d00a5acfa3d1c917e4ea2af57ad594b4bc6","run_fingerprint":"e5ccf8a301b169e92a710894f9860495b02cfafe02e6cfc3e8dab7a1879b3afd","score":49.490269,"score_display":"49.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":47,"at":"2026-09-14T23:34:42Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"404fb8ceb82c5c05b8dd6c36049d2b8076209296e997ad336021fdfa18f26748","measurement_key":"6572a4614965f055d90ce44ed071bce140bfa0d83efea7a1d90927320e82f672","metric":"score","protocol_fingerprint":"1c161be4cc2f14788a6c93ae6b0d835823fb90da0dd87a01492df42dfccfd9ef","run_fingerprint":"e1084ada55d3042efaa5685252129bd5af3c7933fe6406632ecfdb2f34a962ff","score":91.167,"score_display":"91.2","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"70c9bba381113e56bc436fe1ed16c60e3f71f727f43e27e9e4cbc823441554b4","measurement_key":"c14f0ba2239445fb7bffaa56076776a04e970b30b52d9b614372ec11b4033c73","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"e090fa41cdb113a42a2b6e22193d9715364d9b8c52ea99160d82a0bf7a57764a","score":81.05354761904762,"score_display":"81.05","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d5e1156986042d89257c34a7538e4d4a0769378ac2096bb09a5b5737f6cd7e8a","measurement_key":"3547562e38e2629e2a3e01ba18d0c41b7f09eb5b2cd8a50244383fa1eab036e3","metric":"pass_at_1","protocol_fingerprint":"4f12fabe8d2250a5013fa45059236c777dbd88eb8f16da1a50e9d9b4da791afe","run_fingerprint":"26f8a50d9bbd7812d523958651682ffc8444a211769bcf6a8d338fdfe6e5e490","score":82.604,"score_display":"82.6","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":108,"at":"2026-07-15T19:04:43Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8791be4ad80f99f61be5abff59690cbb61b8a90a1a5bcff162bc91272b476963","measurement_key":"f10a9b5f29b9e631cc4257b6540bec16a8de479a477e3c6452e9bd02a97de7e7","metric":"pass_rate","protocol_fingerprint":"0fc3b8d6f4d8c50c3737811e9a270a7940ae5e176e14669a29ccf5a92ae9ba9d","run_fingerprint":"63fc2bcb19ebe277dd09c4ba31154de24ab14c11d912d25ab4c6aeb490ee2edd","score":81.8,"score_display":"81.8","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7bcb5fa02e3e66eaa72b4761","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":82,"at":"2026-08-10T16:12:44.772Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c76dac7acead3b3eb6fc7994ac6b9e74238f75c222a3310e1bb52bfc8e2699c9","measurement_key":"6df4e45af1be89cc13a78b427ccb3d9856f824d8ca1d9f13bed4ae3763ff1fd2","metric":"mean_score","protocol_fingerprint":"a58de79cf4f660b386289bc562f0a44ea06f3aa39e01544289220a4104beaad7","run_fingerprint":"d2d74ffcd4d9f1e7db15d333c77929282bdf7660dc2458d140c8b1a98ac679c9","score":20.0,"score_display":"20.0","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_79938598fdbb1914df59fc3c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b5d67e4b208802174570d52b4ba2f54f0203a93b685fbd8e78e6e8f7bbce1341","measurement_key":"d1c7088d7c97a9ca66552d6b986dd2fefce476a59ae9af44b587c6f63f299edf","metric":"accuracy","protocol_fingerprint":"13bf06df9f9d63ea18257440215dffe6d85a3acda2b0a37fd602cf7961aea7ca","run_fingerprint":"7e8e470af07d50d63b5d33325e590a700feac08681e32f560cdf3e8f970fc36b","score":89.1,"score_display":"89.1","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:41Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"93640fb7b5b2937f1f3a2eb7cd96e4d1d008338ae1599242bad7dd5d157eb95d","measurement_key":"78f4d9ec42030785d176d41d9fdbea10aa93ab2fe28767188cf46561ce44b88d","metric":"accuracy","protocol_fingerprint":"722e2d51968049d4abf1ab172e834323570a2474c4369f894575539aa1bc75bd","run_fingerprint":"6a9cb22b487d24032aac8bd62d5a91e4bf169ed94673483a8c0615f81149b6a5","score":88.844,"score_display":"88.8","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"osworld-2":{"benchmark_release_id":"release_15c5525fe39f33bc181dfb69","benchmark_version":"OSWorld 2.0 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T21:27:40Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7a0c33214378f1b3406a22e6c39e4b605f13860f49ffbb9b7a795656b6ff2d5b","measurement_key":"9fc4c06ebc97a56401d89e9b453c26d97b76b3f6f823d5f1afb652bd88fe0020","metric":"binary_accuracy","protocol_fingerprint":"596dfeddf4f879c97fcbf0ae4f906947b4af3f10abbe2ec8c0e260ef3c506b87","run_fingerprint":"ad6b1577820cfaf53e0024915ac51ac8491f0050cb95895ea77f7c3dc2d7b619","score":27.340000000000003,"score_display":"27.3","source":{"id":"epoch-osworld-2","name":"Epoch AI mirror · OSWorld 2.0","url":"https://epoch.ai/benchmarks/osworld-2"},"source_authority_tier":"B","split_or_window":"binary-accuracy-500-step-budget","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":115,"at":"2026-07-09T02:07:13.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"293a503b0cff38362d4d82edd74207dc3f41e9521a466439652f4780e2fffd73","measurement_key":"a1f8447f6e4e98ccd9f15ad86d4eea49925da83072ba6ab462fd43d5c58b9c24","metric":"mean_score","protocol_fingerprint":"af444f0831bcc1693c151ed626c6f9124e9ea5e83544fd5e9442f46ec348b72b","run_fingerprint":"7c880960c0d8c6d1ea6e29f15d9d328bffe44fb922ef8e98a60c08b8e3c3cb6f","score":100.0,"score_display":"100.0","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1b87a1fe804b866fa99b4f67b1d92194e60d4ecc2fff9459324c8f61bb5b238e","measurement_key":"d8e6322f9ae4d514afdb34d8e58bfa8942abf9e5ad913cdc240bbcc6ba0a6d3d","metric":"fully_resolved_rate","protocol_fingerprint":"47773af8a9bc25d41b7fe90a2b6e479d79ccb61a16b918edf3d3361677e4d0b8","run_fingerprint":"ce9fc75b27b079e84cbc21729c572b0cd2002275a3a7487d29a3cd6b07bf2721","score":1.5,"score_display":"1.5","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"caf193f9fba3f365fb2efb8f7087af8029aa8a5dc795b1bfc95e455979017edf","measurement_key":"7d04179a1bada1463ad0de4b50ae1529afff114d2ef842f5c3a7a671c823567b","metric":"subproblem_accuracy","protocol_fingerprint":"e778c20895945a18ad949ce2bca1dab91cdf5e768fb516689d40cf333fd5f1ea","run_fingerprint":"0d887240b1b9fe322ecbb2a0bbfab684e786e235837f8f74342f10ec33bbb344","score":57.0601851851852,"score_display":"57.1","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"eed4db70935bec0447d7ae8a6ccbbb99addcc921831a212e32759fcb370557e1","measurement_key":"f1d3bf639005bb6ae003438b198803659ed5d3c51cd6edc56b42d6240e1b72c1","metric":"accuracy_avg_at_5","protocol_fingerprint":"f757eca0faeb48281cd4178307e2d0dce127d281f981d358abfdb43cddd15570","run_fingerprint":"b178f827c4578a7a97376deaa830ebdd8b12f9a2d6caee817294a7325c610364","score":64.8,"score_display":"64.8","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1b56e52cdc1b51fa09ca0421","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":82,"at":"2026-08-10T23:44:30.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5160c9f92fc610292f547001a575a81613399d21c58ea89aea8ab0a5e8a3e358","measurement_key":"2517f54f8529a3e5eb6dafdc1f2d850e35c81e8d622333bae409d73e6dadf6ed","metric":"accuracy","protocol_fingerprint":"e8c442b4dfa0deb1c59f43f7f6c56b371e45a3134beb26cfbd35e2d47f70d096","run_fingerprint":"8929324d75dec5002f8ae9600f99349c0f7160ad3430a65c3930c6ab69d6b151","score":69.69999999999999,"score_display":"69.7","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ce75cb0ac0fcc9516e35cb78ce1f53b3abfa826e53d20c56bcb4d74f0389623d","measurement_key":"84a83695525f655ab397f88fed2a0dceeb4f1dadd7d95528436421aeb3ae8f40","metric":"fully_solved_rate","protocol_fingerprint":"c324258a209eb38ee8b49c1c716e13c95469b96f5c905aba4e30d5705eb032f5","run_fingerprint":"3c4b061cfe29bc7373492fe3a20e464456868625b1d9f962c7d694a455eaef36","score":30.534,"score_display":"30.5","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-live":{"benchmark_release_id":"release_9d2de9d5be7e9822af19f7b3","benchmark_version":"SWE-bench-Live Lite","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":36,"at":"2026-09-26","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"521d8ed5899146a6b0b6a20cef7ab059f056dce76e5f0b81c9a2ded4dbfffc67","measurement_key":"2fe1b1e3fd0a45158d231ad589069bdc49d9fc2f117ad96788b43df0f2fcaae4","metric":"resolved_rate","protocol_fingerprint":"bd7ad59d365892c2706fedf0a6bdbe7910b502a8d50f3bffcbda83cdd20c5567","run_fingerprint":"f1cfea9c0194b41b9ee6a5c929b19f552f97720866aa1e526c41a51f5e20d03f","score":70.33333333333333,"score_display":"70.3","source":{"id":"swe-bench-live","name":"SWE-bench-Live · Lite","url":"https://swe-bench-live.github.io/reports-0605.jsonl"},"source_authority_tier":"A","split_or_window":"lite-300-python","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4aea036993309752d798d393","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"swe-bench-pro-v2":{"benchmark_release_id":"release_d9b58bd286ce316ccf0ed891","benchmark_version":"Scale SWE-Bench Pro V2 public leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":25,"at":"2026-10-07T01:44:58Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e4ff89db8c677fd3c4a9b61a0abf4395888fa922369aa73567d18be3a998034f","measurement_key":"df4497fd9e1bd6e87b021ad81a3d6a3ef940c9dab9e52396dd5475fa46a33f47","metric":"resolved_rate","protocol_fingerprint":"7ecf9fba227752f399736f421de012e74e0baa6680438efcb7921dcafb6b4055","run_fingerprint":"07f8723af6eb2125d3e50aaeecc8d4e6cfdf22d80651e4f8dcb224870f49ce58","score":95.5,"score_display":"95.5","source":{"id":"scale-swe-bench-pro-v2","name":"Scale AI Labs · SWE-bench Pro V2","url":"https://labs.scale.com/leaderboard/swe_bench_pro_public_v2"},"source_authority_tier":"A+","split_or_window":"public-v2-642","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1b56e52cdc1b51fa09ca0421","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":115,"at":"2026-07-09","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a8e05ed03fa73ea1b54b5f42ddc930dce9d5f8530c712fc027c0e57b30b4d1ad","measurement_key":"ec533d1aa33cb42f661c011b7d0f08631f843b426db03d20c8fd45de1807eab2","metric":"resolved_rate","protocol_fingerprint":"ad9b439d1c65794d955cdc4ff3e4a7bb1e79fbef405d3fb9234f06290360a001","run_fingerprint":"d93df57625e3f37bdc16654afbc48acd994b870415fbc11fd09e7c8decc42222","score":96.2,"score_display":"96.2","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":115,"at":"2026-07-09","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a8e05ed03fa73ea1b54b5f42ddc930dce9d5f8530c712fc027c0e57b30b4d1ad","measurement_key":"ec533d1aa33cb42f661c011b7d0f08631f843b426db03d20c8fd45de1807eab2","metric":"resolved_rate","protocol_fingerprint":"ad9b439d1c65794d955cdc4ff3e4a7bb1e79fbef405d3fb9234f06290360a001","reporting_origin":"organizer","run_fingerprint":"d93df57625e3f37bdc16654afbc48acd994b870415fbc11fd09e7c8decc42222","score":96.2,"score_display":"96.2","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"contamination-risk","conflict":null,"directly_comparable":true,"display_role":"contamination-warning","evidence_grade":"C","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"50975ff78dcb4886883ae6a8fbd9a79df23e9f9a9483f8c461f8837e939da1ad","measurement_key":"1f665b9eefd2e2dad8cc7474fc304935ee063b7c0c4efc24a7c7c98a0f960ed0","metric":"resolved_rate","protocol_fingerprint":"d16ae687df2d5dd76d6c38924008b1ef9c7b3d1d6fc457424d2d15395e17086a","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-05-15/2026-07-01":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"contamination-risk","conflict":null,"directly_comparable":true,"display_role":"contamination-warning","evidence_grade":"C","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"50975ff78dcb4886883ae6a8fbd9a79df23e9f9a9483f8c461f8837e939da1ad","measurement_key":"1f665b9eefd2e2dad8cc7474fc304935ee063b7c0c4efc24a7c7c98a0f960ed0","metric":"resolved_rate","protocol_fingerprint":"d16ae687df2d5dd76d6c38924008b1ef9c7b3d1d6fc457424d2d15395e17086a","run_fingerprint":"041f5582280837b3009bb70c48ba8be0b3667954e59efb13e41b8aa67b072567","score":62.34234234234235,"score_display":"62.34","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"medium","profile_id":"profile_05094233109adfe43508046c","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"}}},"run_fingerprint":"041f5582280837b3009bb70c48ba8be0b3667954e59efb13e41b8aa67b072567","score":62.34234234234235,"score_display":"62.34","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"medium","profile_id":"profile_05094233109adfe43508046c","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":102,"at":"2026-07-22","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9e2f3c32a9cd48e71962f9cec95a2e54d413996e7b8105d78bc013c911ff9256","measurement_key":"c6f379a570efab4284a91a50f2ea58dec7a759c2259903d9d91d63228e8ca0a9","metric":"pass_1","protocol_fingerprint":"330a2d901d6208787dd59902438b274fd530133a84c8829a19757d7db2052656","run_fingerprint":"685807b51284fb64664d42ea68f5c63a653866e6b50c930da8fe9c8c993b9145","score":46.90721649484536,"score_display":"46.9","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1b56e52cdc1b51fa09ca0421","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-09-17T14:33:50Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"621f3f12d48993560bed074580548dd877a20ffd0cba2b804fc1e8447464775d","measurement_key":"ce0861f2ed4d91a0cfa7178c9c74adc77e8501d0a1071c321585648cb240c53c","metric":"pass_at_1","protocol_fingerprint":"23ade084fc38f7474bf05c58f2c4fef336a2917680c322d09980491a27aefbde","run_fingerprint":"583b249a195123635fe98bdd0babd8b221210898e360287e27a0aa21bc0ebd02","score":44.329897,"score_display":"44.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":115,"at":"2026-07-09","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f21aca5cb9fd73a2fa740337011f4e9a03afabde1205ec813c8df80db152058a","measurement_key":"e26ed319aff1b9946b9993b3a698363b6f4323627658f1c3a765d2186249e9fd","metric":"accuracy","protocol_fingerprint":"5a4ba5f568b886433683bc8464125fba5692972e726d46b54e21ec8426cbf204","run_fingerprint":"f3c73ec9ff722a9d7b0c13637d63f9296494f87250eab086b5f86bcf2de10f10","score":85.768,"score_display":"85.8","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-3":{"benchmark_release_id":"release_ceb36f25882d8cea2c9d084a","benchmark_version":"3.0 · b936386b-4afd-4ad7-aa7f-6b52bcab9853","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":80,"at":"2026-08-12T21:39:34.661007+00:00","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bffc17539f3443c97cf8012594e6c22586fbc437fd27467abbb4ee17995b403a","measurement_key":"b991c4d290f84d445f938e069eaa491521be750abd9b66f09f1de10c6224df91","metric":"accuracy","protocol_fingerprint":"b9bf808dec50df0e64e3025aba0c983c695bea80fdf2f962997e816e5bc5d50a","run_fingerprint":"d969f0974e04e7354172c44eb11514df49b6c9e5d131fa248e147ad8d3e0a59e","score":34.59,"score_display":"34.59","source":{"id":"terminal-bench-3","name":"Terminal-Bench 3.0","url":"https://ofhuhcpkvzjlejydnvyd.supabase.co/functions/v1/leaderboard-read"},"source_authority_tier":"A+","split_or_window":"official-74-task-leaderboard","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"39a6de31eb642b8200d60da9e5637aea2d65724d8bccdf706fe0d98c14ab02cd","measurement_key":"d35022eb7341bad7d2af2d655cdf058c6e30dbc24adbbbf0857c2de03f1067d0","metric":"accuracy","protocol_fingerprint":"9257b66f4993e42cea8cfe756a50cf1c6a910cd98250ba6a5b9b21b971ad30c6","run_fingerprint":"a8a33df9fa62680d0bcc7fdbc1897ae055292c8994153405ef961126cbceae56","score":37.879,"score_display":"37.9","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fc3eccc5ba912c67ad25688d5b8afb4b2b698ccbc71080f0b9c34c241179dfff","measurement_key":"615683fac972f343b5caa573684fe51e2ea0ef8f475cdf5f1e349efa16b4ab72","metric":"accuracy","protocol_fingerprint":"7aacd7ab587b68ac9c2610692316aae6ee7fa6dcfbe88915b7d978ab95e07298","run_fingerprint":"da52242bbb7f5d1452f280085a6be060d99ec52fe6ba9b4cf1670a375b6c38d7","score":20.0,"score_display":"20.0","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"eccfb55849daa3e676c6565438f04ccbe08b771717962007bb8489fba5101779","measurement_key":"48f4e0e0a650754577e7df9495f040df501545037a1cf9d08ec664b173c7822f","metric":"mean_final_balance_usd","protocol_fingerprint":"8a79dbbf928d612db6c65ea087a14a0a1840500e78ef2f83840fa5bd8ad54c38","run_fingerprint":"b41a28c041128ac5724f151ae9ec4b48ff0d68067a4c570241323bbb2f2b5e53","score":9619.367999999999,"score_display":"9619.37","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a6e3048e0b5def1df0f81987","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"02b9ced8a7f71096c73e56a671f9f037c089aff56570f19d15c073d3299a4882","measurement_key":"d02c9b407a93b14db5296e006a4eaaf0449dc350d2e410effbf132d298c17364","metric":"score","protocol_fingerprint":"bd1a4d2e22eda48391322e1793c5cc84df8bf558eb0788197fa2a1bc88d20982","run_fingerprint":"30db70b8a7fb3e401c7fd6744cc036ac4bf1d2111e73bc736c35b5bd6fef1b10","score":80.495,"score_display":"80.5","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8714bf16870123fca59129638678a68e0683dd8670b03d4cab60c485a2377e99","measurement_key":"401b7ce3f78e00583419a8c0404d6d2a94f1469acb60390bb0faf62e24e0dff6","metric":"arena_score","protocol_fingerprint":"20b320810c74e63e9300a28d0409ea168553d88796b2a11703644b28f1d60729","run_fingerprint":"2c042c193e76e57a716f296234e0195cc90488c8c8bb8f8c8a5433aaff8d8d47","score":1615.7849726003753,"score_display":"1616","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1b56e52cdc1b51fa09ca0421","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d9ab75610082361944b66eca3888724821fb1309d9df299b199d57ef8d5fcfb7","measurement_key":"2ffd2ce3991f86f66771793ed82d1ff22988cc8d991cf2bfaea48e6404fccaec","metric":"accuracy","protocol_fingerprint":"d10ad421cd3940208257e8f5ba0b686f73dda194844159ca82159e453a2ce7cd","run_fingerprint":"2b091f35e66c7ccf56a88d5e97b9733dc402ae04f7124c09e685eae4048e7c4c","score":89.43,"score_display":"89.4","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_ae20fb1272fc841ce5c8675a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"67ca79ded5feb37cf64da2da2adcd4fc9248116aeaa9a2d6e28ead6495226af1","measurement_key":"f075261a58e27a5e246945d415f5da2b2630b6f0ec8d35bd780948794a4a6836","metric":"token_efficiency_weighted_score","protocol_fingerprint":"0bba1ac555db26ce37fab8ff63bae81dfdaf320ef5b0963edce65a06009ae77c","run_fingerprint":"d306c8dcca6d7d36388204d2c92bff990a85bf37d634430545a26701ac8b0109","score":14.992224545454548,"score_display":"15.0","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1b56e52cdc1b51fa09ca0421","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"openai/gpt-5-6-sol","model_name":"GPT 5.6 Sol","parameter_count_active":null,"parameter_count_total":null,"provider":"OpenAI","selection_rank":12,"weights_status":"closed"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3fe9c58be9b99feb47311e9a0b4422d2480e758005264ae63c602dda89b6aae7","measurement_key":"a5801975075e8c2b61208b26f8d6526a39ccc177449123954a4e3fe07ce4cb45","metric":"index_score","protocol_fingerprint":"cde2a5b12bc4fe6ac3a7da79dff414421b06faa09cc40077b25a573723426899","run_fingerprint":"76f6f8032d1acc2c5ce5fa6c60513c1917f0b74b720a60a806bf481e0545965f","score":43.324823,"score_display":"43.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4359bef657d5e96da8d9989d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2489257bb7a1ac7778c6f4d46042be7243d110b5562d714c38e80ad3b1ceb941","measurement_key":"55bcdd2d0141d69f08f3211acc09cb4c9cded609af342615eced43a777abee26","metric":"ips_score","protocol_fingerprint":"d34b95863d5672df48f1538ac11194e4d2f59811c4a94883d50e490b03c0bfec","run_fingerprint":"c78ccee7ff998dcf8c315354fffe4940105a07b899de0c0c57ef04d4e577a06c","score":0.031375825809846235,"score_display":"0.0314","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4359bef657d5e96da8d9989d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"84b77e348079884b0d9d2bb41cd5e87969f45bf6d65b2997ec5d7bc249214aff","measurement_key":"7ca7de1f1b5fafe774bd01018c82042176ecd26afa743bff9b30446c479f20eb","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"ea9b2e3a813aa02e747985212fd22995404d2638df039630a6bee67fe4cdae4b","score":1507.0976650433042,"score_display":"1507","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4359bef657d5e96da8d9989d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":19,"at":"2026-10-12T21:04:58Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1ac376d12b10387ceecef5a39533c98a56afdd3902a752d51168994a346375bb","measurement_key":"25e17befdf6f9e67a9f0e34916c6cbbc2abc13d1b433318099d0a2a6470fe2bb","metric":"accuracy","protocol_fingerprint":"e4c1076c584d0fe77418939ca3b4cab0f77c89b08ea6ef8a8f78abaeb3ecb7f6","run_fingerprint":"e98c591e381f33f6964bd43fc5c7cb6e07a569ef6bed49fc551ec97e156c2533","score":28.285714,"score_display":"28.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4359bef657d5e96da8d9989d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"503063b220c83bd8cde7834cc64d70146a39c8cad8168e8ee714b9dcb131802b","measurement_key":"923c8ed12fc1afc78eb6521a33dc5c08b9cd2e94c0438f1cc1d7eb0c9e45b643","metric":"eci","protocol_fingerprint":"2ae33513ef33f957dcb2b2d5103bc88fe29616a8580b08769560afe3f31aeae7","run_fingerprint":"eef9c1d18582afb5b489ed0940c437ace59feac3a9a6bfde1dd413a2d9523ccb","score":161.71,"score_display":"161.71","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2e85b29d500b3921d8c3d7b7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":19,"at":"2026-10-12T21:04:58Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3ee6bf2a99f162e79321521886404b84dacce2482c8ed0f5f55f79a98341f956","measurement_key":"d29beb7c104466fe6e24b1f8be769f7753d2b823c30e1a277a5aec15f8c6571d","metric":"elo","protocol_fingerprint":"19b141c1dc5009047d5237719a9dc09925c296b8d6a57757b93b7e35cd947e04","run_fingerprint":"c646bcf5fb4f00b9ef330e2658b3dfc7c2790ebdead592c1f92ba3b8b0239157","score":1770.34,"score_display":"1770","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4359bef657d5e96da8d9989d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":19,"at":"2026-10-12T21:04:58Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"20db8b7999029649a0a493f0d2b530e70eb3f05b8d0773a887b063218bb495ec","measurement_key":"6ba203771766e919703ce268566805a351b22a5c1bec6ad954dfbf6805974c99","metric":"accuracy","protocol_fingerprint":"9e8a3f4b2193e976309164e99245a733e7b2b43e3e2ba016d3c395062533885c","run_fingerprint":"123c9d5cb8ed343fea5dc4c49d76ed1a636c77ad82d006abfe7174837435c98c","score":50.092678,"score_display":"50.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4359bef657d5e96da8d9989d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":19,"at":"2026-10-12T20:29:34Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"403ea6e3ca3c1950c15ff58a926bc2c50251b7155fcca881ef1a8880727c5104","measurement_key":"b76e06a545225320bd3db4f145025a3938ecc0fd9e44573a0bcba961e89f6471","metric":"score","protocol_fingerprint":"f0be9a5926fe091eabafa70ac121a62734b7f98bcbf7fb74d2c24a155cd4f4c0","run_fingerprint":"59b6986afdfa58e6dc253361ef58d3507d713772e693ced0b9737fa41a7ea05c","score":66.944,"score_display":"66.9","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4359bef657d5e96da8d9989d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_de40c66bd40a7b5483b40f9a","benchmark_version":"SciCode v1.0.1 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":19,"at":"2026-10-12T21:04:58Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"93fc9939503b4a38d876355ec033ffb5eb52b44274a88003d00c16c93b5e4670","measurement_key":"73f2d0c57badb360a8869b217d0f57653437c664b5b5a606333e6478cc9d23eb","metric":"subproblem_accuracy","protocol_fingerprint":"2190a53d9fff6afcb1e3a6bd83b83ece697aac8a802ea9bf5ce396832118a69e","run_fingerprint":"4637d86e5e263158e8e020c9466428c9caee928f7d180bb2cd53ca7139d48e20","score":60.300926,"score_display":"60.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4359bef657d5e96da8d9989d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"49e7d98918457ebd1b6b2f3b36b0b2460b4e2a58e604165887857b5729f9c73d","measurement_key":"e327fe263deeddba4c97cc8f646152acd6ac559418851be0cb8203347388119f","metric":"accuracy","protocol_fingerprint":"0bc2bb5fde24128d8a33dfdbbf88832b7268022304f19f398c78d898747c2a2e","run_fingerprint":"2316af2dd9311e2e36a7d1a118e118732853bc97e67cddbc5a2923d0d03a7efe","score":49.495,"score_display":"49.5","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4359bef657d5e96da8d9989d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"02bc09b7945ef8e709cb7297e1bf47767731cdb1e2d6fd70d7a50d1f38358d86","measurement_key":"68e98b0bc8c70716ba68272a30dc95b454639de2823ec8fd6ec9eedf0d84d219","metric":"accuracy","protocol_fingerprint":"4007d1fa997e3bb695662565e32a1fe821ed4cfbcc00f626d79a347618190c34","run_fingerprint":"ffdadb36c5b86e6861a164460308b1454d858a6ce624d232f07de91ec7c20494","score":22.857,"score_display":"22.9","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4359bef657d5e96da8d9989d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":19,"at":"2026-10-12T20:29:34Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cf4cc0c8bad2baa3633085900b4cb637a84e776f97b4ed35d284ecc8bbabecf6","measurement_key":"ac2f82b0da1a7673c27bfbd1cec33de3bd4227760eff31bb4975eed0ce8d5fd8","metric":"score","protocol_fingerprint":"9fa0c9883e0916f8db7267500b9cd2c728f736c48b515ad8a316d25516ab56ea","run_fingerprint":"07dc938afffdbbac12d6b53d0d127f4bde991e029e8450082f7b107fa995d980","score":83.089,"score_display":"83.1","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4359bef657d5e96da8d9989d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4ee1c140f9ed76faae947fb8331faa1963da41aab45ca7ad601fd698303b2011","measurement_key":"0e526a97dc7f95083efa6eb94ddcca1d8bba301de76db144f7bf0d8bd9fa4616","metric":"arena_score","protocol_fingerprint":"978b3ca922cccb2ddd3c0ba3b0bba19dca3e2e258f30fef3bcce5d6aeae68ce3","run_fingerprint":"b5ca0d3f0159af1f75ad40f8ae2c99af03a43b276ad655de3abe6118213c045e","score":1652.0939667524244,"score_display":"1652","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_4359bef657d5e96da8d9989d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"meta/muse-wonder","model_name":"Muse wonder","parameter_count_active":null,"parameter_count_total":null,"provider":"Meta","selection_rank":13,"weights_status":"closed"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4a0aa07560ffcaa24517417d7380ef84f5b9af516cd08653c633b2078b4519d6","measurement_key":"7c9bdfb37c1fe56f30161a7e86e932861c43e04cc788c967ac1a83a6373398fa","metric":"index_score","protocol_fingerprint":"b725bcb4ff2f202eaaa00fa1772c63c4b3d4535616d9e0a2e420d3861c523583","run_fingerprint":"9497602a2c9281f7550f69a15c4d5b882f2ffa183649875584d7cd65b57546af","score":36.234544,"score_display":"36.2","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:04Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8d5c3d818a6deb9dbb4a4ed0f60194c803f5673990a99a47aba4a5fb10fffdda","measurement_key":"eee3b0168ababc739ab3acdbb3ef97303c88d60bfcd14dbecef600841fca8dd0","metric":"performance_rating","protocol_fingerprint":"e625ed2602378778bb8fc022e40168ce9c5bd5f85c71e4c1b1d2ba8cd1f8da33","run_fingerprint":"2b99c96dad9076be3ae8d32909c96d82b8d6a52ca7ac4f42c8c5779b8ba63448","score":1587.0,"score_display":"1587.00","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_402928bff9da8bc5523c7b2e","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4393651d280cb666b261c3153a14161fd4f1cb4fd1c736e7cacce3ed380f8430","measurement_key":"dd2de5939a870b77d1f0feb4b0d63a27c8ce6419c83019c3893da91f75af06ed","metric":"pass_at_1","protocol_fingerprint":"a0e29de3218632f99454f1b32b0610157f76f290ecd1d47b0e860a480d4d82c5","run_fingerprint":"ee6c8342472ac216b052a0f59ba4b8664c2b55448f8154538db9f4b2b2b395f6","score":56.10000000000001,"score_display":"56.1","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":12,"at":"2026-10-19T22:24:17Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9c02e193d52584a567e53e0cd184f56bfc48c5796c526794f5858fe94ae4e79c","measurement_key":"bfe479fc675d0d16de941eacceb0db208b1cbe06dccf9760d88b96be507e430b","metric":"pass_at_2_accuracy","protocol_fingerprint":"36ed7e927d9a9b2b486db826807d1ee4eaac02a7d4d493866f2173d19e6e9f3e","run_fingerprint":"da1e0a57da033c0f9c4b03c6708c62783bc693005472d0044f0753771f6365eb","score":89.0,"score_display":"89.0","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":17,"at":"2026-10-14T16:32:28Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9a168b37fc44e5869b3d33370b9b6a70e38e19bc02ffd7ab14207c02f01b83c7","measurement_key":"f5a52fe5d6be1f7820a2b1aee6421959a1da0a6a17aea2e68a7f64e48329bfd4","metric":"accuracy","protocol_fingerprint":"f33ddd1da76c8fc33ef95d5e97f345c654d661ad6d878f4d8e683aa33639030d","run_fingerprint":"0ef6d53901f2b4eed4b99fe3d4906ab767a18d47ee6c994519efb430e93186d5","score":61.25000000000001,"score_display":"61","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_64a24f9630001ee70ab87c45","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e8e4efa5a1f39bd7e22917fa44c6651e09bcfd3ff06210ca8f9f3ece2076b9be","measurement_key":"7b15ffd9a86879a3ab3c6531cb6aa82cdf696d85a59fbfb6df4bcff4dda009cc","metric":"ips_score","protocol_fingerprint":"33c84bbaea8304aa237c754cd12a152eb4ba4c8a7e6f92cad76f8fe65b59ddf5","run_fingerprint":"8b0aa0861d787adc3ccb3bf6840d7d21568f4e248a7b20ec18f0725c4f6fede1","score":0.014326641851425207,"score_display":"0.0143","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_402928bff9da8bc5523c7b2e","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f6d1287f187c24a09a953df30c2879d792edbeaf3d760c1eea11192e4ed7c771","measurement_key":"f1371b48b52e4349c4045e1b6954a721005e599f21bc66aa9430957559ca7241","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"404e1d69c390082a5c0b87adf660a1919a25ced951bdbbaf9764a7bd1756393a","score":1424.8248277757675,"score_display":"1425","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_402928bff9da8bc5523c7b2e","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T12:40:01.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7c18358b32ec6dabba3cd0641ec159a3f4c5d9c5304a1aea18986303a22e552f","measurement_key":"d47e9a6dc1058d16768aa452710789ef29ef87d939c58566ee068cd015bc14f4","metric":"mean_score","protocol_fingerprint":"f990cb74f11747d21c09ac6d5eddd2a2f4c83eee32bdb2d21a3c182c304c0299","run_fingerprint":"53154b250a69a4e43d4a0b6b04ff4d2729d6d907137278b5f602bc0daa7fa5f9","score":55.00000000000001,"score_display":"55.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c112684679902abe6700b9338d34d0dc04524cd5367b7944fbca1f3f12d6c23f","measurement_key":"77369f795174b100ecfd5782700d5a1bb62ea1f4c76400b8993fc1432924fbc8","metric":"accuracy","protocol_fingerprint":"7d50bb29a34aa0dd3ddd8f042157941fe5d7ec6c855d56423cfcba0dc5753b35","run_fingerprint":"651de07ae726da8d6059c5d9b6dbcf4816a739638b0a4dc9ea8a3b7f81a04ccd","score":18.8571428571429,"score_display":"18.9","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"cursorbench":{"benchmark_release_id":"release_9acebd5b002e9c3f18a30606","benchmark_version":"CursorBench 4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:11Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7caf869f92fa2b740490c8dd49a50a3e78fa42e893979201edd4cc2c33c6db05","measurement_key":"658072345edaf68fdf8c0b9f7f3bcf120e7e3d1f85a7a90baff79ed3a90d1cba","metric":"score","protocol_fingerprint":"9b0285d6898de37b7276a9b61e639721b2c47b9ae9296bca17e79fc986b53a15","run_fingerprint":"4440d1988fef77b5ed25daa6fef3c5500094e20f3570aa0ab463e1f6c04f4d8e","score":48.4,"score_display":"48.4","source":{"id":"epoch-cursorbench","name":"Epoch AI mirror · CursorBench","url":"https://epoch.ai/benchmarks/cursorbench"},"source_authority_tier":"B","split_or_window":"official-current-suite","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2359e1a5977089f7ccc0d240747c82e1b23a2e9f16a7333f5431dcb252ddc0af","measurement_key":"4fc7a442bf32a443a624235af329d441af5cb31ba83b5da641c1a81ae6013914","metric":"eci","protocol_fingerprint":"4a8380ec7d5f2c3165205da89b379f76314783109d746bee1b4ad94d43886603","run_fingerprint":"2eb1d7806b13d060b54838d7b9deb357facba7943c8ca6366feafecdbf53bdd6","score":160.37,"score_display":"160.37","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e90398154612163000b79efe","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:11Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0eda78f3a0a6807b6329b58a340a555f81b9fc6b9bced66e6faa6a13322a514c","measurement_key":"8b624a251254b11155a557af08b5123627d90d65d621b6d36562fb9796fa1db9","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"7a7737f1d2a7a011c439011d0b6bdbe2746b86870cbb9fe1c87b5acb6f25dfdb","run_fingerprint":"687f789a507a6d5d7b6d46f020d8c0df213395369ce13f9b77119d065d4826f6","score":46.36,"score_display":"46.4","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":24,"at":"2026-10-07T20:42:31.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"61ac0472103c9dc9dcbdbff8d0ed91aabfa247855664587a5ec0d90257057ac7","measurement_key":"9fd046e6c8ba9c1df46eb96ba442589d8e9cef643aa73544f9f867a1b3489f01","metric":"mean_score","protocol_fingerprint":"47e7ed13b6c1beb3d2911bc3152659a4ee1475cb0467bd3f67eaf7625cda081d","run_fingerprint":"2962c68b70932d3a77a6189ab5b600c737e3cca12c30d1ffaa53b598682f7a8c","score":75.08771929824562,"score_display":"75.1","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"68e64c18cc77361be8754b089a5dd4523dd19cebb45b10290207a7aa0c038dcd","measurement_key":"da1dd8917cf3aaa26452b53c6f91ad4eb7208d511ccf86a19334f011f9a19a3a","metric":"elo","protocol_fingerprint":"bd3849ed7ca5e0f28f15d270073add330c8d3f617829221d2fec150e85895c28","run_fingerprint":"e7ffa98945e5740027546c2ef1147da56ab85f9d43ec59c3130827d8788eb0d0","score":1630.83,"score_display":"1631","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":22,"at":"2026-10-09T14:35:53.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"351542646899ce1e2d693c2c25eb5e728d5988b90bacd3b1eac7359fa68e24e7","measurement_key":"9b2bf690892871bfc4d485fc6087e573f7214162ebc310aa20e4b113032d3f0c","metric":"accuracy","protocol_fingerprint":"a0b068f212b619b912fcd634570206c0c70e07fb8b601064a73f01a5113fe8d4","run_fingerprint":"9f60618b9c592c6f87b002736876027d73ec1216ee471d469b57a55ccc86dffe","score":89.64646464646465,"score_display":"89.6","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_8817af9d9a0235bce0826e22","benchmark_version":"HLE finalized 2,500 · Scale protocol 2025-04-03","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":23,"at":"2026-10-08T16:52:01Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"210d4c1f100b2f734d7b987dedfdf4a2202ea904146b404c383ba6b043a30300","measurement_key":"4a6a40ac1642865a85154f29555626f6dc9d894636eeb720579aa2f764c29ce0","metric":"accuracy","protocol_fingerprint":"643ace62339da1cb20b8007e77d0b04e9a92b9d40133cc98a36d3d19b13bbe6f","run_fingerprint":"ab2d511334b8ecff15a14498d58e94deb604480bc9566c30fd2695664fd961c3","score":30.12,"score_display":"30.12","source":{"id":"scale-hle","name":"Scale AI Labs · Humanity's Last Exam Full","url":"https://labs.scale.com/leaderboard/humanitys_last_exam"},"source_authority_tier":"A+","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c017fe0d6e69d734d6826051","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"70a2d25e028a6787caff00fdab2fd3909f0b7ae37b9ea92253736d57e1531d8d","measurement_key":"acc44ff910f3f3750ce1a2cca6b8338475f5db82ae5faab070e66f9779f5dd46","metric":"accuracy","protocol_fingerprint":"339c843e337f861d6acbf46534fb66c8aaa9eb4c78cfb94a9e53dca73ceca25f","run_fingerprint":"1ea311d574dc0803277c38aa9255524a2504ffb90ce101ddd9acd904fa03bc3c","score":44.392956,"score_display":"44.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1fff8429f78eab2e5633df20b76106e53696af1e2f16153c0bacde3c644e8d2e","measurement_key":"12f07e5ecbb851457beb86a50e67a7aa6d069e527665ceeddd619d39c1d64bb5","metric":"score","protocol_fingerprint":"e900ba02b462355fbc467d91ecfb5785d4b934107e6b0054cc0af911604410e6","run_fingerprint":"98176b1f633a0d00c7547146de1e8130866cb50630bfc4f2fc3dad3ac7a75be8","score":47.278,"score_display":"47.3","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":23,"at":"2026-10-08T22:23:18Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ec994dfeee2dbab29e5b30dd520b30e62c934753564888a2dded004b3bcf1f30","measurement_key":"339f4a7393997403de0e25d0103b492687372b35936643eaf9557d6e5180773a","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"1ab80e6124d661966fb7aea3b148a2afbf17abe396b0fead25beff9851a320c8","score":67.88196428571428,"score_display":"67.88","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T16:48:32.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"237a0f6df7bef2abe510d61528098dd9b59916df4ec189ce5212ff5be59cc807","measurement_key":"d3b00af31af3058b8bf25b94309ba48258912136bddb5fc1d3dacf5215597af6","metric":"mean_score","protocol_fingerprint":"cb7f07777ed38d8bd52a692364ded762e8514350c8a0129c6d60d6301b709d57","run_fingerprint":"2f92168d34f887fc8d1187a32b0de3767e4a187175a2b16232c5e388b834ddcb","score":78.88888888888889,"score_display":"78.9","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":24,"at":"2026-10-07T21:16:36.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"551dca864acade72f6ff10891bbcd432dc343e560a865bdedeaa935a73953da4","measurement_key":"69f5b3635239b623562f66197982c801a0212f551326f679912b1df9296f8eae","metric":"mean_score","protocol_fingerprint":"492dda5a7ecb65f146bb09a90ff176ad5eb3914474f71387c7bb8b199ae656a6","run_fingerprint":"26be6ab66927465e56828cfdd1a37a4fe3e7612ee6d34c7a3ab892b752ecb908","score":98.88888888888889,"score_display":"98.9","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_64a24f9630001ee70ab87c45","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5362e7200d082540b4829af53b99d159358bffbcf573cc502a736feda6d9af3b","measurement_key":"eca9d24af3d8693316e76dc33053b942a5eeb8ee36505f3da7774141be08a398","metric":"fully_resolved_rate","protocol_fingerprint":"544dce0a787479119b554dbdbbd3fd6de38f0d8479eedcaf86707bb0f20504b2","run_fingerprint":"7be31016ff18ee92620243cb2e419d6af660653ab32c82909a6139306c33ddc5","score":2.5,"score_display":"2.5","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e77722d7abfdcad300f24b088469de04b5cac7d6fd7bb9256c184e2855ca98c4","measurement_key":"f59586a939ded331fc05c6e80f3f2ea411b5e1a528bd52167ce5fe010ac2450b","metric":"subproblem_accuracy","protocol_fingerprint":"40f49ec10c9af7781950ba9ed4411d7012b1011a1d1ceeb997f7f087ca0cf9c6","run_fingerprint":"a997ca1717e8d28901b92334a1ef9dd30160d956b1baa723ebf0724dfce5a35a","score":54.976851851851805,"score_display":"55.0","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":22,"at":"2026-10-09T14:36:06.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"54eca07622dd36f3338cece9c3943ab132bdd3fa7e997b98595d5a0af378d95e","measurement_key":"21f472e2eb101bb3722d0bba1d0673d1a70c208acfa7abf5c1b426ddc0b337bc","metric":"accuracy","protocol_fingerprint":"d8100fd039c486c8b38dae94356690651e85c35b65a2f4a1ff005468fb0404f1","run_fingerprint":"882a248a94e0b62af2a5c51c536acc6e15091d94d597f98b484b25240cdfb487","score":23.799999999999997,"score_display":"23.8","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b6d637b920c0b64adb420cc6a8a6b8376b7f1b7bbc86023283dc2c6d1b5241fd","measurement_key":"07879451aa93a44e7b4d802da884e6b5f9e3e2d2092e4f1e71c3569ec2453661","metric":"fully_solved_rate","protocol_fingerprint":"629ba584332e58c7a68571bf59ab81341ddbba637b917594e714206b6ed94bd3","run_fingerprint":"c5e94725b93009ccda507e72382aa931832a6928247b7d947844c1cc8c202fe6","score":5.725,"score_display":"5.7","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-pro-v2":{"benchmark_release_id":"release_d9b58bd286ce316ccf0ed891","benchmark_version":"Scale SWE-Bench Pro V2 public leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T20:32:00Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4d78ac263e831d9d58cb0aef218a59459fb77a7da84a2cc6392ac8c1d2e9a292","measurement_key":"3bad6db2739b553d95c4eb19457268406f8403497df7de6ad14398207899e7d8","metric":"resolved_rate","protocol_fingerprint":"c4f67f499f9d874a0a7e45c1e3502d4cbb19f22c96da5220c3a865f0354f8040","run_fingerprint":"5c5232a8c545100d6fe69f2aedb61355ca3331d6a664b66ed1a747543cb2468e","score":87.23,"score_display":"87.2","source":{"id":"scale-swe-bench-pro-v2","name":"Scale AI Labs · SWE-bench Pro V2","url":"https://labs.scale.com/leaderboard/swe_bench_pro_public_v2"},"source_authority_tier":"A+","split_or_window":"public-v2-642","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_402928bff9da8bc5523c7b2e","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"75386ceaad5aaf5ffbb9d1c1a44ba9665fca6be3cab8afd2342392e92514476b","measurement_key":"c63bd3d2c8fd4b9432aaa992008db724f169f7869f4419ac114796202ab672aa","metric":"accuracy","protocol_fingerprint":"88176da786d49196c1f6b6ea2ff59bb6fb666517104e92fe7bf2aa1d690cb567","run_fingerprint":"3fe683c472327c9ba16782ad295a434afdf9b47dd6f940707c40145aca97dc0c","score":36.364,"score_display":"36.4","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":24,"at":"2026-10-08","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cecbb255259563978c76a4df2e75e6fb3dfa7fdd3efb61785eed7d0aec72d58e","measurement_key":"b50115b70a15140fdfe8c1e541ec23f5bba60251b7ec7cbeec15bb83711952d8","metric":"accuracy","protocol_fingerprint":"3d9de72e09b5749296b8c0a74dcd519fc7d69400ba5a29d307793a47490250e6","run_fingerprint":"95293cf774a399883712fc87af7112213c7d36b45ffc49707a4e5c40506d1452","score":10.0,"score_display":"10.0","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:15Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f20bdfeea0aa85b5d1764e324170fd6da5c70b55be1b1ff0a9d970fb4b0ab367","measurement_key":"a5aba02f6b73037675d4848754502717fef9a378a3857d96b870292e07fd609c","metric":"mean_final_balance_usd","protocol_fingerprint":"af1ef0b223163ca0a5fd70f8980fbe44d476eb17eeedd0fa7f09cb11e4dbb98a","run_fingerprint":"36da00eaff1a858a283693bf2a60d409a3c736f7b94278ab29d895018033679f","score":3602.4633333333345,"score_display":"3602.46","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_438fca3d002dbd040e5f517a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3224215fc728b3366c2eebe655fd910f3242305edcf8bc3de561e3f338c4e8f1","measurement_key":"5204cc282c59f1307c17f546372844f4023c47a4db15fa5c41fd9369e64d804d","metric":"score","protocol_fingerprint":"e7f5e848e8bc62dcb56ca1b8e76c3211623f02b594c52bc75b18f8761884ad0e","run_fingerprint":"9fe33981c1c9767b951c901fe38b11aa2b4b1dc77a39a4c7c55dd184e20710ff","score":90.444,"score_display":"90.4","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1c08bb4ba5da9247e5d7c416","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2620d6e4e32f696bedec5d1c9278d0fa0f19d2af4976fa134a8898bdf8139ed6","measurement_key":"50bcfb6d7bf32b81e64f939fa60e8a238d234ae61e928d5eb4f23047353e3f47","metric":"arena_score","protocol_fingerprint":"8c6c77c90e5bdac298b066fef6c0218a451a101aec608ef15500926efbb92b5d","run_fingerprint":"31f893506123435fd9076784e1ca8b7510bbeba14e478e23fe13a5b7037f68ea","score":1588.8330617127986,"score_display":"1589","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_402928bff9da8bc5523c7b2e","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c10c11ade1461afd8c8346a528985d42772b7a37064b7a84c1351a3247a8a8c2","measurement_key":"d61ba228fe483f301a7d7a808cd23c6c8e0ab8d4813914db846145f46d37bedf","metric":"token_efficiency_weighted_score","protocol_fingerprint":"a151f5b307e508323b3ca48d3d0d5581139f4b9b249ded3e7bee3dc003fd1fca","run_fingerprint":"77d913d9b9f3d262874dbd930cc96bace8d355c45810e7e5071c55956a6da91b","score":11.695232727272726,"score_display":"11.7","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_64a24f9630001ee70ab87c45","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"anthropic/claude-haiku-5-5","model_name":"Claude haiku 5.5","parameter_count_active":null,"parameter_count_total":null,"provider":"Anthropic","selection_rank":14,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4b73b41a7de5ef70a58fe2b121d713c3aa91a61e2d47d586992b68e2c5d29bcd","measurement_key":"601694e49e6301c19c18eb374e6fb813b83a56117ed4506a1ed06a7f9faa10b6","metric":"performance_rating","protocol_fingerprint":"27f0be14ac4f083323244ac5b6ffd62ecd97b3194345e3ac7bd2b981343f7641","run_fingerprint":"a7cfe357f7dc3b68018fe3548dad7cfdf12a6a8f185193ade0b1dc7f5e9d3e38","score":1951.42,"score_display":"1951.42","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e750eb4b30cf5308f78fd5bbb314a752bd68f40f77528b12e5c7ec3c64cd31d1","measurement_key":"f4359685fba9c0ffe53ee88431b1db0192ea51510ac4d67dd74efe33ebcea838","metric":"pass_at_1","protocol_fingerprint":"fec372c219c2731ca38a304996301cb2ba615d79fd83872b61b1f4976b94aedf","run_fingerprint":"2ea7bc0988ad760874756e1a297abffbdff13b0496ce941e12c24904734b3788","score":58.20000000000001,"score_display":"58.2","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6fb2fb527bf34e516fdc871fdff2adc6a0f432cc04cf0c20624cd37d1c5089b1","measurement_key":"40ec888e34cacf1cbf0527eacf0023b1c96121d38d1bdd8183b3ff385c7b4429","metric":"pass_at_2_accuracy","protocol_fingerprint":"f49fc5d5dc17d925e46a34e90ac27d33983718b43bdeec786fc58172835b5c89","run_fingerprint":"f49fad63a8378f116653eb40aa4d5be3943c8bc21e15b067ccce8efe636b29eb","score":96.5,"score_display":"96.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"54ed6c427f02b8432ccad1d6ad55a41b9a2dda764385378f337e2b974b550651","measurement_key":"f007ce98657fc20ea3dfdb4bbeb49a9bb19d42c407388dd0a69675bd56cbfd96","metric":"accuracy","protocol_fingerprint":"5cbbd56fb7c7da82fcc952237dde82ddda0e41bb8f2be7e491076edadb0ba62a","run_fingerprint":"0daa83fbf689715d2caf59721509d52fe894c8b6b27615e885472d332505ae27","score":83.89999999999999,"score_display":"84","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a0769915514f42715f1ee64c21b1f2e5b4c23747697c1cd062a08a3fb1e53d6f","measurement_key":"5b098d5287ec1c521733b107364b2e88b5f3a4eaa58f73031a4b053a48e994dc","metric":"ips_score","protocol_fingerprint":"78ead7f38e717d142b1ab05cef4ec431b5bdc9e72e041c0cfdf17df2e50cdba1","run_fingerprint":"41a8453a6106fac3336d2f29b9d8975977fb1c99364a4f6b10d60a0637b9daef","score":-0.013902435627719558,"score_display":"-0.0139","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_10b9eba1355d3375994a7c40","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6118c9ffc639c2d04b2a784051530adb44f9183cec069c46893069cb2c44a0a1","measurement_key":"aca890d4a796940b3730f0dad2d13f1147e539eca0b8f1d6fd6ccb11258c60a5","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"b2f191a55d90decb22e1bf869f39a95ab59d8cfae73818c526c810ecef9eaa9e","score":1467.337294227145,"score_display":"1467","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_10b9eba1355d3375994a7c40","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:53:13.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f9dd099bdef26913d6265320e408247103a3255cd603e07035dee8c0f32e4c89","measurement_key":"7918d1f7663468028162a64a83f0df9d5684b87141edcda4cfebe16e442f748a","metric":"mean_score","protocol_fingerprint":"f7747f43de11ae40b88991932308c7af56eb77d62c4c3bb1464a84ac8347bcde","run_fingerprint":"61be4778176b234344beda928d45da0576d3c2f56253746d38eaf1aad88b20c6","score":47.0,"score_display":"47.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7104bc32140dae8f0f15f4aee65e20bbf40d25234ae78adb66b1a955a6daf84b","measurement_key":"e0616ed53c588008fd4cdb89196e2f4f4eb3c6496d4f2c1d1a22299fa99eaf67","metric":"accuracy","protocol_fingerprint":"596cc5a4ca79492f51c51847f7052c93d75b9f69afd7cf50a9a03f4d5717f77b","run_fingerprint":"0e4820472c1e2e83282efeb703e8a186d7cd498c82769be59c8eff30459a7287","score":30.0,"score_display":"30.0","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"cursorbench":{"benchmark_release_id":"release_9acebd5b002e9c3f18a30606","benchmark_version":"CursorBench 4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"64103639d186cef0cd17bd10831c913c8bb472733c82b51092c3f9c011724d98","measurement_key":"58c15bf015622b679d5686231110936ac7af5626d1ef787b0bb46278217dcc4b","metric":"score","protocol_fingerprint":"f672612a035137f64e1339dee647878cc4bc1d74f31822e6d7df166bab580883","run_fingerprint":"bc35420b05a54293a438b8cdb679d414117e5655cd4d076c5ec1076bfdf15588","score":41.3,"score_display":"41.3","source":{"id":"epoch-cursorbench","name":"Epoch AI mirror · CursorBench","url":"https://epoch.ai/benchmarks/cursorbench"},"source_authority_tier":"B","split_or_window":"official-current-suite","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f8f4813d3f8b1933d5f29a92aaf14ae4f72e9829122d8a04bd22b3d8f0d14437","measurement_key":"cf2fdde27718660bec6e4fd9bc18ce9ab30369c15a398b593ff89011544d4eb8","metric":"pass_at_1","protocol_fingerprint":"869d4cd8ddde2355153ef770f54e40b2142f9c58a3a57dcd9757271830347ed1","run_fingerprint":"bffca5bde24465d231f8a2a3813eb75aaf5da1ed2736e912ccfd7b929ccaad93","score":69.62305986696231,"score_display":"69.6","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"09fa157fec7635981b7cb0ec9e9fa572da6fd3e1ec9dcb6f8f68f650ef6696ad","measurement_key":"b2cc3b79662884b67446caac0561ee2cbc5e2a2386c28ebf8d45720edbb5c45e","metric":"eci","protocol_fingerprint":"84003d4daf797c6800487df93e17a6dcbacda825601a0581ea5b6e9455a002c7","run_fingerprint":"d2fca6235129c14abfe1bb7da070967daaa7621d36b4608b8f68193d20791211","score":160.09,"score_display":"160.09","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_5e3ecc9092fbf935153dfa39","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"279082650a63709bfd0578de825a500ce8db081a3f08d4843b5cf016de6b195f","measurement_key":"f27e6beafda594e0f9177e0a7cc902157ed4f6ebe00d331a261bccb2a7b1c0df","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"28b116966df3105e70a47466a630f92d7e1cc8b81dd0f1635b10ae1073527658","run_fingerprint":"cd0d08a879a68c3215c7ebd97c1779a18ec468dfe6cdc9176b9c594a4293df21","score":41.31,"score_display":"41.3","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":114,"at":"2026-07-09T15:58:30.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e232957c21deda367a725f0d7d3732be3465334216e69297cb2392ade7b821b4","measurement_key":"1128cc0f11e20f03c2ca925126796e2e2abf2227672889e89437e82e64adbec8","metric":"mean_score","protocol_fingerprint":"133ae6c889e89aa9f144f7637d831b8e5ea0fd03397f291fb8ac45efa2691f0a","run_fingerprint":"15a006cd9b123197a9fa4fa47214c913428c159e7767398cae8e2bd36acc6e13","score":85.96491228070175,"score_display":"86.0","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":114,"at":"2026-07-09T15:58:30.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d6265695e5784bc8a7e04ece0087e3dde58d1950f531b65370a296857ad2ce84","measurement_key":"084e19c0ac66a7c401f06a8cfae77e6ae9647625bb83eaf97bf296348b7c815a","metric":"mean_score","protocol_fingerprint":"a24bdb9bd60f8442edd874a72bb0fb71928186fd85d815b59d6bd044216d937d","run_fingerprint":"d5eb78a15c5098c1816519b5eca5ae37f14d2ea2a0c211ccc3d9563c0d7b99b5","score":70.73170731707317,"score_display":"70.7","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fb5bb99f4a7b99d7e8f9c37c962fc65c2ab0d1cf38d0db715384adb4737ed3e3","measurement_key":"5fa46cee18c3cd8d5d015e3419304e0f059ffe3dadfc0850e10d7c020a605f32","metric":"elo","protocol_fingerprint":"4438714d09a3be3f0ddb1e48f461efc662d3bbfc2af940f9d3784a12162e10af","run_fingerprint":"1ecfad4c6d855e372c5df9e4fef63bdb3bfd40e59d884b5e4344fb473e13d423","score":1461.46,"score_display":"1461","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"afa0dd8c0f3d97966ca4789ba04b9ddf1402801e3e49d2031368251d06e6c467","measurement_key":"c1867bdcbffba5d06eca3c386773b884c43e00ca42d2fcf467892e97cee8f3ce","metric":"accuracy","protocol_fingerprint":"9259e084f0476af524fbbad3e37f90d758af18a650a41c293be77a77d0ac9c1a","run_fingerprint":"a8b2727e7b4ae184f74a40e90aad9e73cfe2c443690c42b531e757c7757de9f1","score":90.909,"score_display":"90.91","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_10b9eba1355d3375994a7c40","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-10-26T03:03:55Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f49a9f68bee650b38da142c0f21097e457939d336a2b92080cceeb47c8718366","measurement_key":"900a7a8460b5d5540978cd4939254ced902f10bfd5936b7755f7b9f7b23a2d9b","metric":"accuracy","protocol_fingerprint":"d0afbc8f90ee9aa96eb1302c1761bc6e4863607d9c8697f73b2e6e39656c559f","run_fingerprint":"3668031ee53d691f88bc25669ac2e8e71b7e409574de724704bed38ae05a93c2","score":42.910102,"score_display":"42.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":47,"at":"2026-09-14T23:34:42Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e5e3bb19c310f7238c0ee6cc96812e62b3f9b04ca5cfbecddeba9c0557bfae59","measurement_key":"214a5bef224a393515c8be3e4a562f8dd2069e230a29e0f4d4cadc9420609cff","metric":"score","protocol_fingerprint":"030e6f30c5b5f4c6c26d341d3d19f39f3f0c1536e78b5ce9e347ba1f12247faf","run_fingerprint":"0de9a663db9756407267c731f1c4b0ab93295ed1c7fbc671737d793afaa647c3","score":87.611,"score_display":"87.6","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"76e731809396bdb6d171e27ec2d22186babe2b10b99da863d4f8975712f85f4c","measurement_key":"c5cc15f99c17fa91f21f7890aabfe2fb508a0ab2ff7da404f163a0e5859ed9ba","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"966e12ac20394b1ec008e6a94f243c9263202df50d8b207f84ac18efc9fe2e52","score":77.93625,"score_display":"77.94","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"eda18a8481dfbfd1f072440f2a9e46d2f3aaef65c369c6012b7e98c4c3d6831d","measurement_key":"fd6f1051bc60cc532d6b34fc115b9a092d960ecb5803a90fa97ec06ca1f6f3c6","metric":"pass_at_1","protocol_fingerprint":"4a8010f008cb50516a1869e16177d943a175d04381a8535bfe752778d45fccc2","run_fingerprint":"9ba42b1eff6f928b3f6c1987ea7bb8a707b437f978714efda59c25896b4cf272","score":85.93,"score_display":"85.9","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_10b9eba1355d3375994a7c40","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":11,"at":"2026-10-20T20:32:26.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"af1b21692f16906a8ddb3160e6267b102e85fc851fca4c3e2e8885978d4e654a","measurement_key":"c6c7fefdd60cadb3c314739f63c48f8f33493876bbf46c9ba4cc2410892f021d","metric":"mean_score","protocol_fingerprint":"509b8fb4fca90460d340b424975a2299f1777c3a2aa05ded4252d395d3e93606","run_fingerprint":"52b6405657288db54ba42354b45554962b4dcb0940faac3b27698d655ab78c2b","score":41.11111111111111,"score_display":"41.1","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e2b34a3f5d5859e459ec25cb028566ae5ce9ad5b45bddee9b02469f755e6653a","measurement_key":"f1f5d081bc3edc941279a29d6365c275996e3b42d70e686d7f97e32450c9b261","metric":"accuracy","protocol_fingerprint":"f9594ee2a69f9f7a401699c6642b5cf69d6c2a1e4951ee73999b288346f6b09a","run_fingerprint":"fa85d1eab75ad8f26ec33bbe194d17e267c1ad1781aee9b9261d149befb3676b","score":86.659,"score_display":"86.7","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_10b9eba1355d3375994a7c40","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:41Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"60f00c905f1c10d5db43dd22489eeb67963dbd883953bdfff309b57d9f17b5ac","measurement_key":"3dc900737d2f7a950fd46ba8eb5ff1f21273ccec1f96403edfe9da8c4e6187f7","metric":"accuracy","protocol_fingerprint":"f61d7669c11176ea7984c2becaef37b06a13c7a2ea64ef1aee1bd9303c1c47a2","run_fingerprint":"2ee450b2ef9be8508b76fd52452e6321704ce41624111297ebaf8b39d659dbca","score":86.474,"score_display":"86.5","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":114,"at":"2026-07-09T17:07:54.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c3b4aec2b669450cd4942f8692c52f5df947e0ed7d44252f3c3308d65f25f348","measurement_key":"fa94d5172b6b6cbe8ff6fa5361662d11d4b29a68554a868c6938decf4e6e4d9d","metric":"mean_score","protocol_fingerprint":"be69afbe31d7935060cfd908634b1f0b12578c8486f2dfc26e2a3cb0cf474579","run_fingerprint":"3965510986036d214f16ea06457784f9d2e523a74ded20d8823f1ab5310c1c1b","score":99.72222222222223,"score_display":"99.7","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7f731ba0bed3e5c1929ccb28b3c1f206eb551be2fc82eac496af15325c1c8ef5","measurement_key":"1637ff5b8aab2a8a0758ab65f5cc71bc9bb792f46a5f27ce3e31cff2fb559977","metric":"fully_resolved_rate","protocol_fingerprint":"785c19dfcc17a217bf43871e003523ca62db7d85c08826a350e351fd85b30997","run_fingerprint":"2837d20ce59ba49adcee7ddb57ee72b40dda5fe8f394cf1ad1c149e8f088dabe","score":0.5,"score_display":"0.5","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2077c4f18de65cc728a797e57449a6f77d5906814f5b554bb8e89b62cfdf702d","measurement_key":"2e2c1e8293e97418ecf53664a3fbd6e4db9d6aa7a9e680ea5a21ab417c712107","metric":"subproblem_accuracy","protocol_fingerprint":"3f3b163f8a0e9ff3ded55295ab9a2c86e218e7202c444a20602d29a924e7bc84","run_fingerprint":"102589cbc8c681b26512485a1ad4c8d4031c5cd783b45c7041efc95ab017c857","score":54.976851851851805,"score_display":"55.0","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6cbd9c5d671b293a6a269fa7d907d5e52a61081d799a60b893f0ba8b1d82dad3","measurement_key":"0c71a36e52910c552d5cabd63ca1749f9be44ad166a6e19991fc73cb2fd7e9c5","metric":"accuracy_avg_at_5","protocol_fingerprint":"902409fd7a7a4a66284db7f42458a2c436474c8784c97627642233ce61ef4bbb","run_fingerprint":"c5664b0c2edd908342147bf6754442b4a98f946226905e3dff21716e4c147d56","score":48.9,"score_display":"48.9","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_10b9eba1355d3375994a7c40","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":82,"at":"2026-08-10T23:44:21.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"215d8d2adf48ab9a2c3cda865f5475bcca7cc8c0c381c0032addb13b6473909a","measurement_key":"cf2358a67524fab02ec5ccf406e10c235f0558991962e0988c95972f9b7feb98","metric":"accuracy","protocol_fingerprint":"cf9b8ad33e4f2c0dd59dcc48ff4cf1e8b142dea609b0caac629012897ecc5c0d","run_fingerprint":"43c08742fd124e14cd52e42b1f79e0ea2b62f72c136ff140da3b18aa04feab13","score":43.2,"score_display":"43.2","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b80853a0bf0bdb75ce23d43bbd0583c12020b63673cca931ba38de7dcf42aa42","measurement_key":"e0a0937e4999d11e2c39a5a895c4572d64c3d4d62aae1f4eaf05d8d3fe2364b1","metric":"fully_solved_rate","protocol_fingerprint":"4a88e5b3a014fabfb8c0519eeddb0aaad2024bb7a038a6b65a5431402cfd3458","run_fingerprint":"fd79bbdaa60e95caaaa307263a256d01e1f6c6e3f772a04002d108bb14123b83","score":9.542,"score_display":"9.5","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-pro-v2":{"benchmark_release_id":"release_d9b58bd286ce316ccf0ed891","benchmark_version":"Scale SWE-Bench Pro V2 public leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":25,"at":"2026-10-07T01:44:58Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"04ebe9159b1a4d7f9d85093b88a089e09771bcddfb960ab93e490a5627a16af4","measurement_key":"1112b70ffd75b71a5ee49332890c8948833695f34168e54fe258c92a5db5c5f8","metric":"resolved_rate","protocol_fingerprint":"bb3b98dbc0e5353be5d24b583c01ec13af2000801188ab700ee3905a63ebfcb1","run_fingerprint":"e9256dcf3f0659b5ff8591333da7786898a48f6495df1d72827198d12bd6319f","score":92.37,"score_display":"92.4","source":{"id":"scale-swe-bench-pro-v2","name":"Scale AI Labs · SWE-bench Pro V2","url":"https://labs.scale.com/leaderboard/swe_bench_pro_public_v2"},"source_authority_tier":"A+","split_or_window":"public-v2-642","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_10b9eba1355d3375994a7c40","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a805497b4515cb42c17841e6fd90b7dd8ded2ad89f08cc13bcb756f397f77818","measurement_key":"1cf502937b6a3323a27e723eae66aad19c244a874ba3f088d9e626c91d3c5354","metric":"resolved_rate","protocol_fingerprint":"9f593eff97eded368a2a5202ecb446e3a70d257e0b15e124388293ec2b52e7bb","run_fingerprint":"de8b52f7100b63ce8814052d4602d333bb4f5ef964ea27a537cc987ea86e4f31","score":95.4,"score_display":"95.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a805497b4515cb42c17841e6fd90b7dd8ded2ad89f08cc13bcb756f397f77818","measurement_key":"1cf502937b6a3323a27e723eae66aad19c244a874ba3f088d9e626c91d3c5354","metric":"resolved_rate","protocol_fingerprint":"9f593eff97eded368a2a5202ecb446e3a70d257e0b15e124388293ec2b52e7bb","reporting_origin":"organizer","run_fingerprint":"de8b52f7100b63ce8814052d4602d333bb4f5ef964ea27a537cc987ea86e4f31","score":95.4,"score_display":"95.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-10-26T03:03:55Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3dec1ebb1c074c38e78f8efbb30446d2bf53e76197e9f44c84eed9d0e8930560","measurement_key":"075565d65c1c752420ea7561b8b55a62167b2fd1ab3e8b926d75fe3d38314dea","metric":"pass_at_1","protocol_fingerprint":"88ed41acc102afe2027af4516d6adba5f83278c801741a5692fc562408cbffb2","run_fingerprint":"dfc9b375db76d7b6826d46b7e1929052cc6fc2836418aa2429f26d4803a5f876","score":40.206186,"score_display":"40.2","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"83698a8a2edc3c85c45c75f86ddd31889360005d421b380baf1e5a0d5c1de779","measurement_key":"1aed817279e29c0ede2c554919bb4ec06a5f898ae68c3781c351192add557ea2","metric":"accuracy","protocol_fingerprint":"34c0fab0e6346dabe9646d8debe4dc216ea32bad33a0108c393ed5f6f43ff452","run_fingerprint":"02bb961bf99f8098067f60242182fc3c757c1902e74b7dd6e2c5f7c767a635a5","score":77.528,"score_display":"77.5","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-3":{"benchmark_release_id":"release_ceb36f25882d8cea2c9d084a","benchmark_version":"3.0 · b936386b-4afd-4ad7-aa7f-6b52bcab9853","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":80,"at":"2026-08-12T21:39:34.661007+00:00","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c11ea58daf33dc934917dad6b9ed9c08626c6a2c192a071ed482a921a4a4d2ff","measurement_key":"65953bb4f2376a19d9672a0b6f359b9742d31fefd6677b717aa91f8ac7637882","metric":"accuracy","protocol_fingerprint":"a3674846c9dcf29b2407ae67a492b1d523022ddcfd99d682b436215d9b3be416","run_fingerprint":"763202f791382f7b7ef5da41a61a23d7342d7f54ffa25ffabfe00a8c2e77283f","score":20.81,"score_display":"20.81","source":{"id":"terminal-bench-3","name":"Terminal-Bench 3.0","url":"https://ofhuhcpkvzjlejydnvyd.supabase.co/functions/v1/leaderboard-read"},"source_authority_tier":"A+","split_or_window":"official-74-task-leaderboard","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e8c624ad25eb75d29f6b71b1ad10284e821c36ad7e714874731b496030934bc3","measurement_key":"b818eb92213a94ea89df834f452f0cab2f59bfeb4ab6dca126bee638fa49b87e","metric":"accuracy","protocol_fingerprint":"4f9cad5114a3ed9fe0ae7bc0a047a19b833e44aa7c26716f9026b615bbfadd28","run_fingerprint":"e059c72c91c14e650a68f5cadc5059c8866692b5ad1a961fc7031be10208205b","score":22.727,"score_display":"22.7","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"947edc512a3e891792825bd53b6a3e17400a6156b27e68c7dc1f5d6ab6193137","measurement_key":"931a67593399614666330c9159b0186e6e348a5a96a8680ca2e5991a4daf7eb1","metric":"accuracy","protocol_fingerprint":"f86eabd07ed6cd5c58f3bf788e838786c6ae9596806380bc0886b29d04157b44","run_fingerprint":"99731683cdfb6a980bd718765c99c3ae18a73239e779c85e7c3c1ce1b275597d","score":10.0,"score_display":"10.0","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4a58472e3738fbbbad9cf162cd1406eca1e51404733838aeed700477cc57fc3b","measurement_key":"5ed3f2d454bc319c12b902571c558cb7528db168b73e76c7e17aaeabc519c470","metric":"mean_final_balance_usd","protocol_fingerprint":"a513e3bc1170493bbe4a4f0ea74a94f7ada17a29a737518886e56958e0c294d1","run_fingerprint":"945bee3b92aa43c98e4059ffe61d3d6531a7228485b16053d54648e9ab7a0f07","score":7343.206,"score_display":"7343.21","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0770c98a055bcbf0b3bfe388","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b082e85d4c64ac35ab1834c5888f06b3984ec9cedf4f1dedf1c79e9b6d73af1c","measurement_key":"a9ee828aafa9ab8928ca2dcb0729e77ef83f164a1fcea23ba2348c5e3b9205ed","metric":"score","protocol_fingerprint":"71e22a4e7f483e29770b8f34273d2da8e3cf3d23bb4d9a57cd99162e7b8babbd","run_fingerprint":"bca05426d3268429d7c3b87f2c9da0a8f7470fa4f47ee3f540c51126d789ff2e","score":74.594,"score_display":"74.6","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_7a539a480ccf940eda2cf169","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"508235f00d0f73ddf54c782c11f3d619eedc14afd7e2a0f7ff3ec1bef76ed8b0","measurement_key":"00b7909b5fde4a7f9207a29a908f14164a211a52c10bee6dbc1933120b81299d","metric":"arena_score","protocol_fingerprint":"c783a058711fa756b0b4c0b6a819ebfd5e28e53155c8de9f59425059f536a44e","run_fingerprint":"ec54b9d2a8d653faf2bbbd6dcc88f2ee7373c0ef143965861d0b91b7526f67d1","score":1520.1279670236868,"score_display":"1520","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_10b9eba1355d3375994a7c40","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6729b7f8b7fae0aa6b463bf70f850e788b118fcd646fc5e9e1d9a9af8f653ab8","measurement_key":"08630b3cb1fef82bb8260ce31b7f415c28f5f0f6717eee737ff41f48058e81bd","metric":"accuracy","protocol_fingerprint":"c3a637f5e3e24eea32adeca84ed74d99473b1db1a5d4d3c763e35c76d785f768","run_fingerprint":"2fd388997e65bfb3841305faadd1286784bbaa658533fd6dd4c43f6f4ebc7c01","score":78.27,"score_display":"78.3","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_70294a052eedaa815d9395a8","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"openai/gpt-5-6-terra","model_name":"GPT 5.6 Terra","parameter_count_active":null,"parameter_count_total":null,"provider":"OpenAI","selection_rank":15,"weights_status":"closed"},{"cells":{"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"aee2ce79c54f08fe76385d4cd5f478e829b4d770e51c98ea1681cc588413b6a9","measurement_key":"86919496546aa7be1c1eb5fa75757c17f7b11795d4a6802ff8df53d986b5876f","metric":"pass_at_2_accuracy","protocol_fingerprint":"d3620fdda0fa9df1c5a9409fcc1a63d89656463398c9dd19a03fe44da9701675","run_fingerprint":"40dffe2095bb778fe6d51ddea6fce7bf3ee5f752f0dfc13f0e79122d405c6bcf","score":94.5,"score_display":"94.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_b5490cd7180da4cea2102329","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b7b376846be484c0de704db9e09c9a311c08c093a8c867728a25c3f55b5f463b","measurement_key":"e27b435cdf98848cf675c7acf80624eced4f490fec594123f650185c973fc6bf","metric":"accuracy","protocol_fingerprint":"d70d8bdb8ded770b2df917285d64d3028140c60dbda01cec10ac66a81e6c4e43","run_fingerprint":"cd35d68abdfec229206a312905cc34c1a1692c02755d7d8e80852e5bbfb8e6c2","score":83.33,"score_display":"83","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_b5490cd7180da4cea2102329","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":17,"at":"2026-10-14T09:56:24.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1214adbd9b742874bc90b9f8c889927e741a932e17e0caf66b5903a1f972b04f","measurement_key":"d86f11db943920dc2c59618e06ce973f39130e190b60936331690c946d38d8c1","metric":"mean_score","protocol_fingerprint":"d473ce7b9e2743c267f016af99f527f45d075aab2a94d3fb3a9bdd16a76d5ad2","run_fingerprint":"ac536d4b3e4f92b96702db2a95cab41d2d8a4eb249586934b217d37bff717d43","score":59.0,"score_display":"59.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_b5490cd7180da4cea2102329","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d370876a81f1018ca4d35661584babac4ff139009a5b08986f00568f656b0f19","measurement_key":"127b9d4128b3c26650e95d10155fc3081c811bdadc861d563e65a00ae7da7813","metric":"accuracy","protocol_fingerprint":"20bad2d02546d0dbea2a4202e81e21d75ec48fe9047a59199fe4024c7b4f73c4","run_fingerprint":"a192f0eb1c79c81f3801d96d9e6cafa09a94492ca1b6a09e56bfedb16a7315e8","score":30.0,"score_display":"30.0","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_b5490cd7180da4cea2102329","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e68c148ecd8289a397dd590d6fc9e92c0158a0673c0af12d6445bbc852856443","measurement_key":"ac3f5eed7ec7fc4a98e9a627ed4875639d414698c9b8e916a343d77975d7e8cd","metric":"eci","protocol_fingerprint":"fe3259c331bc15dac88d3c255cb9da15e63e76cd00edb96ecf08eb0651040931","run_fingerprint":"790de8e76f6a90a0ae12af89212e889a260bab34c6e96354c421080c941ab42f","score":159.81,"score_display":"159.81","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_810ad01488e903e7ff5a14ea","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":141,"at":"2026-06-13T02:38:02.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c35087f7442b680df7d9d73299a80ee0f187217edf3ea3b5dcb8a99952e88c85","measurement_key":"e7999266ee11ceddb78124032aff4b7842ef463685f02e7fe9395f71ec112816","metric":"mean_score","protocol_fingerprint":"c8064973eb5564782e385b99cac1d2a5363d6786ade312eca4d6beca296ca1ac","run_fingerprint":"f391a5e8ca20523d7cbdddbe05989e74fd53bc7ab2f58385b02babb940bf3feb","score":82.45614035087719,"score_display":"82.5","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_b5490cd7180da4cea2102329","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":141,"at":"2026-06-13T02:38:02.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0560402bae1ffabb3092d47e7a4864bc41f4dbcf5dd9b37f424fc4ae2d2982b6","measurement_key":"a4d25cb76c2ee254d3b2a9b9d7f58d62278b638b868f082270085c04272c04f4","metric":"mean_score","protocol_fingerprint":"cfcfd105753964b6092a611d388de2bd1d1b6f3f4e2ad588abccb20d09c05eba","run_fingerprint":"db774535d3ad057d3a4e8ed672736934a1ffb95758e2e636f8347d9403217339","score":58.536585365853654,"score_display":"58.5","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_b5490cd7180da4cea2102329","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":226,"at":"2026-03-20T00:19:39.820Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"c992b13120d5f50a6aee9a19d1bf911a395f343ddcf6fefd31af09d04a746bc0","measurement_key":"82dfed83fe6f31ff6f8dd835de654875166cd4798c4f1b07fffd3c4462cf95ab","metric":"accuracy","protocol_fingerprint":"e472fbb92aa2c73008c634b78c57262b905e36573196b7808f984bba5edb23f6","run_fingerprint":"c1173a657b58caa2004110529ecc167d421a9814bada59d97bf62eb74ed33cab","score":94.6,"score_display":"94.6","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_b5490cd7180da4cea2102329","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_8817af9d9a0235bce0826e22","benchmark_version":"HLE finalized 2,500 · Scale protocol 2025-04-03","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":222,"at":"2026-03-23T21:12:56Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"a508b8ac1e13fbcbc5f714149db2f81e903b1a81cf7ac08e5515dac05a10bdef","measurement_key":"e3c2fd663f8d25e1faf1cd6028b905f10bbe3460211f9145cec29269c80fb431","metric":"accuracy","protocol_fingerprint":"a5f33ec7a278e3b74b3e2cba4b72f1d02c1f5fd642a9c963d65b1d2eee6b3cf8","run_fingerprint":"341b07e8e94251417d8dcf1fec73627b400a46f05a69129a10f216ad423d771e","score":44.32,"score_display":"44.32","source":{"id":"scale-hle","name":"Scale AI Labs · Humanity's Last Exam Full","url":"https://labs.scale.com/leaderboard/humanitys_last_exam"},"source_authority_tier":"A+","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d9016c6789c93f7997fae173","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"90706731f3eb4e40c071b93ea4ca6e4cc5ac60fa9187e234dba442f55ea5b500","measurement_key":"6a19e1b57ce3d9b57046b7df908bf8b367eccea2af93f4ec93edde4cfa1dbb0f","metric":"accuracy_avg_at_5","protocol_fingerprint":"8f34d561d4c9ab49272d860affee75cf2fd058ae445783d63eb3ccb55e8e7f12","run_fingerprint":"c349e5c8a3423545f594717e2fcb519fece2677a0d3d25140e8989afd41b1a37","score":74.1,"score_display":"74.1","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d919041bb5adc55760362ecf","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:28:24.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f813720596c4d46ed80f58f44fdbb17d388a9adcfe5523b84b2b7ee330cc0c2c","measurement_key":"1715ef5763076440551f9c10c9aab2fe0f55301b0ecc59fcdc6e2144c0a84020","metric":"accuracy","protocol_fingerprint":"7a9312bb814bd62a83ca8daba17fab3f15dd4cacf4f0f7d654c6220ef25f94ea","run_fingerprint":"92dc6ef9d2bda5b1affb64fbd256c81bee65e371c1a939445298f9e88a7e1f7f","score":46.300000000000004,"score_display":"46.3","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_b5490cd7180da4cea2102329","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7615cfbcfaa999bf4f630ae12cf22ae8f7bc25d3eb7e276efab0a7372aa2362f","measurement_key":"eeebaf321f41c67b1b1472bc8e021432b66ff597fb1f9eb640e16200aff3049a","metric":"accuracy","protocol_fingerprint":"24f3d247a66f5abc9d7b5ec648f3fddb530e8917ded832cce96c305b839ac051","run_fingerprint":"3f8d18e1c08c68151e6e04c047208e7bbbfaafac41daed1a1b349b9c4318f056","score":57.440000000000005,"score_display":"57.4","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_c2e76640622cf0a45f5bec51","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"openai/gpt-5-4-pro","model_name":"GPT 5.4 Pro","parameter_count_active":null,"parameter_count_total":null,"provider":"OpenAI","selection_rank":16,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"42bce2e8ff4341440c29f00235325f3ce8f804648e2bb629c670675b4edca37b","measurement_key":"2f82943d52dbf29be615476871da74e15ad3d0fab065ec6609295388b6e09740","metric":"performance_rating","protocol_fingerprint":"2d92da04a443fbc506c1f2abe595602cd41f70cf835a170a1b89821baaa2b939","run_fingerprint":"d594c8cb91ee07449d415d8782e5af74cc622af414264a97cbd1d2bfa1fc474a","score":1563.83,"score_display":"1563.83","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_3ff20fb03ea5572c13bd7021","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ab4098b38f43b4ebb93a81c10ed38cccc325c93b20220d28f1fcb19c3a23c8ec","measurement_key":"2705de0a6e3e326930603ff69db2eef7fb1e6de36b56fb3d42a8fda34894db59","metric":"pass_at_1","protocol_fingerprint":"82ea4a6880dec1d92a79a955a76dbcc1519cbe28021f6ca3d4dd37556cbfa3ce","run_fingerprint":"6aebcb806ebadbbd98711f5228fc40f227f2525111b0474d5e74f6190250098b","score":48.9,"score_display":"48.9","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"63508e0885fa54fc627b672aa7d56803cc249de871ddf196f4367c92c3f8b12d","measurement_key":"9f9304d47ca0b7516809d46cad525f556287dc3bdfd49341c801dd9fe7d3d262","metric":"pass_at_2_accuracy","protocol_fingerprint":"9f87e4176f2a64b2f0804476be952e926e8821a4e85daebece5d9588a07bbac2","run_fingerprint":"119ada31b69c498de358109a11dc3d31e6bbe0cce7f9adffeb5b99ffae395423","score":92.5,"score_display":"92.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":59,"at":"2026-09-02T13:33:02Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3da4350f9c010ec86ee5d8b00660dccfcb9965a7d1e6dff7a532136566819bc0","measurement_key":"a95fbc5c5338ac9e0159bba3ece19c62eafe388ebe27f088a1712164fbfeb1da","metric":"accuracy","protocol_fingerprint":"785a72df191545092d039dd57501ca156b8dd8150479806c6b50c0373c9796f5","run_fingerprint":"72da4da2a24c118696e25d0877da5582ed1ca9cc9bc70ec67e229cd766bc309a","score":72.08,"score_display":"72","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_3ff20fb03ea5572c13bd7021","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7090728c577fc41d1f68ec4f32641fa8a52db2e9ef03aadc3d9d5f0431c3929f","measurement_key":"6463d4149ee2a85c80d20cfd86b2679ca5301a04b13d4f06f84fdacf0a1f906d","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"12cb5102272989009a293acf4a7feef24e6863d034e94407e04ffb263de5c763","score":1481.711070665865,"score_display":"1482","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_3ff20fb03ea5572c13bd7021","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:35:27.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"18227964cda56c962b6c7c48015e51c13572f13d8936fe3d669a2043cb1d3919","measurement_key":"4080cd809e02683209a9d62927ac2056d55bd4f4ddffc3eec62999c0f69a94e4","metric":"mean_score","protocol_fingerprint":"62b52b71b2ccb9831d5c233c3ed19a3604763b637badb1f1ea577a9bcc05a7c4","run_fingerprint":"9249b518702e1626a876e9e0319acd834520d0f8b82ebc718d8f7a6f30afce14","score":52.0,"score_display":"52.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:41Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ee2ca80d8e2b18dc16ae537aa2f6216379eeac74f2547cd4b19211ed6174aac9","measurement_key":"529ef5f91d5c16ab5dc6917ce875b1513c4f7b63151acd280b0da480a1cae675","metric":"accuracy","protocol_fingerprint":"eae1f751d22a1666394481c64aad373db1009d5cf59454f549cbd63424bacc61","run_fingerprint":"2efe2ad3f337edb173ed3845366befe82319ae9f180350ee4e62c9335b76b4d3","score":20.8571428571429,"score_display":"20.9","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1d530abfe9a116a88ad444aef13b9e074953d117c33e68d3e1cf2e7d2e1925dc","measurement_key":"02e6b3c58206dd1bd7a159c4b350f1c71f8bfec1aab6e1e59f3d0b3c243b77a1","metric":"pass_at_1","protocol_fingerprint":"4ad987fa0c4aefb8ce2c11684129ff04829491fd3bdfed633b66139aa56c3c1d","run_fingerprint":"71a0f61a00fa655e502a3f9271ff3bd4787f6ad87f5eac0047c2db9393e1ecbe","score":54.36241610738255,"score_display":"54.4","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_576644939af96eac30f5bf8d","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0d292b5f37a0763aac69e19f2c9e43222ae4f608d34dd4ff7c4711676b0d73bc","measurement_key":"01d3b2a79401ede916af9cb97ee09b4a4f4788c043e47fcd02e131b0a83a2588","metric":"eci","protocol_fingerprint":"ef857165a5b10fdf19e8f420846f2ccb73e01232080de55cadbe4728731a2864","run_fingerprint":"a20acfe346121f1705512bef15016bf377e68e6f9277323ded07d20b795e091a","score":159.57,"score_display":"159.57","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_19fe5fa33d354d1d1a022388","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9049f8d808935c905e5ecc78f1794c97f1da290a808ca9b97a1b381e3c7a512b","measurement_key":"089c34ae740387b9b96d0f1b95d4529fefe13343c35f798b37a814172d4693b8","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"6c43f8697f1e896c86b18155ebe54af2143529dfe05f19c2b87a6469d8be96e5","run_fingerprint":"70d55f2a031712951adea002f68246f5071df74457fd9e257f399c9c4f974492","score":46.5,"score_display":"46.5","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":143,"at":"2026-06-10T15:25:15.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fd77c67e665368bab7981e3bfd6180a1ad39a4bb77c1c7e14d43bb3572dd8a46","measurement_key":"759c1be35bd75aafa23987c17208192f9cb76f97882a61100bde20c0a317620a","metric":"mean_score","protocol_fingerprint":"dd340eb941ab0c21506a3592392589d334adab0312a07863d24010721c5eb092","run_fingerprint":"bc6862118a68f29930153141c3eff689211765cd89d0ecfcae6e9341c88bbdcd","score":80.0,"score_display":"80.0","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":143,"at":"2026-06-10T15:25:15.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2358d47cac15e978cbb4c0b4ae399d02ed8c4d45583ab59ca75ffe1862f8d89d","measurement_key":"71a368162bf05e9b61783707e946a3b7023baba1a625d9362ce1dd4f0092332d","metric":"mean_score","protocol_fingerprint":"75931d8996e8e66e261aebde906fd9ff2c0c295340bc18b20aa6eb2f379cba06","run_fingerprint":"d3dba3667d637752967aaa8ba99e11dfe4682903743dd8aed384e40d517e0b8c","score":56.09756097560976,"score_display":"56.1","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e6e2f30699dc1ade952251e4409a65fb163f3324da49ee35d48f369ead9cd41e","measurement_key":"8865cb2dd4d4fcf63afff6221ad71aa55035e7b20a3edb08f97655d844ab6c00","metric":"elo","protocol_fingerprint":"1fa926baa74e6bdba5b0b1b08401bbd351b83d6a5aafdfe20fb555e451bdf8fc","run_fingerprint":"f5c5105eaa4dfe0637a7dccfec7e22f5ace8a85e0737022b78a2cc63fadfe55d","score":1461.75,"score_display":"1462","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f9c1ccb88ab1f56f79bbfe79e72186b376bfc9c90cf68fd1b040944f71063697","measurement_key":"7a8fddf098d1f02a59b2982a29a5f34e95d806a00f747eb2203a6d08ffc1b030","metric":"accuracy","protocol_fingerprint":"a7bcf8a4474e072f185140710fbcbe3fd0978faa8934b4e9f23be6351419ad5f","run_fingerprint":"82e901da5f5f44589f29d61b7e4daba50f8cfb6ceeef754a6faa6f3438019f22","score":92.424,"score_display":"92.42","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gso":{"benchmark_release_id":"release_176f07ea4e9e0b8dfeede990","benchmark_version":"GSO current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":112,"at":"2026-07-12","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c533cbdd1802c82945b2e917ed27a0ddf31a898791e4e052cc3c7c405b054199","measurement_key":"28aa727421ed619caeb9f24db21a9b2bfccea6fef0f82ee043a2eeda4621292c","metric":"opt_at_1","protocol_fingerprint":"d3cca460ab4bb7193a78c5fe79da02aa8e3f4b1608bc2f2d43a1e4e0f62c44dd","run_fingerprint":"25ca9010468707815cc61b9dca5b279c496c4b6f0089a5240e2ca621679c0713","score":47.06,"score_display":"47.1","source":{"id":"epoch-gso","name":"Epoch AI mirror · GSO","url":"https://epoch.ai/benchmarks/gso"},"source_authority_tier":"B","split_or_window":"official-set-opt-at-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_362ecb5ef36351fe2feb7757","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"hle":{"benchmark_release_id":"release_c1afb6c54b8ceec8bc1f121c","benchmark_version":"HLE original full multimodal","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":157,"at":"2026-05-28","last_confirmed_at":"2026-11-01T07:28:19Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b082396918f198ce2501b24ea8e2b8bad459f88e9f6aaeba9513c30b48eef83d","measurement_key":"856dbb740b37f6f98e0692ad57d4dbc504d34e0cc291c4b62768355541feac9d","metric":"accuracy","protocol_fingerprint":"8828394c5ab348b4e326438defb67fbb61251e8435b7c24d33f97db6f8d78421","run_fingerprint":"1810b710761c27cc29697c1b0fe2e6067b5a83a11a8f3b4241f2c3a9be7d4859","score":49.8,"score_display":"49.8","source":{"id":"anthropic-opus-4-8-hle","name":"Anthropic · Claude Opus 4.8 System Card","url":"https://www-cdn.anthropic.com/0f0c97ad20d8005706296bd92aa1c27c6b2f4f61/Claude%20Opus%204.8%20System%20Card.pdf"},"source_authority_tier":"B","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0dc76ca4c859b3a6a92b7b6a","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6f6b5c8b08b0d34db071cd7c19ab25c8b56cc849caceb5b8011b23e32f30f485","measurement_key":"a378b4e5c5c3f0c3475fc839c29f87c08b7fa36b69f2e64c97869be5bcdbc7eb","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"06c74994d7ac87c262cbe9069939ba11e776f3b7f4c01dcc082d392c17edfb68","score":76.22398809523808,"score_display":"76.22","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ec34b020d99fdb58074f33f0c56fb1f6ab98d103b461a5781ef57460b9754a25","measurement_key":"dc4c08d09e59b1e27dba1c9fe9d22aee08a71b2241e127bb7a3a9bf180a4c6c9","metric":"pass_at_1","protocol_fingerprint":"7d4e4718d7dd970dc7838f53b8895871966c9f3ab0380b65ee7707fbee42e207","run_fingerprint":"4c42ad29713caf2f52aff64c63daff2cf98bab5639399cc89ba17b75bdc018e4","score":87.819,"score_display":"87.8","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":156,"at":"2026-05-28T17:37:01Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"eeb0a55ffa94246fb66df199aa36f8925631cbaaedeb003b5fc2cf1a087fe2c2","measurement_key":"0413ba620b967684449ee789ee6fd31ad78c4d51d8bfea1721b88eda46aa1b83","metric":"pass_rate","protocol_fingerprint":"ab2b50a51a7818bbcaaedec6c3938b8bf10420b53b14504628ccaab3ab74cf60","run_fingerprint":"3bf17f6d187c5882f71ac8a6271a6fc02b50c13582fff77c13a7f6d1e9e22809","score":82.2,"score_display":"82.2","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T16:46:28.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"584cc225fd4684ac6f91fcbaa95c681ca07df1ec1765e0b440a56781c6576830","measurement_key":"4e23c2e78e568347c18547c17709bb5349a9e97e38c0433e720e9e9cac4739f3","metric":"mean_score","protocol_fingerprint":"c340eaa940cfc8d678f19af1207e8939a829e75a57551a135896eb037dd7b385","run_fingerprint":"50dd3fec98e79d70524564314acaea22d2b5ce4701aa433b3908b1f7f28273fa","score":65.55555555555556,"score_display":"65.6","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1265f4a911420a92004ade350120b568271069f00b09e6e430573e873572762e","measurement_key":"25f30a34849749bbe8569760486909da49f5c9c6e65c701f60e900ace6e4b24d","metric":"accuracy","protocol_fingerprint":"854d656fd3e12bfacdce72437f31b0d01fd553ac2e0a5e999e664334be5d0d96","run_fingerprint":"9afe67485f8eac7e03485304475c55d3bcc960506514cf2933ef79b68c59029d","score":89.585,"score_display":"89.6","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1edc74a3fd36a088835ece6cacdc346d7581d5c06dc419b46055175dfae950c3","measurement_key":"26921e0523f0a7b655636d6392b821117258a40c89615da89384715c361c289a","metric":"accuracy","protocol_fingerprint":"d91ce15eb909f431a19992cb09c1aca45a1aa8bb3c776f678f7b31376fc676ef","run_fingerprint":"6fc3d2bbd3d56f55222eb327222bba3524488619796ee800898f6ea397641406","score":86.59,"score_display":"86.6","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"osworld-2":{"benchmark_release_id":"release_15c5525fe39f33bc181dfb69","benchmark_version":"OSWorld 2.0 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:06Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e1c4905ec5b87860e17d024ff42801501661ce08dd8e4506cdc521a663770e1b","measurement_key":"0f8dd0de46ca91a9136c452d9a46be3bf2aba4998ddea4dbaada451aef180a8f","metric":"binary_accuracy","protocol_fingerprint":"3f78a90e46b6e5d1e3b3d6dac19d9b6b42d15334f71d453e4d086ee22bb1f582","run_fingerprint":"1f8bb98d0560eca1726e0f795c50e7abf586cb96d867aec962499e8f768eb6a2","score":20.6,"score_display":"20.6","source":{"id":"epoch-osworld-2","name":"Epoch AI mirror · OSWorld 2.0","url":"https://epoch.ai/benchmarks/osworld-2"},"source_authority_tier":"B","split_or_window":"binary-accuracy-500-step-budget","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":146,"at":"2026-06-07T23:44:54.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"174463ad9672032b5f31c59d9d2e7a35b92c14b204623de7cb6360b6c4602abd","measurement_key":"152b9c20ee8c5d6f06c51957ecf6bfab6892571baeeb3f553e124e8a57145cfb","metric":"mean_score","protocol_fingerprint":"3363252c17a2fc64205757514a0be605af0eedfdaae23c490b34e31ca4327790","run_fingerprint":"8e853413198d547a958f7b19848455cb9a100abe30a078242496951c835aea32","score":98.33333333333333,"score_display":"98.3","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9de7c361a04b16754281e782eeaea14055e1a1d2428c05ed30227d5bb8d67a72","measurement_key":"e5c24bad2774dd05b776ed6f72f45acc56253ead067fdd652542ffc8cf2f4dc2","metric":"fully_resolved_rate","protocol_fingerprint":"e69dd949165c1c0d6908f5c40d22d7980598c03636851a95c34a00001aca7885","run_fingerprint":"4fbf34477f4ba03f9567d031f27232df00fde9914e3f776b56508ee702f21215","score":1.0,"score_display":"1.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:47:54Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d12bcfabd882e907c7f02ad464e5cc20ad3feb142c43b1139de6174277dc61d9","measurement_key":"774faa417c97e125a56114b304bbb5fc8b95c069677e90235e1d00221192d7df","metric":"subproblem_accuracy","protocol_fingerprint":"7fbb68e2e35d45d01ecc52548723a571e74566f1f545239950b3e54ac27baf7c","run_fingerprint":"d860d3ec9e8698becc4e4fc17ce36713c1ad5f910ede779a81110ceecb98708c","score":53.4722222222222,"score_display":"53.5","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0597d1256ac942b4d5e3d6a3e649b2d08ad29835101c1c7d0aaa23a2c84aa15d","measurement_key":"a9d33666fed7758c1f24edcbcf06e79c97ec3f141ce77f9eb809050e1c00bfb4","metric":"accuracy_avg_at_5","protocol_fingerprint":"b04a4db496b6f73099c0c613de0dc31bbeac6138402dfe202360cdaa95e7907f","run_fingerprint":"3e2237ce4ca28649a34b3d7318591fd60cc2baca23c069f273c4eae828470997","score":64.8,"score_display":"64.8","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c95142f46157a2f984bb1f9f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:27:24.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fcdf130f65dbfe4804ddbe94114d561e3184312563d22b1d716492a37a1dc44d","measurement_key":"ca5eac673f6d5c4d3da82f0bbf5b7133283d20c2b2c4a9749193f9512a8065f9","metric":"accuracy","protocol_fingerprint":"8048e6f0aa21e53a5260b9c83d5b08a693fa97069d9c4dc25a37482175a1a6c8","run_fingerprint":"1d93287d2a8d4ea0a3bd161f60b9f2fc77d8345f4f0592f84fb902a30f8db5e2","score":53.0,"score_display":"53.0","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"skillsbench":{"benchmark_release_id":"release_093b45b8b752b3f08534f6ee","benchmark_version":"v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":138,"at":"2026-06-16","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"967d0832a5742ff76f01e9f8f0cbc3a53196921113e7f79e147b0bc88db41749","measurement_key":"22a426af986a4be328f3b9abad9123d3c655b521564fd891249ed492802596ec","metric":"pass_rate","protocol_fingerprint":"c2ed2025e534826e5e627446f4493a128269710491b35eb2122abbaf19d56304","run_fingerprint":"b2d7a9c072e3c4e8048aa076970fc9face7a6bc18ddb0b75b2ac35eb8d095281","score":54.1,"score_display":"54.1","source":{"id":"skillsbench","name":"SkillsBench v1.1","url":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json"},"source_authority_tier":"A","split_or_window":"official-87-tasks-with-skills","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_63ff087821172cc7e101cfa5","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"swe-bench-live":{"benchmark_release_id":"release_9d2de9d5be7e9822af19f7b3","benchmark_version":"SWE-bench-Live Lite","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":53,"at":"2026-09-09","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bb0c285d91c12d6a1a2964b3ed76a42128fa8d4b153eba05607076b800c1540a","measurement_key":"5218d093b048e4029a3781d33f5f92d7a98a6e51096da8b477a25f71ac7e5513","metric":"resolved_rate","protocol_fingerprint":"fbdc90daa6cf4b367e872ee26db4a4f860d827ec2230943616878e70af968b92","run_fingerprint":"ac608d2eab915d6c9cdb6879bbf08841602bbdb151cf143585908aac24b424b4","score":34.0,"score_display":"34.0","source":{"id":"swe-bench-live","name":"SWE-bench-Live · Lite","url":"https://swe-bench-live.github.io/reports-0605.jsonl"},"source_authority_tier":"A","split_or_window":"lite-300-python","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_576644939af96eac30f5bf8d","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":157,"at":"2026-05-28","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"076cacf0eb09b44a9123b7c22dd131949bc6d3cf4de250bb105c3673ef1afbe6","measurement_key":"5e45b8c920acf7144a6befd89e09f06e0ff2357b00887b7d0d0262f1f502d6ad","metric":"resolved_rate","protocol_fingerprint":"25947717f47e88fe72a2835cffd7b891c770f077725801a16e67c7e2ae03c81c","run_fingerprint":"e365cd1cdd8537e801d36c5b63c385e96ae7b7158302e6a1813b5f2594e58993","score":88.6,"score_display":"88.6","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":{"benchmark_release_id":"release_ed49ef6cb40ad079db5a0835","benchmark_version":"Anthropic 500-task evaluation","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":157,"at":"2026-05-28","last_confirmed_at":"2026-11-01T07:28:19Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cbc07f569eb3f7143cde51046cc7e78d82215c236d67f819c129b8d91abc99f4","measurement_key":"d34e50dee537f5c3599f6747735fd0ca2d11a1455ece340533e43f0684e83bb4","metric":"resolved_rate","protocol_fingerprint":"f595922acd4f9772f570b876988ce1fa827612d9ebb2792b02bdbe22633c821e","reporting_origin":"provider","run_fingerprint":"7044fc5eba1587c26bcc502552c0c09fc67d2ffe9d4a806f4865efb4ac9f2e1c","score":88.6,"score_display":"88.6","source":{"id":"anthropic-opus-4-8-hle","name":"Anthropic · Claude Opus 4.8 System Card","url":"https://www-cdn.anthropic.com/0f0c97ad20d8005706296bd92aa1c27c6b2f4f61/Claude%20Opus%204.8%20System%20Card.pdf"},"source_authority_tier":"B","split_or_window":"verified-500","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_0dc76ca4c859b3a6a92b7b6a","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":157,"at":"2026-05-28","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"076cacf0eb09b44a9123b7c22dd131949bc6d3cf4de250bb105c3673ef1afbe6","measurement_key":"5e45b8c920acf7144a6befd89e09f06e0ff2357b00887b7d0d0262f1f502d6ad","metric":"resolved_rate","protocol_fingerprint":"25947717f47e88fe72a2835cffd7b891c770f077725801a16e67c7e2ae03c81c","reporting_origin":"organizer","run_fingerprint":"e365cd1cdd8537e801d36c5b63c385e96ae7b7158302e6a1813b5f2594e58993","score":88.6,"score_display":"88.6","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_72d764965dd7baf34f983249","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":62,"at":"2026-08-30T11:02:42Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dd2c952d23d70dae7e0d09e246c2bf130c357575d42d7ed66a994a59323c60f1","measurement_key":"01ee0e8631e379582def46cc2e5d671fd103bd0e91231d283dd53a10284a9ded","metric":"resolved_rate","protocol_fingerprint":"7645eeaa8bc0d9f452dcbd478ae9fc099df4ca50dd375c7cc8a3963a612ee618","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-03-01/2026-05-15":{"benchmark_release_id":"release_72d764965dd7baf34f983249","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":62,"at":"2026-08-30T11:02:42Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dd2c952d23d70dae7e0d09e246c2bf130c357575d42d7ed66a994a59323c60f1","measurement_key":"01ee0e8631e379582def46cc2e5d671fd103bd0e91231d283dd53a10284a9ded","metric":"resolved_rate","protocol_fingerprint":"7645eeaa8bc0d9f452dcbd478ae9fc099df4ca50dd375c7cc8a3963a612ee618","run_fingerprint":"365f38b1eba285d4751b16405bf0980756ac038a22f444a4db94202c26c59ab4","score":56.545454545454554,"score_display":"56.55","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-03-01/2026-05-15","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_576644939af96eac30f5bf8d","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"}}},"run_fingerprint":"365f38b1eba285d4751b16405bf0980756ac038a22f444a4db94202c26c59ab4","score":56.545454545454554,"score_display":"56.55","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-03-01/2026-05-15","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_576644939af96eac30f5bf8d","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":101,"at":"2026-07-23","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"557ae3b97c9c7457b034d32b336317bfd8d10b9dc8c9fbc55753a44925156c22","measurement_key":"0f2599df97f911b00c7fb1e1725a860f3b81584c6d7955b8cf7b8c0cb2eb1136","metric":"pass_1","protocol_fingerprint":"88e9ba377425eca2d26ca6bb75fce7b15a85a4bada5fe73001024ea97041a534","run_fingerprint":"29d3083f87533eb903cd2ae19e9fab477b18d93d30dbdaf0a2b7e5c8d49595b2","score":39.69072164948454,"score_display":"39.7","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6f01914f4b4532522b4fd3c491db69c13b9427b077d27b32b9ae09afd5deaba0","measurement_key":"27684ef545a8883685963a586f8e93babd40e0c5589dc494ae56d34fe0121af3","metric":"accuracy","protocol_fingerprint":"e5c26a91bc4de32b3edfa3a48708711fbb61b5e75399afc197e3c51a243b8020","run_fingerprint":"3b654ebcf8acc03ce0bb4d8a10b6715bed6742f3627c91b273a3e9d35e01d447","score":71.91,"score_display":"71.9","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-3":{"benchmark_release_id":"release_ceb36f25882d8cea2c9d084a","benchmark_version":"3.0 · b936386b-4afd-4ad7-aa7f-6b52bcab9853","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":80,"at":"2026-08-12T21:39:34.661007+00:00","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"687e9341980bd7dc7c3fb4b77dd726c93c64312a30a806f3b4271c74369b08aa","measurement_key":"13aea9d81ab0f395aedbddc0ad74ab24456aa3d6cf8f0d65d8f124a59ca24af1","metric":"accuracy","protocol_fingerprint":"88160db45de7ebcb4aa5f678c797f77980ae783f5fe91a0902414c7a82885016","run_fingerprint":"523813b6acb7d59ae02893f63a8cb297f306a5666fb62934eade13ca89100122","score":21.08,"score_display":"21.08","source":{"id":"terminal-bench-3","name":"Terminal-Bench 3.0","url":"https://ofhuhcpkvzjlejydnvyd.supabase.co/functions/v1/leaderboard-read"},"source_authority_tier":"A+","split_or_window":"official-74-task-leaderboard","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"be2682bc268df5801681287ff800a37fb389f8c742981033e2e97cd43da63e95","measurement_key":"5b876eb7e3ed3013e505474ecc35829ff806fe8dcc2d13957e2cf8f5bb19a7af","metric":"accuracy","protocol_fingerprint":"30cbc98f901ff15467520437bc3cf91d0b16481537f4a2d26940681f7d7f2756","run_fingerprint":"6776ab7f08e3f577fa5b97d73d171aa3785ff3c989f9455c60ca90328e40be59","score":23.232,"score_display":"23.2","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5a038187f3436b72b8687a4ccd2646e94a883fa3e64e2cb51ea9aeeca79480dd","measurement_key":"cd2e2c037fe45b30e78a763a3e7f0a5a647356a6bbf9e4fab1d8ba123d4b43ce","metric":"accuracy","protocol_fingerprint":"575a6455222e836ab6aa781653d058f696cbe35556cd834d0beff1868bff9a79","run_fingerprint":"20ac6cef8372c2247e5559da51efd82f253f35c58b0904246ae9cec370cadd5c","score":4.286,"score_display":"4.3","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"57ea11f4c2545983ab7ebbedcf108c3839dc3937c737fbf74e6a5b51a4911995","measurement_key":"8442412db4689ba6ec1d799d25bc0de00fa2c5eaeed3f5d15db6bb911e2e0a11","metric":"mean_final_balance_usd","protocol_fingerprint":"c425bb83180b8a8f09c0a10f808a35acd64e6fafd4b7a0c98900a56b812fe5f8","run_fingerprint":"a59dcc68fef1e04939e7947d7e72b68c3b431673c9a74a3c065c75c0a2529edd","score":2992.344,"score_display":"2992.34","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":157,"at":"2026-05-28","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"56b8b87bbab31e3cbd3fcdf78218386dbd8975b43d8001cfab1b14faf3d10bca","measurement_key":"a2a43d6d5900c88194a464a25c20804049347cb7c2d6a424b6c195fd98a52f44","metric":"score","protocol_fingerprint":"2964986b13c320c9b670a439f7c5e105bd709a89ae2ce5638b1afb5ee977b415","run_fingerprint":"fff7833d3d35cae67882b1ba189089567275d2950c4a1b3160428a2841881f06","score":82.725,"score_display":"82.7","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5ce4eaa381ad965656436579","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a349b460cd9a2b0de8c1c2556184a4d00bd4f2afcd181a2257f0e68b68de3b7f","measurement_key":"6d27e5252b363cdb79551157d2e14b126c804bdec9af0401b83b100a37987e13","metric":"arena_score","protocol_fingerprint":"9c7124e258e9e5a9a057179259a0297da1455623e3baf5981da9cf83a005a98f","run_fingerprint":"dd72e52649bad0e0a733c55fc0f0aa64f350d72d590c688f21e87e7584010451","score":1555.8263524171814,"score_display":"1556","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_3ff20fb03ea5572c13bd7021","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"51aea1564ae15894b61f40d1011721701c329213be94dfcb63704b339a749d95","measurement_key":"78f7c0edf3fc5c3e0da6bac3ec567927737c1d4146d68829128c6e1c6c3b7e5f","metric":"accuracy","protocol_fingerprint":"016047521c58591a431809a45a440c6aeeadd415123b67fb28607bcac62c78a6","run_fingerprint":"026673e30e070f8fa93b58716d749c1113c32c5318d46b32b6d0d225d4a5523d","score":82.89,"score_display":"82.9","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_576644939af96eac30f5bf8d","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"anthropic/claude-opus-4-8","model_name":"Claude Opus 4.8","parameter_count_active":null,"parameter_count_total":null,"provider":"Anthropic","selection_rank":17,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dbc13fd2569631e5eddad7bf9bfba8018cf20a5adc3d746a7d835507be8b5bc2","measurement_key":"39a4a84fc860c570bc676fb87307c1468f27e093c4e3b82bbcc3d45ecc4e2475","metric":"performance_rating","protocol_fingerprint":"97b8488dc2ad8f8c25dd8467ee04388186fbce1e627f2e51de5c4985a0e11454","run_fingerprint":"84377ef373b77b08f369b3476e99762191c9cad200a0e30a4621133eea97ab97","score":1942.97,"score_display":"1942.97","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1d90a4f78b0883f8ca734606748753df5ef7308c1d41ecb25a4688ca7d6e4635","measurement_key":"bb1fe0384579109f19dc1060af7a3699f3bdb8afdab06451ac52b0793965c2cf","metric":"pass_at_1","protocol_fingerprint":"8f571d2f323b02e5358050aff91cbe030cc6ad0e6d26fdcdb64f120bf9ee8286","run_fingerprint":"3059b55ca9032be8fe5527548b7f86644db0864f87a2b12ae144f485bc44ff18","score":55.1,"score_display":"55.1","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_aa4c4f569e5bcfdacbdd9f30","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"64ccd242705195495c396c4d31d52e265faa781386828d62cb95fd05f7388ad2","measurement_key":"76f0de5216cb7c5d7070d632447ec4629755ec2f01947c593c90faf6028572e7","metric":"pass_at_2_accuracy","protocol_fingerprint":"b27c8f16f8fbb9f7481f43ff962202ec8ac65abac8edd3ddaa974eacb7d78b33","run_fingerprint":"5348b53e2e5d87b02e5a5126ed324cc210380c0e423b5dd6e50b5f9dbaaab255","score":95.0,"score_display":"95.0","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"00054b16f49484c2e7713f4ad9445be0bb6241fc3c0169cd9ca9e64ef2696038","measurement_key":"a9a007ad51b8fd8d84844babbebf1a7e46962a0c80baa9ce550d6e0136a8e147","metric":"accuracy","protocol_fingerprint":"a0cfcd82b3d8405c11033eeb7ea6d86ff25e74d6a78b9934a39c06f28c60095d","run_fingerprint":"067edc451b46b76f5953b715749839474d8cb2d750549244a1484a8fc09a1268","score":85.0,"score_display":"85","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6c37268daf6f92a902ca7d67c0f189612946c2c75b830d83a1b993a9d1e31144","measurement_key":"1d29ebe4f699199b0346f42e62fcc295a628f3a8155c6149050e6fe6df7a98ef","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"efbbd463b8eb0f704dcb1e1b41ffef3d0413121c17e3b05eea6e2c5286141bb7","score":1481.6951264151023,"score_display":"1482","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_de975f255b440d53e37ca312","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:54:48.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"343965f05ed05fd3e08277894113adf075a51bde4c90da0d878dd0d4c283e0ea","measurement_key":"05b59550b89aa4dd35537f94911eee1e1db37f678f4a8792233285f2046f239c","metric":"mean_score","protocol_fingerprint":"45b80790144bcf6294b80433581db10dbdb1c44a8fc359e009b98128f2eddd04","run_fingerprint":"466379ffbdf4bbd523f767f8a86d452d561fde036b1b413cca763efef3ea5016","score":63.0,"score_display":"63.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dd6c03e533654c2eeeefa45748157c021d492ff7bc9f82f09e18f6e587465383","measurement_key":"308ff2da8c6595af7d1d403e0f60de0bc465657381e7968e0fc79aa671e159a8","metric":"accuracy","protocol_fingerprint":"2896f47b263fbfd9d897702a037ae9dcf10431a99edf1fcf4e0b542f78ace5bb","run_fingerprint":"bbc78cbc55a6f9c9ab680114b91a6643cddc1d1f0d4beb22a4c2cb34cc992ea8","score":27.142857142857103,"score_display":"27.1","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"32108dd002643a3c9c30777a8eb915c0a26e03f5f99d42aa1d69ff8d7d2ee499","measurement_key":"900c8eef74f3c229d5e113e1e52284eb16522d98209be3d80286d42fde21b2a3","metric":"pass_at_1","protocol_fingerprint":"e069c3df0375db8dacb24d43ec010322abc67897fa4350149d14ef096dc0b9fb","run_fingerprint":"68bdb8de629175dcfb2b193eacf397c5377ec172d2bd6730a1ae37f8c3e9fd6f","score":67.03539823008849,"score_display":"67.0","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"423ecc509b686c2c424a5e62ab6b2606486988cd0cba20ab6739c3405957362f","measurement_key":"3e833020d78b01eb6d12527ed998f776deb85055239d2013c61ae19b6b915361","metric":"eci","protocol_fingerprint":"60543c8e4496caff05af549fe069ab57d64806a3d2d840525d802b2d3ba5d2df","run_fingerprint":"b5bccd87b2ca7bab5cf41f1008e82b664e6610df96c38d196cceae7130640346","score":159.38,"score_display":"159.38","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fc1802c65e18256a1d9ae18b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6c3866e695389e6c979ca1944098d606ac5654a1ed5f093de33bce6e413369b1","measurement_key":"924d72a24c6c358b4c0f154a70701d74e768e4304ec2ff1af55e0fac710f562d","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"a5eefc6dd41a3da732d191b44e47210b280e822c872fabb8a4c49fdbb88b3e20","run_fingerprint":"99d132628daec23d21188fe1a79c9655cb69fab625ec1394e03fd3e309dab5db","score":42.96,"score_display":"43.0","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":142,"at":"2026-06-11T17:47:36.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"692afc5427b97b84ca3a3706e6c025568f094d4b939c5573e8e115c9a8421292","measurement_key":"2b7ac7190ba034cddede2c5230e70a6b9b633055ad498e44463162b9c740d57d","metric":"mean_score","protocol_fingerprint":"8cf0f33d75899c3ad5c42caaddf510069e92d52e9361c57eb73579d380f1126f","run_fingerprint":"a684bfd9dd78ed15936162cb91dab523970e070dc6227af7a336d3b82a61dd90","score":85.26315789473684,"score_display":"85.3","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":142,"at":"2026-06-11T17:47:36.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"39aa59a0c81d86b6326b8153ecb1280a9d700266fb593688aaa0adb10750b461","measurement_key":"6f7fcac555ea3c83428fb68b98c5f6e40392408105def37f145b5a1a2fb0400d","metric":"mean_score","protocol_fingerprint":"c6fe6d4b6009dd1d72f17d21a085b69ed2db4cd517d5f245cf16da2b7779c620","run_fingerprint":"5ed4709c602f1eab2d833fcfb8449250e151d2431986a420be1145514517d559","score":72.5,"score_display":"72.5","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fba02100adf0dc88df150bf963b5f736a3d39fc6bc32ea15466c814f459a2d0d","measurement_key":"d4b92c773da88668b7edbeb7fa528c78f1dd28fa64c539d7a43889f54c384578","metric":"elo","protocol_fingerprint":"3299e6f51d4d3a157382e1afab88327c84b1da7d239dc86c20e50a38d82fc291","run_fingerprint":"65f65ee31ea8aa2145255fb8787277aa910fed3c1c18cdbeaaa0eb3601e57219","score":1359.24,"score_display":"1359","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2422dc45bb8a8891c6df2dc782716af9046fcc726380512782e62ea8b11d8904","measurement_key":"2c2b2e604e18e4244426d115229961040ec8d8c03552acec4cb3661edcdeedac","metric":"accuracy","protocol_fingerprint":"0a5a76ac836c61bbf12c72c83694da49d5bac3d1cd626349cabb8bcf1a1956e2","run_fingerprint":"ebf0a4bb76d7ff5cd8c4f3fc8e90ebcb2c5f42803116e605270c16837708141e","score":93.182,"score_display":"93.18","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gso":{"benchmark_release_id":"release_176f07ea4e9e0b8dfeede990","benchmark_version":"GSO current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":188,"at":"2026-04-27","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"1c680b93356f552915b185d8ee39771fd3c5a2717a87648275ecf30d9c59fa42","measurement_key":"94c0877062c8bf80fa5caac447c5bc9ea6b6e96fea875718de591d4c9d5bcf94","metric":"opt_at_1","protocol_fingerprint":"415724002e0b1b17ef3d982a693cab73330cdb784e569fd3c433322353fe9600","run_fingerprint":"0286d54442ea6771b6a1f6f81859eefb63f3f31562c3ec6818f3d615b21c18a7","score":40.2,"score_display":"40.2","source":{"id":"epoch-gso","name":"Epoch AI mirror · GSO","url":"https://epoch.ai/benchmarks/gso"},"source_authority_tier":"B","split_or_window":"official-set-opt-at-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"hle":{"benchmark_release_id":"release_5f3023448c2ae4632fe1a43b","benchmark_version":"reported-runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":192,"at":"2026-04-23","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"da050b7724b533a9c6096f7683fd23357b538b34e9c9028bfa60b7b55a8f4182","measurement_key":"2cc382b2f4f8aa2930552d0187efbca3682f5651c23970ea01abbfb3be49d5a9","metric":"accuracy","protocol_fingerprint":"5ff7843b5cc0b28f60ea81140d0fc83e0c7b0fb1123ff61449f0cf6367932ab9","run_fingerprint":"c4d00fa87778d3503e0da375a8106b8ec51aca1d5d26784025c8444e5f851cdf","score":43.56,"score_display":"43.56","source":{"id":"evals-report-hle","name":"evals.report · Humanity's Last Exam","url":"https://evals.report/benchmarks/humanitys-last-exam?tab=scores"},"source_authority_tier":"B","split_or_window":"public-multimodal-mixed-run-configs","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ad9dd60f09831d08eff03512","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"evals-report-official","verified_status":"evals-report-official"},"unit":"percent","verification_status":"evals-report-official"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7fd6de2eff0817a6fb4f0ebf69039acb9535666a64c43310c5f09d18e7c90749","measurement_key":"60ae6f2a1c815f6fe8ba51bffd99c64bc1d3ce967b00d54214147f727c77d00c","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"14b1744ee94213256cb5ee5bc5bff2f87eef9c606d78696cba601e3732472235","score":80.18829761904762,"score_display":"80.19","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"73a3d39920ef6ff7722b4c18544cf7a904d2ebaabd344e221e0b0c0cdfca490d","measurement_key":"a3a89df6ec140c0297817f8272d876206aea76d87bda21d805068272cca40d01","metric":"pass_at_1","protocol_fingerprint":"3ef8da044c80b96e16dcae6982010b875e7f41534bcfce38f361590726c3ebf8","run_fingerprint":"a21764ca036a91fe9508746db8f3b58ba3a9abf5e60f0e2051c3043cf4ed7b58","score":85.296,"score_display":"85.3","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":186,"at":"2026-04-28T17:25:29Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"eef8ab9dad2deb5fb8a57ed4ede83570d50e8e7511793c7f55d9891f2bbf2f7e","measurement_key":"18fc80347dc6327f528b1cd0f4fadf4e41dca61a438db5dd2c2efb43be9efd36","metric":"pass_rate","protocol_fingerprint":"b9dc111fccb5176c2d10811df78c44224252d72151c411cdc304d0d0fa5724d0","run_fingerprint":"460d8d52e368a5325aa2fbe70459d9b164de5bfb23f6862e7920b8c235da439c","score":75.3,"score_display":"75.3","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":82,"at":"2026-08-10T16:12:45.865Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f9408ebdbee4d9bc42392d14f2318c5b5d1435e7e92ab634aa5de9f1d0944da7","measurement_key":"d48311643fd83c1161b726581b9c0b0f7da2714c2d2402fbc137c189c27922a2","metric":"mean_score","protocol_fingerprint":"c2bfd88c9a14d237e938d328530687bf8542ca96d58446303b33571e8d999098","run_fingerprint":"532e537e41d425835f299423de3f30f4b8ef4d1ff28d1e152366a3f47a38db91","score":10.0,"score_display":"10.0","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_de975f255b440d53e37ca312","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c2d86f72d482f58a8d60de7323d37ffa8bc95cc4e566377581d07545dc836851","measurement_key":"49486180e0a553c0d69be8e3281e3f55a05b64c5533d0282dcbe9d803d8fde61","metric":"accuracy","protocol_fingerprint":"848266c1ca6001832b12dd64dabf16f5201cc770100b33e270810df234fa69dd","run_fingerprint":"19c761715de3c79bc4d0f018115ed14bd32a079c58acc9fcfb0b46dddced4698","score":88.144,"score_display":"88.1","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:41Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e33b664c7254aa78db5d782837358b6b06c4d232261575777ef0a87245635122","measurement_key":"9d0cc563237af61c10b825a4eb625cf5bd159e1337a73da3b814360a2fa39e8a","metric":"accuracy","protocol_fingerprint":"9211b7d5da0a6e6460b558fa72f27c3746d39f195003bca66df5041bd41af7e0","run_fingerprint":"8932693ae8b5decf3b87081d435e09e1cab6b6de2d42b6b05b14deadd7d3ae8c","score":88.266,"score_display":"88.3","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"osworld-2":{"benchmark_release_id":"release_15c5525fe39f33bc181dfb69","benchmark_version":"OSWorld 2.0 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:06Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"12f26363df699d6dcd603249a996579b3b96146e7ded563d2252f58b61d24ba2","measurement_key":"98de837938e78d807c5d9b7f56387d40930ee2fb9984e20944fa79b361f1f2bb","metric":"binary_accuracy","protocol_fingerprint":"a35a7e4f1f52502187e775bbdee0cee04878e831ca9612df4ba9c8ae53cebafb","run_fingerprint":"8ad273c5f514f7ce2d652632e6d6a0cd8c003142afc8f277c56908a51d76a495","score":13.0,"score_display":"13.0","source":{"id":"epoch-osworld-2","name":"Epoch AI mirror · OSWorld 2.0","url":"https://epoch.ai/benchmarks/osworld-2"},"source_authority_tier":"B","split_or_window":"binary-accuracy-500-step-budget","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":190,"at":"2026-04-24T14:06:46.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"1855f1e78449892d90c30ce64afd6c27e69817a8f083409c65d61ad52e46c3f1","measurement_key":"f450a1da1a3f4175316021caf5dc91a9cbcf7b53d961904d538d0584e8b27ae6","metric":"mean_score","protocol_fingerprint":"f9d40076f0612e117e2b174313bd5a5f12bc67638455177ea0b9c021cc0b25ca","run_fingerprint":"d90f993449dbd204972351c6ca14b2d1d997df4ecffb30569dc841a27d1cc075","score":100.0,"score_display":"100.0","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"231b34863da52d4808a7ff2a2d589c66f0a5a83d9e9eed712422301c0a0f4d5d","measurement_key":"480928d4e51e4a91ab8066fcd29067048bb4c0d53669a8d43012a890990b1dba","metric":"fully_resolved_rate","protocol_fingerprint":"39c92ccb09d945d8aeec1e6ca91c474b55b831598548aa9a54147a1fb16b09da","run_fingerprint":"dfefc84ab8fd5fb08ed36c3189cec7a00d1cb2e580854c36b0df6b8e2743acb7","score":0.5,"score_display":"0.5","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7c29a74fd429f966947da3f65f05fef3500d7092d7b0b14fcb5e2db8c46c01bc","measurement_key":"f6447347a0f02eaec12d21b9a1b95f1a64551e411a8a68b4a611485b95a78e1f","metric":"subproblem_accuracy","protocol_fingerprint":"8588bbaea14ab90214d1b45223b1951a7c2fdeb5d5fc191a273e7ac539a17630","run_fingerprint":"28d3484f01ea7005d1d89773944b8d056e02f076f72d06982484aa781ee1ce5e","score":55.787037037037,"score_display":"55.8","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c5a437756643faac22270ddeff572f0880647c8ff8d562c9be341b85e9de4815","measurement_key":"24264f4ada92386e1dfc85b5f98599e6b20c325e8223170905f18484bd9e5aa6","metric":"accuracy_avg_at_5","protocol_fingerprint":"24ae4b1c43dd9aa74ec0e566041f1e4cd39e0181e5c0b9bf014e1d881e750941","run_fingerprint":"7809a4f77d0214dfe239ccb115abdce8f8acad87ccbb5306b8b2db63241b01b9","score":69.0,"score_display":"69.0","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_cfd072d0392af1ffbd5bf34e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:28:25.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7d099026f8b76e3d374df73a959e62cf580a0af7e6b53152c7e8f10b00ee2368","measurement_key":"e146a96059075f4ffe46f34c34cd234e4799a414fdcae421c598fdc8cad62f62","metric":"accuracy","protocol_fingerprint":"d23a2d7fa0743d0208611541cc6748e0c323c4e88079d09b9ec90ad86c184457","run_fingerprint":"fdf0377c8ac0d9d9f760c418ff6e68fe6635fb46718db32a5f3beba5b2b11619","score":63.0,"score_display":"63.0","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"skillsbench":{"benchmark_release_id":"release_093b45b8b752b3f08534f6ee","benchmark_version":"v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":138,"at":"2026-06-16","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2707b6e576b5cac0a3c6580eebf526a0cd6c1e21b70b1cd7f492d2cae500eec3","measurement_key":"88e1d4a11b10267cb0a52a5bc325ea52f4b0add201437fc1f1fb5966449c67b2","metric":"pass_rate","protocol_fingerprint":"c2ed2025e534826e5e627446f4493a128269710491b35eb2122abbaf19d56304","run_fingerprint":"481eb250f485c83e56664ebebd379a05f19f8fff08010639e58cd7b4680ab523","score":67.3,"score_display":"67.3","source":{"id":"skillsbench","name":"SkillsBench v1.1","url":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json"},"source_authority_tier":"A","split_or_window":"official-87-tasks-with-skills","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_815be32a4499e3fe8b5cd1a6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3e824acaa47d9d2df008fa06642c2cde6e183ce7bbbe51e45eb6587c4fe63b45","measurement_key":"41ac852a3e84bd32e9d0ab5f23dfe78fbc2a701a73f11d633cef498164439055","metric":"fully_solved_rate","protocol_fingerprint":"958b9df1a028a831ff40f3e6698200dd9c44511dbb9f3fe055f8302bd3a24de1","run_fingerprint":"a7d5000e9a459427c0edb16ff8f0b7ebee22f0b97974574f38edd9ea0e41ad31","score":3.817,"score_display":"3.8","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-live":{"benchmark_release_id":"release_9d2de9d5be7e9822af19f7b3","benchmark_version":"SWE-bench-Live Lite","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":59,"at":"2026-09-03","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7ceef9410994e0d775461f97769558eb253249c7f40072af7f8afa4adcb30e18","measurement_key":"dc81f867a040c69c37b4070b078077fad82ca4ae182b844437584db3298b2516","metric":"resolved_rate","protocol_fingerprint":"42e01a189064d8fb76dba75d73198590fe5d06830446eda18b634417e755a175","run_fingerprint":"20fcae2aa647ebc4241d94c61a6852bb9fd9fdfd76b230dbb1e2133224d70a0c","score":62.0,"score_display":"62.0","source":{"id":"swe-bench-live","name":"SWE-bench-Live · Lite","url":"https://swe-bench-live.github.io/reports-0605.jsonl"},"source_authority_tier":"A","split_or_window":"lite-300-python","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_f669e0173f71ff9f02fbaf9b","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":192,"at":"2026-04-23","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"360705a1d60be26d5d338d011c71eaa8df38f790ac464733880cfe075e66239f","measurement_key":"e4157a1685f2ca836a0da994f853fac1bf32ee97e156ece2321cacfe00e4c1af","metric":"resolved_rate","protocol_fingerprint":"d02112e899255831d29b3648680d2ac85b6c3715e3cdea5cfebabca486d41b89","run_fingerprint":"3b1fb66d029a94b2c16a465f87bd85ab344db188ced7376c7d88b9e57fd09c85","score":82.6,"score_display":"82.6","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":192,"at":"2026-04-23","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"360705a1d60be26d5d338d011c71eaa8df38f790ac464733880cfe075e66239f","measurement_key":"e4157a1685f2ca836a0da994f853fac1bf32ee97e156ece2321cacfe00e4c1af","metric":"resolved_rate","protocol_fingerprint":"d02112e899255831d29b3648680d2ac85b6c3715e3cdea5cfebabca486d41b89","reporting_origin":"organizer","run_fingerprint":"3b1fb66d029a94b2c16a465f87bd85ab344db188ced7376c7d88b9e57fd09c85","score":82.6,"score_display":"82.6","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_332cbf0e979daa9e173de9f4","benchmark_version":"rolling-v2","comparison_lane":"supplemental-post-release-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1229e757891d9bd44cf119f0014fe026cbe5a5f9f7263f5322e1db34b5a1f022","measurement_key":"b2018b05458bbcd7f9704b0b0aedb5bc39a28ffc28bb4e31f86ae43f84923481","metric":"resolved_rate","protocol_fingerprint":"3d78907a601d1c50e69137936fb47907e786d140299fb0d62926c34f04f6ad6c","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-03-01/2026-05-15":{"benchmark_release_id":"release_72d764965dd7baf34f983249","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fbe6ef96a5ee8be066f55f230b45f6fbb08722983c6db8b30c64e0fe72e2dba0","measurement_key":"dc7bec806a0c883638dfd8db72f53e2c054dc5ca5edd50ae04d9626b96d5d87d","metric":"resolved_rate","protocol_fingerprint":"5267691d46803160619bd91fb115fd7ea2abc4cbd70ba9f1ea118dfb15775d23","run_fingerprint":"6430dd29962d77bb8d3a627bccc3e7734d33d0599830debfc533220453bf8375","score":62.72727272727272,"score_display":"62.73","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-03-01/2026-05-15","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"},"2026-05-01/2026-05-15":{"benchmark_release_id":"release_332cbf0e979daa9e173de9f4","benchmark_version":"rolling-v2","comparison_lane":"supplemental-post-release-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1229e757891d9bd44cf119f0014fe026cbe5a5f9f7263f5322e1db34b5a1f022","measurement_key":"b2018b05458bbcd7f9704b0b0aedb5bc39a28ffc28bb4e31f86ae43f84923481","metric":"resolved_rate","protocol_fingerprint":"3d78907a601d1c50e69137936fb47907e786d140299fb0d62926c34f04f6ad6c","run_fingerprint":"32b742003ccfcd025e4c3cff0917135cdef008a8f6af4242e8c943873503ae26","score":66.66666666666666,"score_display":"66.67","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-01/2026-05-15","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"32b742003ccfcd025e4c3cff0917135cdef008a8f6af4242e8c943873503ae26","score":66.66666666666666,"score_display":"66.67","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-01/2026-05-15","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":102,"at":"2026-07-22","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fe7cd6d9a44f442e9316ca81652ce89d1c6007e7ba7fe61f3723d7dc87c30e1d","measurement_key":"09fa8736d596592a5fb64e333b824972fdffcb185b4c3bc09732f94aee119cbd","metric":"pass_1","protocol_fingerprint":"ca1b0f52e5f57f2a197d9554fdac27ff8518c746bdb61a2a89fe030c814a6421","run_fingerprint":"6ae289ee0c6ee62514bcac78f01b51628dc7e7c8f0740de4e91366fe242e530d","score":44.58762886597938,"score_display":"44.6","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4059bb7eac40e7cf74ed1f0857a568bfd1f030b34e46dad49cbf2acaf5f4c0ab","measurement_key":"d77c6fdf3692d0d2c58b47ca04b0633b173b88d5956f23c32582232472dc6c21","metric":"accuracy","protocol_fingerprint":"af6c35129307abc2e39650ed53846263d385b5bd893a43db4d57f6a893781c48","run_fingerprint":"78cf8e0ee78432524ab0dd8ea14214bc3e6a4f2715fa58666aa9dcf9c0777c0b","score":76.404,"score_display":"76.4","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_de975f255b440d53e37ca312","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"963fda16709b38b5209238cfa544ae8b95af884b12f7196f30efb69dc1628f46","measurement_key":"f66d150ca27d299d9e16d66bc9ed9bb78f31f446ce4195344abd46400c805a53","metric":"mean_final_balance_usd","protocol_fingerprint":"16dcef846831a895f1270680fca37a67cd20d43510a0e7fceeb421430b42eb58","run_fingerprint":"a1f25a63b5f90ee3582771319dbe06cdebe5fe77f3c2cd799ab6144727ff8c1c","score":7523.843999999999,"score_display":"7523.84","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e2ab7970e7428fde1eca209f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":192,"at":"2026-04-23","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"71f9fe5ad1a0c2ad7444178c5b992fb89ba4633f01736c73cb44d1302c362e69","measurement_key":"3e358d2d97b191bc7d35eed60858cbcb0c25a9cd4fc1cfbf7d4d140e3aa3036d","metric":"score","protocol_fingerprint":"68c749226bb0d2f4ea13cfe8ffe2ec61bce11047a1916876e0ed697ccf9c5edb","run_fingerprint":"ccbaf5ac24cba7f672e8107bc270a9138fffbdef5cb63c4116e0694e42a09284","score":69.847,"score_display":"69.8","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1536af7d406532b7f6def9bd7397118ebf733788d378ef0027e8106fa10fd525","measurement_key":"be457d5c7d119f8b14e134cb681d922f61204bede8279fb47a0a76eaeeb2c50d","metric":"arena_score","protocol_fingerprint":"4b834aee64cad8078b0c63c8c2a6c1d915f39c020dc702e55a5d7df51fc343f3","run_fingerprint":"d2bc88e67f509ad51cd391016a75827a9074e7c1aa7ce3651c8017f7a866ff34","score":1512.099404756151,"score_display":"1512","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b0302da98d4f6fed9067b3c73c059f810e0e9cec172322ef11c4e0c437bf83aa","measurement_key":"acb14ffcd70d33f2fe4e08327a9d94e8563571642112fc79c1e18f7e9d8a7b4e","metric":"accuracy","protocol_fingerprint":"5f1e963ac2dd299059fdcd04c621362c1517cd74eebd1c8b30c33821cdea8047","run_fingerprint":"388d858d86dd99a3cf0aeb3bb4c4cec793fbb5d92a94c42e309df1d38a633b5a","score":84.91,"score_display":"84.9","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_618796ded36fbc2ed30584a4","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"openai/gpt-5-5","model_name":"GPT 5.5","parameter_count_active":null,"parameter_count_total":null,"provider":"OpenAI","selection_rank":18,"weights_status":"closed"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"33df0a073fa8c21c28172b556130da9f8b8e7225480584ec920e421a7854a7b7","measurement_key":"0b825eac54a6267ace1cf2813c1db3f3fae5876ee32e0babe0d667f73fffb4b5","metric":"index_score","protocol_fingerprint":"7c82f2ce14313e9c37348f5f517fa708a15246e06672c9ed62859727e46f7218","run_fingerprint":"9a7349a79738b1a52f9fc2b8c5c3dcc7da8059bb5d1852454f24a731fb71cbbb","score":32.489639,"score_display":"32.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:04Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a8ff0a061a863b3c0d1e951729de4bb8d389c35f2d4f355c59ddde2680b76c1a","measurement_key":"83b38853d86854122350d084d47e3427a634d4ccb1716a5da577e51648eebd36","metric":"performance_rating","protocol_fingerprint":"08fef3acbf0eff28af2e87a090728c27fc19eee807ce11bcf5068011d98d89d0","run_fingerprint":"08478edd08333a32cd0555b8c862a6141cd24439985f9ef70fbd0a9600f2315f","score":1622.0,"score_display":"1622.00","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:02Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bb63f4c2807e64f3e0d66c16b9bc87caea39ba2480b8f94931ccad80de517bbe","measurement_key":"1aa813c2e5be7618003b703117950754fae10146e8f002e30c2bb028cd6ededd","metric":"pass_at_1","protocol_fingerprint":"e33425a8ffc0b19b0e6e238eaf01bf5d3925263dab4b2ea2d87565b486b29226","run_fingerprint":"afc9ee6bbdef2c7a7e8914d48ac8fd08ecaeb581fc5e82c69b7597c359fa9a49","score":69.8,"score_display":"69.8","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:03Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"991c207445e2a747e417f7248386683fd76f95b830e427568e9bcf9e053a937c","measurement_key":"e75b0cda51ff150accb789d7288995a6456d9fac18ea096a56fe09dce5fbb451","metric":"pass_at_2_accuracy","protocol_fingerprint":"c390e152fc5ba816c546d9361d0cc18e63f1f376203c9c100ac914b3606c2f23","run_fingerprint":"b5a191fbde6799f7f5d14b6f700ffcd972788e25aaeca72696da3d96f4c12066","score":93.5,"score_display":"93.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":10,"at":"2026-10-21T22:23:16Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"26bc373603540318270cf38332dcb9bca941f44f00193ec2716b827f0a359b27","measurement_key":"e9e320c9714ae46c40d27d3932d0048b19cfb82e173edb4729741e98e00bdd71","metric":"accuracy","protocol_fingerprint":"53e1415093a166d4dd0cfaa6bba0e34840feb18b462366fedced90269d47296b","run_fingerprint":"81c77fbadacd876a75e2fd78260db02b745e81d8f99c0381655d77d6e3a63dfb","score":78.05555555555556,"score_display":"78","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a57d2e9f7f346277c78493332710b5f26dc59a5616eafab96440302bad2b0202","measurement_key":"8c91c7dfaf3b6dfc8aa8b8fae81719ae95cbe8338d1cbf12ffa6cb2a86bf009c","metric":"ips_score","protocol_fingerprint":"ab294d01dec1bda74524da3e7bca7c06a30db1445d6d21a2f63bc8eaa189a260","run_fingerprint":"295aa6ec06617d78dc1f8d0ddf7a7ddb35ab71319a38112e17f3f694e8a11f48","score":0.026748579776335085,"score_display":"0.0267","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":12,"at":"2026-10-19T22:39:00.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7b5e008e284494132d8eada58016cfd9dc0bc46c1743fd09c0eda9300784f23b","measurement_key":"bb69c01d81fde19d6aa1289fd759a62a0f8e38e95cc59de0f5a67a326ee4f268","metric":"mean_score","protocol_fingerprint":"52e6068ddf31abf8531b046e4f0709763137eadfe121bfac9c15bd189ad1c2e5","run_fingerprint":"13595905a376c6a3112853335317d9134bf6ed5bd28337dba019e67de9d70847","score":46.0,"score_display":"46.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":13,"at":"2026-10-19T04:43:19Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f06928c1316e7b0e692d4bca43c971fb48e25ea618f268729e6c74b72a74ef1d","measurement_key":"ebc0b64f451e214c08340276ba7cdabd44ad71c74ea988f3203b495e9dfa0092","metric":"accuracy","protocol_fingerprint":"e5700bbfa0fccc839832c4b41bc0dface1658207d6ff0a083bde7c68aafb9457","run_fingerprint":"da672aa940290063ef23b77fd3083ee2c01b1badfd425062a644b700c0c49aac","score":24.0,"score_display":"24.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"cursorbench":{"benchmark_release_id":"release_9acebd5b002e9c3f18a30606","benchmark_version":"CursorBench 4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:01Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"63945ed15e41f2c6971613acb391e683fe2640728dfd795f1ddf2ee220be7e81","measurement_key":"df9824363f28d2257e9b77e0c21262bfabd3508b15edc792842bac52dae6211e","metric":"score","protocol_fingerprint":"6c641bc1d76715a3aefa356f3f8396b2fa8451327c856d7292bf3c0b285d0282","run_fingerprint":"b5923d48eab48194bddebef7f147c068fe856a23837c7236eefb6db26777e572","score":47.7,"score_display":"47.7","source":{"id":"epoch-cursorbench","name":"Epoch AI mirror · CursorBench","url":"https://epoch.ai/benchmarks/cursorbench"},"source_authority_tier":"B","split_or_window":"official-current-suite","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f3cbc4bf9ea3c196d71b66ab39bc227f6b8395781db698d825a50c48f7914fdc","measurement_key":"73af198114c8c2ee083d4b5ccb622c1c536e66cab091e9790a832ca54ab9a955","metric":"eci","protocol_fingerprint":"adc56dc177f1e00a3e47615980d8b809bef7e65a79026a6f4318576b63332afb","run_fingerprint":"2c68daa6fcacc38de076e782e56f37f4bdb7d6e2d5c263cf6285ac8bb9f6bd2d","score":158.83,"score_display":"158.83","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2db9ce730bc98e27173d249a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":12,"at":"2026-10-19T22:39:00.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4416743ecbd34b5942afafa8319d387f36cd4f179e4381d5c2dabccd9278576f","measurement_key":"25cd246968418605b1c962a2a7ecce6140c933da045550879ad9c6b9bc9f9a2d","metric":"mean_score","protocol_fingerprint":"3763a53937183b88c672c91b1415e69144f5ab19162000326b0d89e7e4592b97","run_fingerprint":"0ab38c20c2c4d4af6b3a20b4d00c661d7a45bac153ec382e1eae6d3acbdb7e61","score":71.2280701754386,"score_display":"71.2","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":13,"at":"2026-10-19T04:43:19Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"70d58da0adaddb4e905eedd75a199d295cc4e3a1b6db2c273bbc72d0c290dad7","measurement_key":"18bf1dccb33f0f4b91eb269d890634193b16478e9ede718d4406a5013deeb298","metric":"elo","protocol_fingerprint":"38ca9c850a82045ca3916b3f20dab96a791a9ccf17f6190197094bf8be599d7b","run_fingerprint":"ec55fafe68c79bb9a404bbfb4c15a08e08abd68cdad13eec551e200dfbc5ff66","score":1745.77,"score_display":"1746","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":12,"at":"2026-10-19T22:38:32.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"593a054ab7859f4e0e41b82917e41f6145db7aca7aba0bdac914c7598994f5ba","measurement_key":"4ea938ddb4173b7400c1fdc0a82bd06bd7ba30540f6e6c5aae6c2f0370c1e3e8","metric":"accuracy","protocol_fingerprint":"a993234f8f2a31d3e51cc72ccbe3fb1f1796cd92c777cb68a0611427f40baad5","run_fingerprint":"0d235601c73d45a8648243239a80ca13217c89c2e8c1fb11c706e28589b9c608","score":93.18181818181817,"score_display":"93.2","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_fa9e908ac04b067eb00182d4","benchmark_version":"HLE official leaderboard","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":15,"at":"2026-10-17","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ccf4cca8359654bf6637ccec3c4045a9addd0325153de7615f5fa7dde12f6ebf","measurement_key":"557fb77428a03f06984c58a881fb0f06ad7f9bfc3feff321eaed25e67067f715","metric":"accuracy","protocol_fingerprint":"be9d43810413d30c86cd140f91203d82325c7eb5bdb9362db23ce77a0a066295","run_fingerprint":"d5d55febfe8eef35c95a238b2b5ed03faff142bfefd2207322634cc0caef0650","score":44.0,"score_display":"44","source":{"id":"hle","name":"Humanity's Last Exam","url":"https://huggingface.co/api/datasets/cais/hle/leaderboard?limit=200"},"source_authority_tier":"A","split_or_window":"published-leaderboard","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_73c7903143f8bc46fe1fb626","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"C","evidence_rank":5,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"self-reported","verified_status":"self-reported"},"unit":"percent","verification_status":"self-reported"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":13,"at":"2026-10-19T04:43:19Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7198729b47a30b6b8f78bbd4ec5facc7be510250c207c1803d972d73c1556a2e","measurement_key":"e5e515eb1af8e017f76570a44f02dbeed116e762eac4d5a84996a553833091fe","metric":"accuracy","protocol_fingerprint":"33c26e1d10e09ca503f161d3c19688771af0d60c45d49433b41263e57c564428","run_fingerprint":"a4d1e5fc51971db5cf57c8b18bd698f7874498e6a43313b64e39cbf37bea0e21","score":43.327155,"score_display":"43.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":13,"at":"2026-10-19T04:43:19Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cc68d471c6ef075db820835c8bfd61169da3b839603e36b8c53726296ec251f0","measurement_key":"215d76b5013560b87b3579f5b424e95e06be0c9dd21659c948523c4fd68be539","metric":"accuracy","protocol_fingerprint":"1eb33289ec2b6b80c3daa249d86058c34f4505c520be1868adbde17c2a4b3970","run_fingerprint":"6f394f9d1ed54c6373d7dc8bf9d211b8d591247cd60be3b5d7460a7f239ed3e2","score":80.635838,"score_display":"80.6","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":12,"at":"2026-10-19T22:39:00.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3798ec2265dfa45bbb865b43d9adf1dd28004f66419405b76cb9129c8b3ad22f","measurement_key":"4f7b71cb583474968a93396909f4f91504e2eba7a8b1da55645badd6c6c15ade","metric":"mean_score","protocol_fingerprint":"912facf3dfdd839d89f365cca3299dfb731a2abf7798c5e671fbb0c2e9c8715c","run_fingerprint":"1b0aa3e2ca7009bc8fc138eeb6d792fd40a9d0dd129e6459e96ccea690a7857f","score":99.44444444444444,"score_display":"99.4","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:02Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bb110ed026e0f841fe9ce59709d6a16c7ad9be26417db09892bf43353d99c849","measurement_key":"4821f57f094b0586a9def6b54e839b3ba0860a2ef75e62290bd26721d3b22237","metric":"subproblem_accuracy","protocol_fingerprint":"60794fc5d94f43aaf01512adf1f24b963edafcc67c7e7b78ccf9c642648ab819","run_fingerprint":"3611dcd3d406a56e3a6c39f01259b47b3d0c99285138e75d3c1a5e226000421f","score":55.9027777777778,"score_display":"55.9","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":12,"at":"2026-10-19T22:38:54.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4898fa4b78ac9134049cc74fc7dc59123e5f3532748749af8ac3878f5c1887f4","measurement_key":"a26c8d1af12a84e5deb5e11052f81b3c6c472ac21b1da67f5cc64bb4cc247294","metric":"accuracy","protocol_fingerprint":"99cbe422c840bfab4fef49ebbebf773febe7cb793e6b2ce2706556e05b6df312","run_fingerprint":"db15136d32a68252621a859d398642728481b97a9416cee0822da724f7268e83","score":42.5,"score_display":"42.5","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bd8874b4f3cfb7a1b6e5d86fd7e0bcfd54b034bacd8f72e45c68df12665f08c3","measurement_key":"e44ca5a5b44297d255865365818f30a9a9badc954c0ca36136ff2826c728e1cc","metric":"accuracy","protocol_fingerprint":"201ea99257996aae4b74b7d921b921ea2c21c5a41a6806c971b39eff36862282","run_fingerprint":"49add2a57803c137457fb01c18ff9f38f225c650649e99749cff2e43d1511930","score":31.818,"score_display":"31.8","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":12,"at":"2026-10-19T10:28:59Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6e94a7ac8791961c0bc57999c73e7442f35b47232d862308bef9ae6136b3a786","measurement_key":"69464132d1b8a5c802685e3fb8c54b373049a88c1356a986512423a3c5789814","metric":"score","protocol_fingerprint":"416d0e02836e95692eca6edabf7d15cf56a0c3dcfe669f7148325fa3b55207c3","run_fingerprint":"ef8ae8eedf2e8149f10fccfc7f13b4ccfe3516539c4805c6a2b9c91b2805373c","score":87.73,"score_display":"87.7","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"df43ab20c370c71592258d11b1a61b79067f7ad39ae7d15202f251995254e397","measurement_key":"7354dd6c53ab8bbee28cc6e7bf3ea36c177f2abdc7c6603dc991053ba144cc9e","metric":"arena_score","protocol_fingerprint":"716d55c6e96665a5c9562d2f1c0d93b6704a47af5d653fd6484634137d6cc455","run_fingerprint":"7a2ad2c89e1486db79f897c1a76b1795dbbb191905f77554071a73109ec2e1e5","score":1665.040445245608,"score_display":"1665","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_e01929ea31f86853f12a3cec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:05Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1eb90cf001e40407efd51de25bc6078c7bf3970961a6030b0afe8a90cb158570","measurement_key":"cf81fb96812edbbe6b3a80bec91a94fdba7d632ca8923a3d8c675c6350b8c392","metric":"token_efficiency_weighted_score","protocol_fingerprint":"f270043cea84f572be6ff64750bba9120d03125b0f6fd0cf2e007fa38472df6c","run_fingerprint":"e56aaded4fe4dcb41d70ed5a329768946c3d1990c5dcfb7e0ee11c6f1d33b582","score":9.19092568181818,"score_display":"9.2","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_c944b51d250e47008d0a1b60","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"deepseek/deepseek-v4-1-flash-20261017","model_name":"DeepSeek V4.1 Flash (2026-10-17)","parameter_count_active":null,"parameter_count_total":null,"provider":"DeepSeek","selection_rank":19,"weights_status":"unknown"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0eb2960b5b30da0327f912a119eae92205d20e740d345580ad55b44e98e5a9da","measurement_key":"45d05a21a2d7034f461ab8f987de459eb0b57edbb0527f6b9ce6ad226f8951c7","metric":"performance_rating","protocol_fingerprint":"26f8e2ed3572372625e53bc30a10bd0c1ddf914250ae5e5186f642f3fcd07773","run_fingerprint":"edf2b44f7924b4f0346465e2a3b59f4c048ae89bd1f3b8ffaac491b647023387","score":1524.47,"score_display":"1524.47","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":12,"at":"2026-10-19T22:24:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b4feedd80a1c9f968b0c94b651d26b8bac3e7ef3cb7bd56b0b682cdd7e3b1335","measurement_key":"d07c83a41d15eb0658f72d28e610c8fdb75f5feeecaea55551ad86ce0ebff33d","metric":"pass_at_1","protocol_fingerprint":"70143db5f478d32176a20dc8404621bf9500598e0c746d321db264c6ab9f9ca5","run_fingerprint":"a777c33985ce5ef2262b7d7600f1e8b80638bdeaed19384aeebc72919e68b03d","score":47.8,"score_display":"47.8","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9b48cd9b9e58065d050a20a9","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ed0e7ec4fb563e9a5f4dbfd972b7963a4c47e6fa6880d05748b0d772c05e0afa","measurement_key":"4f8de2b5a47d45ce41b4df856012c64d3f0f047c05a7ef1ccb2670c75342899b","metric":"pass_at_2_accuracy","protocol_fingerprint":"c0f8b1c6d5c3d190821c86efc20cca9fcd013ca7bf67de5beaa04c177ae4459a","run_fingerprint":"fd639615119049ba425cffed797db19ea3a277a0a075ffa5346aa6c77a90a942","score":94.5,"score_display":"94.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4a07c96ca40cb010ff958abc0a217311717f944c74aafe903973e8ae50cd9981","measurement_key":"f6fd07dfc659596b18c4bb039d805bff1d49478f667c8f72bfd88b411ddb61da","metric":"accuracy","protocol_fingerprint":"42b22b8742fff641dc193a46a202bc267ec6e13ac30cbe53bf8a3e841fe66b6d","run_fingerprint":"9a15dd5e79c0a13ccede080eb3e9fa564b924e3182cf6dbf90360a34587738a3","score":60.416666666666664,"score_display":"60","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"585da9e2b1977e98893a98471ae6fe1522da8314260d7e10398f852409f37e66","measurement_key":"155ecdd1850992383bb8d37c4836e3c5ef71de31bc15c7b77a98d2fc6490d591","metric":"ips_score","protocol_fingerprint":"206f50383b99286af4fd22c5271f21a330a236359c338c3cd1968c63c6ebb157","run_fingerprint":"242b341efbd4738c3af01d4048225eb3356d717cfe6178606f786c2addb1565f","score":0.010787136728542578,"score_display":"0.0108","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"480c0d43a3d6f866625dc0362464772612568fe0e29e3764ef134302849ad711","measurement_key":"465d9fcc5484237f36d81aa2253f52925de8d8dfc5675bf71736a32c236078ea","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"9476ac8858119b35b2b49171ec79ddf957d037e836af955536b1dcb15c1e09dc","score":1488.1894728804475,"score_display":"1488","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T17:13:35.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ecfdf4fcdf6d3a488d63e466e9a2969c23f224fc53c2a19f4b02c60340c01a47","measurement_key":"a792fdf37f452a3ced8ec346337066cbe9d3bdd9d3b85bb320fd854760937405","metric":"mean_score","protocol_fingerprint":"8964ec3f7cd10291681183923c3a7e640253d9e24a5db073cd0846202888cf6a","run_fingerprint":"ff23b72e4a56c00887d77c38655ccf87e4f6b9165e8196e7d915e43cade47ffe","score":36.0,"score_display":"36.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:41Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b023e07b057566dee92d055d89f73cc9174f9a9b31f6247ef92983175b721b82","measurement_key":"fbb4e9ba4730922435acebcb6a4292f8020e89852be181476bee07593a0ccc70","metric":"accuracy","protocol_fingerprint":"59cca39d88f18559fc0d18a44f486256be02cce06212032473cfc39f9b4d867f","run_fingerprint":"4645273c8a6107ddee46707eb8fe6602f7f1af744df83d796ee9c6d08cbada8b","score":23.400000000000002,"score_display":"23.4","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c25ce5401f264cfdc37f52a96502befc2ac014b482503be496e2a1d189bed513","measurement_key":"b24bc9e2d7d2ec975c28ba7844b0d51266ce745059cd2d2d228991db18b682e7","metric":"pass_at_1","protocol_fingerprint":"306487a785d65dc89a1708ac4b32950b6ec9585e38149e470860ea5d905e336b","run_fingerprint":"7e47747a62e403f96ee540c24b9dcb6238b490abd78f21d7a73484b9d6d730f9","score":68.51441241685144,"score_display":"68.5","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2b88a2dc6434f91b1f1765071287a9fb607b15209064304fb1c1f429569234df","measurement_key":"58785f61fa26ddd34fdd55cf5936eaf94d55a97d39fb603b4f3373060270ea96","metric":"eci","protocol_fingerprint":"229801ef2b9d4fb28dd8cd63272c855c333d194626843b78494c92e218213ba1","run_fingerprint":"369a2b0f159d64a2fd062b4a514f0f615e9ded67874d243a003949d450c64502","score":158.33,"score_display":"158.33","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a2da5036f8e35f4973a1f1d7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a03f0e262524f20dc1f163683bef67b8ecbd4202dbe3df9aa52658cc8942beed","measurement_key":"6a4f294b800912826f4ac83bfe48293fc5c23851f2921fd0917abb975820cdcf","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"c7e0ed9a1238dc923792161e4c4e2f6758900ca23d2261dfff6b838e57b05782","run_fingerprint":"6be974353ee3e7502cd03aff9b94bb8322b624cdb0fb733d576a655fadc7b29a","score":44.17,"score_display":"44.2","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_1ae7fb380652700fc7c15f73","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":107,"at":"2026-07-17T01:48:42.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"61249d20255670984ebd7abc1f9c7a49afd725bf8657e1d3d528a57c5903540b","measurement_key":"5d100d4d0079d561f23d4a068592197912c22625dca957e8d04bd8b798996196","metric":"mean_score","protocol_fingerprint":"8cd6dd3d3cb2d972401111c3a3dbca3df50385d3b1f06d522a56977e1ea3578c","run_fingerprint":"7c1a329cf3e0ce523357e1a85d405b34828175da2d6bbf04c7daf5bd7fa3f6af","score":72.1830985915493,"score_display":"72.2","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":107,"at":"2026-07-17T01:48:42.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9931c4d00616afca783048d1d265bcb1eb6f7f062be8998a37da5f0f1f6560a6","measurement_key":"442cd223534ea7a452db811787de3e42d6bd77a04fdad8dfc5b15c9383ff0792","metric":"mean_score","protocol_fingerprint":"6a845d022df3285937b93ad8eb42b1c9fe0becf0699e3a92964e5c4b4d9c122d","run_fingerprint":"25d1789291243ea1e2fce19c790995733757a28597d19634bdbab8d259817e0e","score":39.02439024390244,"score_display":"39.0","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2c4b28a007cce0a843736a7cef1ce174a17e42ca820a43ba099e2af985857475","measurement_key":"d74d694828819e676bd3c167a5493484736bba23d754bef2d9f4f893dd52d3e9","metric":"elo","protocol_fingerprint":"59aaf3d6f2f9d29609b06bc1b843ae84fe3f8071c91b96c5a63bfb3106816c3e","run_fingerprint":"0bc1cddbbdc14f64197687f8444144b9383302dbfbfb78a4d46018a80cdce725","score":1542.76,"score_display":"1543","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f2ede0b7f010fe42dacef5648c07fba31a85b4f5234b3e58f800424b5c5e107d","measurement_key":"599bfa26b3b1ecdf10644c11d35ee177c1ab0bc46beb7c429bb1e65687c163c3","metric":"accuracy","protocol_fingerprint":"7f3c372b5b9d08c79117a9d056e7d7c5e6f0a18fa77ce40b4966a6d6caf74611","run_fingerprint":"a792b2bdc4d8fabc21c787eb54aa5697730385a38587107f4ee3d75b9fbb6474","score":92.929,"score_display":"92.93","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1e5c3455b6099d35084a3c99","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_d43dc12b725969a1cb1e2a28","benchmark_version":"HLE-Full (provider label; revision not restated)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":97,"at":"2026-07-27","last_confirmed_at":"2026-11-01T07:28:21Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f72fb32ca3e8153ca58cec8fc8854dca8ab7e989fc9a620b6859ff79f785c84f","measurement_key":"acc8b40c1203bbb3919238141fc1be125f35c00dc5a268140c35fcef0dcd60f7","metric":"accuracy","protocol_fingerprint":"6547241796b7257e8ab884f956a879819be7729074e34228a3dfbd69d4f79e1c","run_fingerprint":"e35a8b6faf99dbf6a2688cb01c029a24c7760cbb408df0c9348eeef2bd86d431","score":43.5,"score_display":"43.5","source":{"id":"moonshot-kimi-k3-card","name":"Moonshot AI · Kimi K3 Model Card","url":"https://huggingface.co/moonshotai/Kimi-K3/blob/main/README.md"},"source_authority_tier":"B","split_or_window":"provider-report-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-10-23T12:23:56Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e8f003ad7a529c1aea12c3d20760c9f63a93b00ee9a8d96e06b1bc3dc1f718da","measurement_key":"4d622196a8a4106e9a2f2d4f61d7ec9c1f428815d33bcad587c1479594811925","metric":"accuracy","protocol_fingerprint":"e4222e9089f31e296bed718769c7c24923b2b7499edffbb3a5bced24d21c697a","run_fingerprint":"35788b0c6ee53a32d8a5496c7eeb81c94ad432d49d34877ed89dbedd2574aa99","score":46.895273,"score_display":"46.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c5c941f2ef3fdfc2acb4243f320b21b2d11491b5fa8048370fc02d6653065d5c","measurement_key":"412c18a0340eb3ea7a8b9a407f02a5dc29867456ece47dc804943a49a5b342bc","metric":"score","protocol_fingerprint":"d00e0d2333d717ddddca461635327b78e3c7fd75b1ac49a6adea50bb44c02e28","run_fingerprint":"1d9bd114d0b268b05f2f31f6d8f3a5b26a8b9cbbcc7b39f89419ea6b4e3fafe9","score":48.944,"score_display":"48.9","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ac4d3bb6ce98793523f1752d6409dd79d90903fa09298256eb2cb10602a05638","measurement_key":"930a2cdf743e8b22ed17ced2c82aaec85ad2dff2845102920a5fb0c21a8597be","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"0ae44147578e5b57b250f7990a149b0ef43f36765bdf7f3a0537128525a5febe","score":79.19304761904762,"score_display":"79.19","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2ad36c6efaf22e10e2082fe7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"96aa2a5bd779ad3d833ca401a08c4dd44420e88bfeeee61fc72d14a95a891831","measurement_key":"c78eb0aa45484fa3b8e18d7f9f3e066cf8166f5222e9d04e46bab7f49a17e19f","metric":"pass_at_1","protocol_fingerprint":"cf909926925b282a11e854233cfb493e4c415d491b923b787e755d2b23db3c7e","run_fingerprint":"a7ab42c47f4d373b685eb27cc1ea7350b0b957c0bfecbe87bb0066b301eac89f","score":87.185,"score_display":"87.2","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":103,"at":"2026-07-20T17:00:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b997057b43163a0d8ace305470bc5c236356c9345f2308dccb9d6723f02c7af6","measurement_key":"34aae388fe88e7464d7154286c4837b04e3ab66255fa697134d846a193228ca0","metric":"pass_rate","protocol_fingerprint":"cc9d2e009b518b3adffed41d282410d2c79474d1a3c986fd52d829a2bc0d9931","run_fingerprint":"43d2051074df866e8da4537229cb15043b91f4ca6507ffba90aab513646fe1a9","score":82.3,"score_display":"82.3","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-03T21:02:17.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"398ed414a629db5e8e68d52f8899167266f5c95a3465ed8debccefcf1c93a662","measurement_key":"5a1a4dbe2f7fb40c2a68c777887e366d0172044682714d2c5724fe6c33798890","metric":"mean_score","protocol_fingerprint":"904c442ece3e21ed6442928487a8e3b1acb439ceced20523cbd0f0cfad02f58d","run_fingerprint":"d13cd7b119ccd2939ef1efcc9f7575277b4ba66243b0be7a6d0f39786e3daa2b","score":54.44444444444444,"score_display":"54.4","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"59426b4594744d03b9e04a03a5cb588b729bd0063603f8fee7b15cdebf52147f","measurement_key":"2b09b1cc45e647d36c6a2069af2f9d22042b25cbf338676951406da4393d156a","metric":"accuracy","protocol_fingerprint":"3039f87c799cc0ee74bc38b42ab8172d0e1a0c5d9afbcbbe899e385734167535","run_fingerprint":"12d3d378a65be702d209dc0713f9eccd92c10bd7e32f02b0e374efef379565a8","score":87.973,"score_display":"88.0","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0cb4c511987dca9997bc8f024a582bf9584c4fc84b60b55c103eae2ff283c910","measurement_key":"ecb4f6beaa1a784cc7a266cb2e82ce7492554475a318cc0bd683cb92b33fa00d","metric":"accuracy","protocol_fingerprint":"6919a5c7733cd4daa2083f67ab0e7562b65969b8d1f621fc3b5e57be2792b6e1","run_fingerprint":"79b7dd03fe7446350d7cf01939f3975bc1b976dbd507b05c6936bb0e3a04d904","score":88.15,"score_display":"88.2","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f82da36312f78d41c5384ff8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":107,"at":"2026-07-16T21:59:40.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6a1c483792d6cf4e01878822d98d05c08322d452486a23a678b82ff2bc61da3e","measurement_key":"d3fa49bece1c6838abb8e50f322162e37ddb9c726bac8e2364c5b914e020f9c5","metric":"mean_score","protocol_fingerprint":"5083290679b6574e185789e24ba694af1cd7e60a77fa6d03706ab192a8c43cb9","run_fingerprint":"16b04537c155a1bed20eeceaf66f7bfba282c40ee2b0c90b2d084a2c0c96ced6","score":97.22222222222221,"score_display":"97.2","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"26c4f5a61034be49e0812cdbdaf1ed3b91bb046e924ffddad65fd58dc09a3e7b","measurement_key":"1ff3668f6497955deed5af9b71d4160636487cf0c42aee0609b2d2a9e4f5c1d8","metric":"fully_resolved_rate","protocol_fingerprint":"f5cc6678464d269804314fae3c938893505b15b61747dde2248eeb3544341176","run_fingerprint":"1199c5fc0425e063437979897efc4f898fe2f020025744309249e7967fa193a5","score":2.0,"score_display":"2.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e69c6787d50e591da58165c2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"02cb5ede8aab72153b450e350942ca8b5f2895ec40ca1e412ece808da6c4c8f4","measurement_key":"c0a0fe9ab7255d137ad1d03ebbe6f5b17baa5f30caae15255ae41ca6a4ef6968","metric":"subproblem_accuracy","protocol_fingerprint":"d207f4bd9a8315a188c36c2f8f48954a11e30145087d14971eb8a55d67f6fda4","run_fingerprint":"a4de8b9ca28d41344c2995eb7d0554c72c2041b8afe7d2255edbb35afae068d5","score":59.4907407407407,"score_display":"59.5","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"eff8b1e9d50a3b1c08a34f9c8ce395d35fd697e9d6adfb26c44d8e242b07ea83","measurement_key":"9819ebcbdb0ff86d7733579a184aa27df28d333c7943a50cf6ef45a1f8b13996","metric":"accuracy_avg_at_5","protocol_fingerprint":"34d15d8fb21b57acc8ecf80c7513e58a21cd3eea609126bf88cf0714279cba0e","run_fingerprint":"abad372fa85eae820b735df13516eee59337c51be75a2aa64a3769deb144986c","score":60.70000000000001,"score_display":"60.7","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:36:12.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c31873775273f98c9bee5cd8ec3c78648bcdf8ff588874e3b4f0ab58cc2691e7","measurement_key":"7f4a00ebb41047245799db6ca42b8b57942c14031c1af9bca3e23ab608d2b93b","metric":"accuracy","protocol_fingerprint":"8a3839bf844fafb00603a5223443e491cfff9eb6b96d800ff480fcd85634633a","run_fingerprint":"1d4114e7a5cbf8f28dad6d78ae990e030fa9cd9ab58c24445fdb06105aed6a0b","score":50.6,"score_display":"50.6","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-pro-v2":{"benchmark_release_id":"release_d9b58bd286ce316ccf0ed891","benchmark_version":"Scale SWE-Bench Pro V2 public leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":25,"at":"2026-10-07T01:44:58Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"925b23c81e5c5c561375731cf3b85a17c086a69c0058e1a2dc3b7d2f64c36aed","measurement_key":"c18c1511413deae397b7777a67c198faeb222e71e8dd099c22fe4edf8c326356","metric":"resolved_rate","protocol_fingerprint":"595601bd3296ceb781aabc9d0a50b934d20fbac11b7f070232c064d4ec64208d","run_fingerprint":"94fbbf6438131565279e372d6fa1a4e1e0f83d468c48e8f2cdca65e7f61065f7","score":97.7,"score_display":"97.7","source":{"id":"scale-swe-bench-pro-v2","name":"Scale AI Labs · SWE-bench Pro V2","url":"https://labs.scale.com/leaderboard/swe_bench_pro_public_v2"},"source_authority_tier":"A+","split_or_window":"public-v2-642","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cfac77f030aa5416b30a79c99594184406dbc65e80d8169f09134cb73366259c","measurement_key":"11dc2e98c3459568c190eb635848e5978053dfc197f1a1548f0ac0ae44072a72","metric":"resolved_rate","protocol_fingerprint":"e5146a7e1aeb95ce4cf2f69911cba1d5e88fe4dc3a17a5efbbaca38e9ff01ef3","run_fingerprint":"84004b8d1e4e0c557dff82cd3f35025c4a609e779c5ba85a2dc3b16e13bb25b8","score":93.4,"score_display":"93.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_cb71961e616ff6ab8428806f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cfac77f030aa5416b30a79c99594184406dbc65e80d8169f09134cb73366259c","measurement_key":"11dc2e98c3459568c190eb635848e5978053dfc197f1a1548f0ac0ae44072a72","metric":"resolved_rate","protocol_fingerprint":"e5146a7e1aeb95ce4cf2f69911cba1d5e88fe4dc3a17a5efbbaca38e9ff01ef3","reporting_origin":"organizer","run_fingerprint":"84004b8d1e4e0c557dff82cd3f35025c4a609e779c5ba85a2dc3b16e13bb25b8","score":93.4,"score_display":"93.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_cb71961e616ff6ab8428806f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":100,"at":"2026-07-24","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e1f9e1614fd456480496d1488defafd0e128454bc32dd5116ed296a41447c0a0","measurement_key":"7fb093560c84281582fe30af7088d22b3c6de7c3e4f21a855506589867d2f4ae","metric":"pass_1","protocol_fingerprint":"d4add4b3535a169ff2af2158c9e2174929b38e4bf3719273a4645375b4d4410c","run_fingerprint":"e81a9927a3fd0b940192acd79b954187e22d5b7e3753542c3f53f54ecad7db9e","score":37.11340206185567,"score_display":"37.1","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-10-23T12:23:56Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"655f8143767ca0197ba6ebebb63a17893110f8c4ac4df39cecaaec69030c0406","measurement_key":"ecc0db406287cbdac58cc06bbd2278291ebd00877c5452838e577f85cddd8a1a","metric":"pass_at_1","protocol_fingerprint":"5bebbba10f9c82136b1f1403f12846611f297a8d15029ddbd52cae0338fed613","run_fingerprint":"dd6944447fcf58ed7af6a011c94b94c9d72cb4838ed37362ad0c9764abd4c293","score":45.979381,"score_display":"46.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c7a9ff6cd8ac896fb0c564f09d74cb8061195fe5ba83686fe507a418bfbd05f6","measurement_key":"16e3fecb13df52e6553fcbb0b53ee50952aed148e65f6ab7bd22ebc00980775c","metric":"accuracy","protocol_fingerprint":"bddcb574e9187cc511751527acff9b2b854391d966cc657335f1c10a25bdc9b0","run_fingerprint":"f011615d3a0ff4fc40fab8b7d0f16b30804a5802595601b1c721af7056e577c4","score":80.899,"score_display":"80.9","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3a3b2af30725252e205c7697","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a1958c0ec515b7d37bc1165633c9986298377fc6a0f85d68bf7de7a2cd1ee0be","measurement_key":"e58b933a9eaf167dddaef5288f4dd0a392d2a2408df9755820f8c1ab9197f5c6","metric":"accuracy","protocol_fingerprint":"55c2e28ed2702b6791c427422cba51c5f0c19960cad272616f5e5e584f850d68","run_fingerprint":"751dcbb025c180421b819945355a445872c5d6bdbd6c4eabcee4897b72fa9d64","score":17.172,"score_display":"17.2","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2b9661fe6fbf9e70046297d8c267400aeee5247e9dd5e15d499a65154e38e370","measurement_key":"32127577c68f21de103fe5edf559c9ea3555d55d3a4dead1f4181d184e042192","metric":"accuracy","protocol_fingerprint":"9468dbba5cce4b78e5e35f6b5fa0e8cfd19ed4fabcdb56a4f4f8f6e3986a8010","run_fingerprint":"5c1c738a03a0e413db4f979111ccedcc13da3dd529fe7ebde35c5d53d215620b","score":1.429,"score_display":"1.4","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"93cd43098cbcee209cbf88c02aa3099df718e71666ec7e80b974861a4a3bd8eb","measurement_key":"abcced1cdbb29c0ba9bc2ad0008a8c5d96eaf0f39b315565e91e1abd10ca0c5d","metric":"mean_final_balance_usd","protocol_fingerprint":"4773551f57125bed55432f6478c79beaea73730ddb3a7beda378f762751e4d9d","run_fingerprint":"8e292c0ff260eb003dc47a7c1464481622b8aebd0f40b2ce93c970d629bff307","score":5165.035000000001,"score_display":"5165.04","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_97cb45dbe3d881ac6db37643","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8f2f0b40b1ec183ede22e557e03ab89739d83f310abc1500b494576e965bc8b8","measurement_key":"6799fa1800197a8e20d779e3cff59dc7d059ad8e784e45538d01e30d321b8670","metric":"score","protocol_fingerprint":"f23420397d0c64bc27c2f7696c7528bb4ac34ca86854b63260214860266017fe","run_fingerprint":"9183c9040eefd31a71e9afe2a7928cd78a69fd52448d64fa5e9d89bec7371ec1","score":84.968,"score_display":"85.0","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fe3163e47f8e0b86b0faf8abc088c1adc6b1667fde0f3ee046810a3061eaada3","measurement_key":"10c77d73d5be06a0593986ea59526a66dde0f2a02f28c52ff89c385caedf2d5b","metric":"arena_score","protocol_fingerprint":"501d10378f60694547bfcef5359a990c3ad47ec25d86d2292e96402e7f52b280","run_fingerprint":"28af1c77bf0f898bcf261739f41391697e2bbd32bb7e7de9fc935cb1abbf0b9b","score":1656.390908396489,"score_display":"1656","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c5c832f089347ca98accb8140afe4eb69f3f72a8aeed21a767dc002964c53a4f","measurement_key":"e3270daf707ad1335c48eb98b49261c1a924dfa38873cfcced13de9b29eea7c5","metric":"accuracy","protocol_fingerprint":"8def5ce4f9c29d1ceb1fbe271d3ab21fe88d2533a452a1ddabbfb9d9427de49d","run_fingerprint":"52e0014ebc7b9f4bed34ae9119c7ca48183604808d9157ab6cda1fe9aa817e52","score":82.57,"score_display":"82.6","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_2de1840141225fae3ff55b20","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9a3e4122b31e984afea2977fce64ec66b801aa2261952c4a5d7857ad10ee1537","measurement_key":"d7c258bcaac3b995a99d0d482ec29a4c18f30f71e91ea43b22751162584366fe","metric":"token_efficiency_weighted_score","protocol_fingerprint":"ad05b76231e6475395cc18578eccee22561c4b69022d7d5fa111eef6a70a9dad","run_fingerprint":"9fcdc050713c6704d25200133c217bb92b9bebb0870e957041711aa17dd84237","score":7.544402727272727,"score_display":"7.5","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_1940792474091774d582a01e","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"moonshot/kimi-k3","model_name":"Kimi K3","parameter_count_active":null,"parameter_count_total":null,"provider":"Moonshot AI","selection_rank":20,"weights_status":"open"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"729de20795f458d62b096931011a56b6c3ca12c60f2da1cdc333d0762eed4230","measurement_key":"a7ca06e69bcdd47371f65e80000db446c67fb2971ff0d8f5d4a77b398e985fc4","metric":"performance_rating","protocol_fingerprint":"f3311e4be89c1b73ae094ad063587aeffe70b07391548374dd81996c86f2f28c","run_fingerprint":"9250ec5711f956103cfbd06bc778457b358fe3e990a4551fd39f4f22b3bd2be5","score":904.3,"score_display":"904.30","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cab7bba3879260236a1d66f90726f73cfdfc5d8da424c222dcdf9532c98af064","measurement_key":"6d3e003856da8449764a2b4a0505e7c249131d4ec570234bade3489991dfc01b","metric":"pass_at_1","protocol_fingerprint":"e3016c190d81e28cabaa54e0616b06e6ceb9c11446f411ccd293d67b343e91af","run_fingerprint":"39ba69565003326c245cfd35647b24cb380164f68fa426d031a284b6d1eda03d","score":67.8,"score_display":"67.8","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e5060d9b2625a987949324dd","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"610de55f718144cf8532745e5d6a5088d56dd0cb69109ae30b2000212f9296b1","measurement_key":"36967615b01b89787557a278a0d487bbb365db2ac3e85b92350f1b47aad98e60","metric":"pass_at_2_accuracy","protocol_fingerprint":"69f32bc8259b448a1f8af6930b6b12e08ba568889f8ec89626ba030f9e02c99a","run_fingerprint":"13f14ba6f4825aad82ca126924d0094b1510afbfda8816c7f792b70a3957e8ef","score":95.5,"score_display":"95.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5992b543a60fba78c3638cbdb97f20afd78d647286b01f8f6dea8c5707568bf7","measurement_key":"ea4c540cd1e6f936125cc3b33ecb0935b9457e156ea6b9f08d43dcfd40b7575c","metric":"accuracy","protocol_fingerprint":"f6c9bfb4f2fb48d9291daf5ef9fc0e68135afbc6971eff8c25aca2f196043cbe","run_fingerprint":"246e7bb3ace5e2ccb7b30bb4831ae4a6d02720d2b447125b0a8d622df1a99663","score":84.58333333333333,"score_display":"85","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"594174445699016ea937d6f2ce0a5678e4d7082701fd74ba418c157b7e742ded","measurement_key":"c6922d9ffae91d47fa3e279f327d48d51e258759c77a2a77ed60167ae5e247a6","metric":"ips_score","protocol_fingerprint":"42de3fcbf0e58578f8438d70b04b1893870ab60a89a6d698f7c1be0d0d6244ba","run_fingerprint":"470286f2cadc159e967bed47591ecd7c21def5d1ab26a6927c757df945e4f6e3","score":-0.013461022898167443,"score_display":"-0.0135","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dc80e57791509367752390733b28216679429620446dd0d2a874e825d3c3c85c","measurement_key":"d4e559f81794c11cf63c8076614c32e31ab88e2d2efe41057c5765615b193f3a","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"effd0ae6a372eb59d5e83f5c75f693daa82c4b4728d9d3362eab1c8249095398","score":1489.5500575529784,"score_display":"1490","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:00:23.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8ead28b45fcabd7e10f75793f4358b6a731e911ff7081633c9b12915bc9a0a74","measurement_key":"b38573e082e0523ceb25a6a987c330cd38731f524a40574dbcf578a3e9674a40","metric":"mean_score","protocol_fingerprint":"2299141735ffae39b475ae648b76af24afb1b26108db9220fd90ab92710ed553","run_fingerprint":"8afe353633edecf228948037bc85836f5677d2d2e713f3f2ad195cad19db93cd","score":66.0,"score_display":"66.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"96810ef15bf82fba37137727f3077daa137fb5f8b1884dfdb80d8a236782bab0","measurement_key":"bee69cc04a898d99b6d7d980e99e2c6d988bd1500db66b5d7412f24c5460ff56","metric":"accuracy","protocol_fingerprint":"83984a57bb7a1c473bd9b81b37832555c7b6ad1321db082679ce2256efe7860f","run_fingerprint":"705b03dc62ffee11f03e1a8db04102e23f19b942810ef564b8cc6a308bdf9c40","score":14.285714285714299,"score_display":"14.3","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"87e9bee21cbd1df04bc424abb64876f913627d00af5fe54fad1e698e57724c92","measurement_key":"cfd74860ac5d7304c421216b5343fec14af66e6103b2229a14da3206da5058ef","metric":"pass_at_1","protocol_fingerprint":"bfefa0da8b857f3d96ac81cd445976b8fee7a53a767175833268ee0896536293","run_fingerprint":"c2fe90d75526beb903835bbbe2ae4e5582d1bf9abdfa369143d517c93656c2b0","score":65.2654867256637,"score_display":"65.3","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ef77e64f52732a8ffc706103898602f8ec8124ce3340418d591db3b68a893ae9","measurement_key":"f0c89730b64b7fb9bf322e8dae26057bc54d54cbc84ba39f72958b7d84a92ec8","metric":"eci","protocol_fingerprint":"a4c6e5b59eb818d5e7a4ba564b3a76f08f622d4a6dcfbfd37890bd3275ea41ea","run_fingerprint":"6a2d0cd3e16f2d9fdeff9bec637765cc1187dfbd62c87e6f2c5d741154cc26f4","score":158.17,"score_display":"158.17","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2c8a392b509c1c0521fc9bf3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:01Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d4fe1c8f33157c73b7384f37392b1e5d77b9208a0f652490be895a500ba495a4","measurement_key":"d1b30aa5d18d8e2493397f4f210d4483dff48a9c7b1124ecac699f21c58350de","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"e84a6924e739ee6966136bac08817f053eedd3e1dad6eb56cb049f8836dab90d","run_fingerprint":"6229d7fced424b5210620af451ee0b9e52c7918ea14c5118d26ff63c8867f03e","score":43.59,"score_display":"43.6","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_ad3d84b960dfc393e7214ac4","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":78,"at":"2026-08-14T19:59:58.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dd2d1fb30d9ac3c51b1937bd1e104be5a57f9a2816d7cae0403f327add08f579","measurement_key":"db9ae78480a3c9931a8d6dc4d04217abbf658a0e2ce1777d87a796ac02689ce5","metric":"mean_score","protocol_fingerprint":"5c4ffbaa4694435d16724924bd3e92e829ab6da23f61d6ca87985f02225a6a87","run_fingerprint":"750f6de0176f1b01bd9c79ed1c464a967f45ff29c0390b58e5d64e1a6da7d48e","score":71.57894736842105,"score_display":"71.6","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":78,"at":"2026-08-14T19:59:58.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d8d95018d3032e0927e0c8cebf8c70101081e3318a4c62d1867941addee77562","measurement_key":"22d18fc0441975d5f490f35313e413cf3e26883d17a7d4b2bad7c9968255641f","metric":"mean_score","protocol_fingerprint":"4c066fcbc43cca1fab40e9bcc635e96bfab7551d349b999e087229dcbb8a284a","run_fingerprint":"aece6c458c18c1fe2961dffe8d146f0274ba162ae7066d9e8522335ab79523b8","score":36.58536585365854,"score_display":"36.6","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"112054e8ea799c29ba09a3e936dc91f730b52b34e675b8f7f38d5fa88d6cba3d","measurement_key":"93cc02dd90ec908a95725233c6eb490776eafcf57e4a1eb27da5446ca5b3c43c","metric":"elo","protocol_fingerprint":"93eb70ceba1cc7f4f7373a4267371005fac1040baafbbf53ba8621e278c071bf","run_fingerprint":"c969f0ff5a91549f26f6ea9358f4de608cc8563b3faec2f26c278cf4e8b8a555","score":1402.91,"score_display":"1403","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f9793a6432e4eaf9a8dbbc173cf047dda3e6ea783f16cf2b55d6dc940799e7ff","measurement_key":"929e6d2ea41e4577dcc856f2a0be04df9ca3004bd0ea584a2927b1b0fd9e43e5","metric":"accuracy","protocol_fingerprint":"29c8d240d75b1279a0d31a1eb0c660c187be5bcb9848d9610e321635fd176b35","run_fingerprint":"125b03eac5e605cf220ce84dfaba9ee5a5b8c8c64af429206b1bef66acc40a10","score":93.94,"score_display":"93.94","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"07941b8b407e563e2e28fa506e62d0f883a943401c2a4c279ab5423b14d28748","measurement_key":"80fb6b652d2008559d27debbbff53311410b0898aabe69d21315ea3048a9cf6b","metric":"accuracy","protocol_fingerprint":"ca7773258dfcd0ce156963016827db6b1137cdd4c4f0777571ce92f9798bf5f5","run_fingerprint":"1c45f03a59a55567820a001236da0986e05bd202fb01bcadbcdcc34dd8527c6b","score":47.868397,"score_display":"47.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T19:24:33Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"68f7f05338fc9503a5ac300d3b2a95f184c8f6e6079f03884c1d5c19ed10b919","measurement_key":"df8d4d3c74603ded9b7ebfc88df7301239a09e72141c4f4b553eee2dd34ed7fc","metric":"score","protocol_fingerprint":"a18b09073320ab85243b0e073208d91c90467926cd4a2d27a2b832c6764ada3d","run_fingerprint":"400479054c6d76f314e255ca4d0fbee25834a0b02ea2db21024a87d990be02fa","score":67.833,"score_display":"67.8","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0ee8ec45dfd3ab0bb53f5df558b16a35bf9330b031f29cc9efb69a4f0d90936e","measurement_key":"afde32efa538ebd57253973eec213976fb0a9e0f0cfe0ef27c9f3881493ab973","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"61e19f8cbaee775955df454a93d83378383cc1c139a43d4a6b56255a7c7460f8","score":78.8260119047619,"score_display":"78.83","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"14f3b6365cb65dc692c517b8856ee8f0735785b62cca89f799f58276df66a7d5","measurement_key":"1dd3f58fe8340b2ba4b9715b2d8cb50f4facb3cc6db14b54a169b469f9a99d7d","metric":"pass_at_1","protocol_fingerprint":"4f3ce382986db9efd84e74b08136b5e4acdc7aeb74bef6c5244b43413bc19d91","run_fingerprint":"114e1539661087428751b773859563ad3e5b3b3a8536f80e7c08da73d995170e","score":88.652,"score_display":"88.7","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T16:49:08.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"309d44f0cba78432d503e431526c29ac2ff84134d4ec3194dc88a22cabb68db1","measurement_key":"dc91f1050448be934925830aede8009c9511436470f909291bffcff9bfd8a174","metric":"mean_score","protocol_fingerprint":"98e8b63d921ad13c340ebe3561a974acaa3554f644b6f9eaefc2a373a8938dd4","run_fingerprint":"24c8769f9c20a07118cac446e55ca8810c6ffb7e6c5d71b26d36510ea787d45e","score":41.11111111111111,"score_display":"41.1","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3bec72c01588149c3ac00d94198277f69beed60615554951b770f7eed2e4445a","measurement_key":"b37aadbade5bcf79883c348cc70e5d2803ec68960ed6b34e5e69d637e611cac7","metric":"accuracy","protocol_fingerprint":"60fd7fe0a42e91f4b9844276aebedc209a9231e29d526fbdced17103bef37018","run_fingerprint":"09786e4445c4b228e536ab725f1d379c1471f0702981dd01d0c6468255e08538","score":90.121,"score_display":"90.1","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3d1a5f00604391ff36b286235eea165e4a6967c2690057884f284d98e2f87aa8","measurement_key":"9d18392ce92bdf1d50d30c7a05666318fba738c91b60191888b144416bbbfdc2","metric":"accuracy","protocol_fingerprint":"5417bc3335af1f333eed959cabff2962ea36d6080781b040aee9c79a6bd35db0","run_fingerprint":"8844c58ab235fe1a5de98394b8a16ea3414f6e8522a1ebc662658fcef294d9c9","score":88.96,"score_display":"89.0","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":78,"at":"2026-08-14T18:29:12.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5c350c11ecd01400f7406ad648e69c0683fad881fedd094fe46c8d7c5c417b95","measurement_key":"c2015da720d93d6395684d36c49b4b2132b6c1414b6890c3a8a2b4208bd4b2a9","metric":"mean_score","protocol_fingerprint":"32f8df7bfa32c631c95c02add8808505ef388aa6348f5af1da1f0fd50cb3c08f","run_fingerprint":"c98de7d2ce5590230fa9f7bf8153fd3729541ca9e000593d4c6afe7d695d58ce","score":97.22222222222221,"score_display":"97.2","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0fc0567d03658f890ef88b16af7e625668785b27a9d9aadf0bab721a53f8bf06","measurement_key":"5e6ce10e69485cca0d02b91839a81e959ba52c8b9b5c58e3e84d22603f9617df","metric":"fully_resolved_rate","protocol_fingerprint":"0b1207a652792e565e4ab5f2ce4b9bd7d4ac8ae5721eabefb1d59792fc7ecea5","run_fingerprint":"38eb990fd2d70b364dde14e7a18c25aa254d25348c9414e0ff1ba0a4472c4b70","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2d604d8e8d63708ee89e0c93b22b273d7c19c1a109cb1c6cac04cae4e28c2d9a","measurement_key":"73493a37d34ead515994b4b5d6e52705f13ee718a6f58118ce5512bb978de7cd","metric":"subproblem_accuracy","protocol_fingerprint":"a1957ec864f84f6d3231599a8a9b9cdfb930290573864e8857f74c2c4e1e5327","run_fingerprint":"25b7c166cc6a7e07bd65696d93d573261de529b94dbcf612dc51fa9a9850d146","score":57.175925925925895,"score_display":"57.2","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:30:25.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1516467a06c6c43709cdcdee0b4f7d7b3356c7a1c7311ae143ac10d116539b30","measurement_key":"c1486c3274639ddbd8c1ce3d06269118a3eb8edd15c25cb1532c6f65a6ffa13c","metric":"accuracy","protocol_fingerprint":"9f5799cd60e18ca9aa0eecd6743a82f7e7c58c7b690fd09e185585ab33e03352","run_fingerprint":"e80e3e5cefe0907999bbbe5520afd5f232e7da3bafca2c799bb7e3e275b560c8","score":69.19999999999999,"score_display":"69.2","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5be21b9e576e98e9ee48fb380ec091dd38d56447a1bd06ff8cb9605b99696e6d","measurement_key":"57845616ec2b8b95a6e432ea4c935c2a52f335a43cfa5c28ce17d283785fa5fa","metric":"fully_solved_rate","protocol_fingerprint":"228d0041f446b5a3d7e7d29c0bb03e27402bd7c00a644d0ad510d02f997555fa","run_fingerprint":"098e174e7723c268034aee931278b1c45be47b134254613454a4486e352d289c","score":4.58,"score_display":"4.6","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5f048c456c7548bd7699c944ec0fb313d336342297660a78002db123f84366da","measurement_key":"5964792ddd9cb8988a7072a5b340a0b48c67c07b5842f15374a911274c9b1d0c","metric":"resolved_rate","protocol_fingerprint":"aad3384a45b481d0d0f360c7ea6d46d4de011ffe30453fcf0e373637590dbf67","run_fingerprint":"6bed1ae144c6b5f3d03b5c3a48f78d9a27cdb80ff00b72393a2beabba1d256bc","score":80.8,"score_display":"80.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5f048c456c7548bd7699c944ec0fb313d336342297660a78002db123f84366da","measurement_key":"5964792ddd9cb8988a7072a5b340a0b48c67c07b5842f15374a911274c9b1d0c","metric":"resolved_rate","protocol_fingerprint":"aad3384a45b481d0d0f360c7ea6d46d4de011ffe30453fcf0e373637590dbf67","reporting_origin":"organizer","run_fingerprint":"6bed1ae144c6b5f3d03b5c3a48f78d9a27cdb80ff00b72393a2beabba1d256bc","score":80.8,"score_display":"80.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"900e3e16a2c3b089fb090e00d2404cd0f1c02876add5e8a4f2b57415c57e853a","measurement_key":"2f1396269fd181b760afd12768a3013b9b0258be72affcf98223cfe8053ae9f2","metric":"pass_at_1","protocol_fingerprint":"bdb882a998352194414c2aef9eef02eb80c32a1557da285459625023f8b85807","run_fingerprint":"2df23e2db8828eba3d20c28679b9c9098932807a4df5b562ff8143a533a5d61f","score":32.783505,"score_display":"32.8","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f851d9782ebb319f6786ba101fb44ed4bb8c45939565232158e4e6dd17b1f23f","measurement_key":"7f0cf4c5fadb217b4fe78bdc81b68204282b904dfcdf23ccc8d8ccfad80725f7","metric":"accuracy","protocol_fingerprint":"47b086322cea7a838c624123b6623395c0092c49a7fe2ab74a7f76e2c70f0b95","run_fingerprint":"b69bd2958c1be3517037660ab77f5b9326a0a2d4f87a6b4f258230cc23432574","score":77.528,"score_display":"77.5","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"44085b168c2546e9ae206095ff7db51466af7dc6591a48e30a6a31f072e1da3d","measurement_key":"8eeb19701acce1658576dca158549551009a46aa6d3a0250242bbb6dbe054764","metric":"accuracy","protocol_fingerprint":"9ffde311d7c0a3135f7ec2b8fd421177fd1e875120978c7e18bb3bc031243d99","run_fingerprint":"d4a0d957f890f4325006867882a6e9c713e2ee763f4a6cf6d2979c42168b044f","score":12.121,"score_display":"12.1","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":5,"at":"2026-10-26T22:05:28Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fe499ad83881d82fc01995cb9df65adb23ec904f4be26a74b3e7713f317553a6","measurement_key":"ff579a9adb8ce69ff9a3bc24e44a5ac67599c4bc6c2f1e4411f5350f950befe1","metric":"accuracy","protocol_fingerprint":"346f0b7bc9db3fdad5926b9d9058c64eb39e51e991b0b5f0b35f14b8529ea12b","run_fingerprint":"560a7edfb9117250f2ef5c4af36d22e26979d177208604264bb7f59bc3008910","score":7.143,"score_display":"7.1","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e7da7006a2318a5911c7d57255f4def268193612452c04599c46916545e62add","measurement_key":"7874d9d37ccd69f8203c6747b763462d5273c026d16d22aafae62f0744f0e870","metric":"score","protocol_fingerprint":"0ba0f7ba05fb0ed5547d084d7efb554186ab22f9a38c91f0a0b9fbef5556b55e","run_fingerprint":"78b1f7042e6c0185a0fa14c7a80ac77093a19f652a6233b6241c0b72945d6566","score":70.395,"score_display":"70.4","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b99c1a9abb802b08ad139fa1bd2a24fea80cd145aa9c25f718ca8833849ca814","measurement_key":"37e8a3b3eb7afe0501a4fd3d23b115651181cf582f7e41b32f24c07ca685aa7b","metric":"arena_score","protocol_fingerprint":"5b2ccece8ffaa95d1b70052dfef45054d355ddad73d373b9b877bd66d5925eda","run_fingerprint":"98b9345a68cf987e361cce3c07146c29a435514f9c4639a2aad4785859fd92ea","score":1589.6728568868868,"score_display":"1590","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_45fbb04067e2dc09bef71f8c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"google/gemini-3-7-flash","model_name":"Gemini 3.7 Flash","parameter_count_active":null,"parameter_count_total":null,"provider":"Google","selection_rank":21,"weights_status":"closed"},{"cells":{"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:12Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a62e1a674f8346616c6b8d295d2debe3212ef032a1c1ac2e5fe98632d4258817","measurement_key":"3736a3ecd667f3bbb291770fb88efa5d93ea44b966bfcb695464b9dfe040eb63","metric":"pass_at_1","protocol_fingerprint":"69c1d7d460388b7e24674149491f6ab3cc4ae90f0f53207a3102d10de3d6409c","run_fingerprint":"c14a09655774f59dc545f7886f4f2f8a0c40221ce2f2f2020b67880cb9b0b3d3","score":63.3,"score_display":"63.3","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1718ae78cff960c44c0c9653","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b236ba8fc2b1a89c26c09433504365488342750717bc5271a16473bc42ef32a6","measurement_key":"ea35ad5fe289f90fd68d375013e7e2d28cebcbc4a9be53e1a00da894310f7978","metric":"ips_score","protocol_fingerprint":"09dbbfd1bda806f47a854e3ac7c53c0813923a4cc900df9730436ba9963a486a","run_fingerprint":"0677237f30807d75c2da925c279c1f0ddce6d3e8140612b04af4e72d2faae0a8","score":0.004482244232743595,"score_display":"0.0045","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b609cc1047aa681b2607f1ec","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7460a6453f421448616021fccb04dd39f1c5e3c4e259dc3badaa3a70848d69ce","measurement_key":"b0a09a905ab7802abd62828bd8682173657c2d2420446a5544772f2b47e85c2c","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"609f6433e57a85d1bc29aece0f235fe85e347e25ec12a0b2bf20074f9aa5e62c","score":1482.4121421338182,"score_display":"1482","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0d5bba5bc760b957bb971b9f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:13:49.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4643b669e36531b1cdf63f910dbd871bb348f1ae219c8cd5d122cd391d411004","measurement_key":"2e1916743e4aa8456151bc3a7f54e986cda5c5390cf61da373345aa53cf560cc","metric":"mean_score","protocol_fingerprint":"da5c828788732614f309d013145d55b69ccc1bea1615c3284266d8bb0db9d3f2","run_fingerprint":"d2c0c32a9b44d6917866a096ed2dadb93e83a7a6550cc64f91a4c761cf8672d2","score":46.0,"score_display":"46.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_9f288de94feeced4427eb208","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T21:27:01Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1662997d5c6379f07228b112d4a41cb90df401523fc7625c46401bd6e2703041","measurement_key":"d3ea8608113d9fc85ec6bd3b5ee8277c57a11bc94f0ac781047dfa77361526b6","metric":"accuracy","protocol_fingerprint":"8ae55df023be0e7f2e62d5823972ffd02ac3245bba85d29d76faeaedb4b39410","run_fingerprint":"2b65f6058a5b441123715c864e70fa37ed6067a3e568954a2a0bac2d1b71aa9c","score":20.0,"score_display":"20.0","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1718ae78cff960c44c0c9653","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dbfb894347faec92ba083ffdca70d7b1d28a2e973311086b346022a40449d2f7","measurement_key":"8378254d3beab5b760a39b306e884786a1335560ae82be64e4e404f4eae44c0a","metric":"pass_at_1","protocol_fingerprint":"a7141b72f5abab97686747a8f456230d9df3fc1dfbefe0093c97e1efe26855df","run_fingerprint":"9027b13ee5edc2c1d2b927df6d7cc4e6fd47c4cc4f9354b3322c513c60c50612","score":57.46102449888642,"score_display":"57.5","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_9f288de94feeced4427eb208","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d3bf594ec0b7f294f12db8659f24fa43e330aca3a4e6c8d2df3327cf64cb7998","measurement_key":"b429cde3c46c0131851af386b427f0b8b2c608b7eb6c0035e7b520e28ad3864d","metric":"eci","protocol_fingerprint":"5b121ef874ed48728f049425d72e52d7aca09a2b22b5530eae7cd4d9f740522a","run_fingerprint":"99968e904733b21c638f6d50fbe09a6d66c40496e53ccc51a913a827929ac443","score":157.98,"score_display":"157.98","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d877af62a921b2b206ad3009","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":88,"at":"2026-08-04T19:32:51.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0aa9fccf4b68aef41a6d1b73fa634ab51859d63ef24710e273cc9bfed1f9a66c","measurement_key":"0d7a2eee4bead288e9cbe8dc07398ddd47a090dc015ba95025223e36db693a65","metric":"mean_score","protocol_fingerprint":"7c3324d48b24f2962ccf8492e8bb7abd941cae2adad1c1b4cda5aac279ed9ba5","run_fingerprint":"996daf37bd8487671eb4001ab7bc11215b289c8dd9118e7ad129362b13250ac9","score":74.73684210526315,"score_display":"74.7","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_9f288de94feeced4427eb208","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":88,"at":"2026-08-04T19:32:51.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bba89c7c3443c9e0c5373fa0c859c6d7d98562010703b30eafa735bd7d884392","measurement_key":"909e4682153613eb8383d5713dee30176ea8d942a79c9c2b110c3ecc6d9ee628","metric":"mean_score","protocol_fingerprint":"994602caa30af06c383b9d649b7a2039606845c9ba9f3093dd42ace2159cb112","run_fingerprint":"15467be0f0b2838604e9164d845f830f5ee462293c0deca96d522701e7669038","score":46.34146341463415,"score_display":"46.3","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_9f288de94feeced4427eb208","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e0c218e6fb00729ff3368d15873f55a43699bfdf77221db167ce530d089a8a32","measurement_key":"ce9b1be5bc9edb952b241a559fed21e923f9b854ea7b2df339097a3447d9afd3","metric":"elo","protocol_fingerprint":"a1c5d9828d35cccaf99bfed5c00522b98c774b8b126b7cad63a4f827167cdd8a","run_fingerprint":"6452fe7a7931c77d667dba149ae1669d4752c5d8be7b375a0fc0902a0f01dc4e","score":1611.45,"score_display":"1611","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b6b0f9f89a407f75ea5e8b2a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"92b4ffb0b9d26cd7edc52eb6a2d0f8954f506f4dfb5febaab785fb27cde8ca05","measurement_key":"167683a90cb075d974df0c2a42e3e393ed858c41f09b1760ce4239b1ea1f487e","metric":"accuracy","protocol_fingerprint":"7c268612c5c83f2d6bf0e679778d3273d8611ab34d7f7d5ea0ac9b3afc56f162","run_fingerprint":"b493b3f7c7c40b773ca8fb90ad6862b107910affdaf6d80f1eb340bdec70dc52","score":93.686,"score_display":"93.69","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d8aafdf161c3cb55a509389e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4a07576103bbad4392d3a27cb30b24d014d7a0e0bf2baa62adcdb2cb648f09ed","measurement_key":"9dd4fbf5109d0b6965f04b3aafb69e239872bd957fc4f0a39a90a46f54c81035","metric":"accuracy","protocol_fingerprint":"16c4d8cdbec0efd3e09029bc345c875326c99fb0fe02090c1b765e95eb3285d4","run_fingerprint":"e2cc90045c78df263bcffda571d90a352f9f17b52cc0bcc99805e13e74407f84","score":43.04912,"score_display":"43.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b6b0f9f89a407f75ea5e8b2a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":47,"at":"2026-09-14T23:34:42Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a5f0d0da357c09b2b7fbb8d235494534293aaae0e22b7ea7e1a38307401c67a5","measurement_key":"64f5f23cee0bec35c94828575c694f2a4ed13a22a2b447ab0b0dc6904b432399","metric":"score","protocol_fingerprint":"8cebbcab44039bfeed0638029e038c696cb0b4b26037af01003e8061836cf8b3","run_fingerprint":"b74f12dd219b2c7b4bc2f5096ba1b9b28a382f38ba221bd967c3e1370c5b96be","score":68.889,"score_display":"68.9","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_dfe941467107f74de26697a2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1a373f3db0795cda3afce37d63778467ec1459ea1f6e904bb96f5d8b8442dc79","measurement_key":"6ed2a95a3a30d44d756bdb6b4e81c8c30a3f81d742009959eaa4e1b0e7995562","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"3671599ae555646f0a9c97e7e8f3003afea6f41ba8764dbd274a64c5bf5acbd4","score":78.46089285714287,"score_display":"78.46","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b41ea21204b5a7e098c39301","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"57cab98dcc9dd6df58101736eb9a5492f0e64df49526447e87a71fb52dd27f70","measurement_key":"fdf0f87cf99480d92bd30ea20956d68e450e29b1682c4e1d5676623abdd73bac","metric":"pass_at_1","protocol_fingerprint":"0deadf0164de399f3f8418b7c982fc6f516919472b3f8f7c081d190ae87f671b","run_fingerprint":"06e6076c44b9e1ce30034e63fc6e35d938720cff883d210ddb485c5ebdd5ec56","score":87.852,"score_display":"87.9","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a132c45f37998747339c62c9","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T16:48:06.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e2c936dfd4f9ebf123e2a73c3c9d7600fd77c458a27ce2e3d95620e3d479b345","measurement_key":"504f15943df41c7d5d3346b29339a746cf8068684bac864100521fed833611aa","metric":"mean_score","protocol_fingerprint":"ddd08864e99511b58aea5315dffaae5847523b2ab61a60c7f7407b498c073429","run_fingerprint":"d68639702a82412f3b1e6fdf3070772f7e02c3360d38dccdfb83cca41806c890","score":52.22222222222223,"score_display":"52.2","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_9f288de94feeced4427eb208","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"089709d07d950e4da395b05b90edfb9634c7f32001c5d8e5461fe71abfb66af2","measurement_key":"ef242615fef17c281069af334dad5b10430209cd3090d8b0180e3edef7cc02db","metric":"accuracy","protocol_fingerprint":"0b21cb8a5fb871fe1188b4cb0613a34c11f26970ba7a9ab001d219360477590a","run_fingerprint":"54375fe6a46fa7840e3cdc0e28a0e5d5e4d255fd5ad7422837e12c83df7267ff","score":88.602,"score_display":"88.6","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c9dab4aa7fa2f362d4a64f77","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:41Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8ac1f6bbc35f772917280a02cbed2c647dc600b35dae7ad4a9df2e34ee369ab5","measurement_key":"635fb1aa1dcf178c3c03ad342dd3135fb341f122f1969495ee3d779363ae2b38","metric":"accuracy","protocol_fingerprint":"b18c6e3f6d0c5344793766c2ab9defec2c5bf8a2bbd7159883f78828aed18739","run_fingerprint":"6a3a02191ee03c67a7edb8f4b466705f5d5467abd4d58039d0d8d0652424f30b","score":88.035,"score_display":"88.0","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1deffe7efba519db4b67e6e4","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":88,"at":"2026-08-04T16:28:46.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"95832a8dca438ec6b1008a8eba5cdccf5f7dce13ea76ce1b225148e1b01a9599","measurement_key":"675bb8cd8f27726c42b42d478868b56bf5569a9df2f693afe654ab0492aa5b0c","metric":"mean_score","protocol_fingerprint":"e63e8660218051fe73ec5b9f865c4b6e4182286cf8945c04ba7347e139856fc4","run_fingerprint":"6aad45fa2e71a993b38cf69a5971e530b6afc3f269eed2a0151adeee30980956","score":99.44444444444444,"score_display":"99.4","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_9f288de94feeced4427eb208","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"78e83cac0b065d0edd948187d9680e1ded773b771e9427c6d09b7682cd84f392","measurement_key":"1a1a65f6a327e9f2c55157cc90d4f9be72b595f46c272e3472490c4defc12a20","metric":"fully_resolved_rate","protocol_fingerprint":"46bfb827e85a5568bbe27fdb40973fc208ac66ea68de655ff415c90750dc99dc","run_fingerprint":"5769502f4107dacf0a4d1892f931429e6b6e675f150a56beeba6d09a1963de0c","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_89bf2183d1e84ef4c1347f7d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1bba2f38a89b396c90cf2d9f7ef381fd49818ddaf7c0b496bb4e5beddb03ebb0","measurement_key":"3f6afc0272e077402326cfc10317f6600c3fe42e2da8f65bfdfdc8dcebca8325","metric":"subproblem_accuracy","protocol_fingerprint":"a8c79cc3c4c00a0e4d283760bea23df2d04d38daa2bc97bc3c2fa3fc632b6df8","run_fingerprint":"5fcd3efa45bdaca870a22d1a6f225e605f388afe60532e08b0be369abe0415cd","score":53.2407407407407,"score_display":"53.2","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1718ae78cff960c44c0c9653","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:30:55.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f7aa13d239827cebb31c111d0abf1627169556f2c0416fff58d68df9a50726b1","measurement_key":"7e1dba6ddc548ddc17444a2040cb4e970860a06efaf8d4cdfb8a22015c1bd82f","metric":"accuracy","protocol_fingerprint":"3f9353637d7d4fefaf798304b12dacc4c53ba0e42ea81f1284993764f419ef4d","run_fingerprint":"f67a0e3b4b9a471caca177a4211e2588f51ca771a10df8ecd58d688c1901be25","score":45.800000000000004,"score_display":"45.8","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_9f288de94feeced4427eb208","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"skillsbench":{"benchmark_release_id":"release_ff4a6e288c3c17d588478b46","benchmark_version":"SkillsBench · Qwen comparison run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":81,"at":"2026-08-12","last_confirmed_at":"2026-11-01T03:42:36Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5849cc4cc83c700fb7dfd173959c53d369bd6504526768d924bcb8a67384cb30","measurement_key":"b7a4b2e23087026d517362e09f361313d17bbc14142304c6c1215c16e8fad39e","metric":"pass_rate","protocol_fingerprint":"5a87a249627548ba41ab1e22adf8f465931b323f1bc4cc1e11b5f7988d5b1a3c","run_fingerprint":"a2c923d59a904bd16ce46fb77f8585d4df9d2b251f29f53be9cc730557b5847c","score":70.2,"score_display":"70.2","source":{"id":"qwen3-8-a95b-card","name":"Qwen3.8-2.4T-A95B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B"},"source_authority_tier":"B","split_or_window":"qwen-vendor-comparison","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_646bb68a28e877c1466e9d75","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"acf295a70f88a54ecc55bd9fc570e516083783861bba601a4f8d1296756de6de","measurement_key":"ec2ff9d25e19c5609d81d7c86008fee87f97b2f7a51def4226802e5562ea8327","metric":"resolved_rate","protocol_fingerprint":"b0f08309744aef993faee12e36e962b3149e5630a4dc4bf7c56ac9978392fd49","run_fingerprint":"a47a33a73703130cf29462911e35fb47e2d415cb8beb2e12769dc270d37128db","score":85.6,"score_display":"85.6","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_5f68ba2f45063ad59689c8b8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"acf295a70f88a54ecc55bd9fc570e516083783861bba601a4f8d1296756de6de","measurement_key":"ec2ff9d25e19c5609d81d7c86008fee87f97b2f7a51def4226802e5562ea8327","metric":"resolved_rate","protocol_fingerprint":"b0f08309744aef993faee12e36e962b3149e5630a4dc4bf7c56ac9978392fd49","reporting_origin":"organizer","run_fingerprint":"a47a33a73703130cf29462911e35fb47e2d415cb8beb2e12769dc270d37128db","score":85.6,"score_display":"85.6","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_5f68ba2f45063ad59689c8b8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":90,"at":"2026-08-03","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1aa16913a61d676e6b9f8c76e9e2506bab57f3d4a591da2ca49b69238640cb1a","measurement_key":"95a68ab84032f015513c7b12e4e8048a38eb1c60b039e276f8794235a071cfc3","metric":"pass_1","protocol_fingerprint":"ed98c8443e3b747933fc9595ca5529c72ec372d970230b74353a8645611b5d55","run_fingerprint":"9d815173a6e2f7e9a1ec6f0ba271399a44ad3d9b3cd57853424bc75cad527bca","score":55.154639175257735,"score_display":"55.2","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_9f288de94feeced4427eb208","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"50690a5223bcc337fff22eb595a388954a6705a76d8167cdf8323275a08539b4","measurement_key":"24e6459caf89b6a638981299d68318958e5517e9bcb93918363dceec12928e55","metric":"pass_at_1","protocol_fingerprint":"29ee69f49dde555d2727d00f373c0bd81259e7c9bd82007665bd401de1d6542e","run_fingerprint":"74f3788b22416d2ee905cc0d46c5e3b6b9ec73fff2b2a9726d7c9971c0e5ce18","score":51.340206,"score_display":"51.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b6b0f9f89a407f75ea5e8b2a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5f388ee675717ece7bb3a1d5f82a548f5abb689c00afeecb3e60401553ab76e8","measurement_key":"7894760b7f0d359c8246891a7fade2e6540496d6649ec1331357454fa2894ca1","metric":"accuracy","protocol_fingerprint":"0351bea91b7a27ca232dced3bc5dc62cbb4600b62487dc632833f157f0ddcd3d","run_fingerprint":"9174d1a1997e8cb74ee390c1e042ba9dc1418469cc6560011ed02b416779e929","score":67.416,"score_display":"67.4","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_dad7b63bac0ecf821f75dc11","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b68803341ab4e279508ecc6359b714c2846c1174b1e8c683d0906b9415eb7a58","measurement_key":"4f814cfb582f84c740f2c7661c3c6aba262d25931c8313939a0cb5d6e3041d98","metric":"accuracy","protocol_fingerprint":"4cdfecf985107137acedd858b42df018a582dfdfe0e50e105788591c82bec0e4","run_fingerprint":"2fbe74097c7d197e5fbbc7146175b08a28afc8cb25b048c794ddb1840414d50a","score":34.343,"score_display":"34.3","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4c799730d8ed94b1c16361fb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6c71029faaa0ae57fed15e421b4336fc86f97f5f4abdd7adb3d2d828eff46316","measurement_key":"7c5fe3cfdb5f261c027e7ef779ae0cfb7ae4c889be806d513a348154a002baf9","metric":"accuracy","protocol_fingerprint":"d24a96efda541fed6ee85c3d0749d022a0a3a3e770a8b96ba60d65bdb1d15153","run_fingerprint":"444da58c91a88855a8c0deb7f48f271df46a7457922e8bdf7e9d4621e9781433","score":12.857,"score_display":"12.9","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_466a5cfef0b0a57e549962db","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"10c46a8ead36a8dac641899e291304a2f440db86124feb7feaed26d6e9cfe298","measurement_key":"2fa541053d0b153aa530231111c9be272b9de70432a22ed18fd5ba4becfdc7d0","metric":"score","protocol_fingerprint":"f1408e393d0b8c73582634616b65a1fd2f2e996e2ce024bdcd8bab6b8c5d794b","run_fingerprint":"c651f21f6a2113d88db9c9ffa17c8bc355a9b168eb4de63ff16e0d771cd13217","score":64.696,"score_display":"64.7","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2fef4e63c947b0e5bf3ecf53","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0e69ac5614d9f8822e2bf0f8a7cd41adc92ae1b8202a4b82ab12d5217c336403","measurement_key":"af9cec8dcaab4f1619ca0062849032db8c5d0e7f2df814caa71a51a8964d5089","metric":"arena_score","protocol_fingerprint":"528c2391cc358fca591e32e44ce271af10ce34b174043108968d55c4fc07ec51","run_fingerprint":"13fb00d0dacd44a6370183d7ce8b842943f6c62ba9147d4c0c7d9bf8c78225d1","score":1671.885286248237,"score_display":"1672","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a6cfdc05f4f1b956853cc974","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"alibaba/qwen3-8-max","model_name":"Qwen 3.8 Max","parameter_count_active":null,"parameter_count_total":null,"provider":"Alibaba","selection_rank":22,"weights_status":"closed"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6f7f230d692c8fcb0306980b22da27c56fae0834d4963689f2c1720e9d52c7a0","measurement_key":"0e7570a7289a82812d78827f238a526a950b5febd57d6e3d9f6b99921099479a","metric":"index_score","protocol_fingerprint":"a456e0b71d795210e1107460a5a9ce59ce52b3d0a32670c5cdfc96e5d55739c4","run_fingerprint":"423d75f4c16815c6ddcd3f1e86e42fc6df053ae81e167781ed1124f7a0f6882d","score":30.546812,"score_display":"30.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:16Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c11e03d51037548366a630fdbb47629fc69699d98c8b174e926f9a6a3f53285b","measurement_key":"b3f7f7fc6bd243ad285bf273b1c425a40fcce84c9fbf9c4bddb448ab667bcbc0","metric":"performance_rating","protocol_fingerprint":"4f3bf61e93663a340c7327d10cf822d76f59e596b705dc5911fcda0e91cf97e7","run_fingerprint":"c5eea9c76c004d490a3ee87e13bd65573688ec82ba47d3ef26b04b7e6530858e","score":1269.72,"score_display":"1269.72","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"64a03181fd9388cb544c8ce58c8a9e76c45a974aa69cea60c35ae1b3557520ed","measurement_key":"060c78f867e53a40fedade68068db4c21df8a0ee315ff9994c7e5bba04e99466","metric":"pass_at_1","protocol_fingerprint":"d1db83c8635ab08e0fd6f42727ac51e27926360388397753feba6a0c62b75375","run_fingerprint":"218aaa355128f79980e1f008a3d87f5cb4dc678b9273259e4e3256a1fc4569cb","score":64.3,"score_display":"64.3","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_51f85ec2f1c37d020adb2824","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:14Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c22c92b8df5a490f45a7b4cb6909328d677abc7478ee1cf47d3a000e5bfdd6d9","measurement_key":"4971415ad0c3a3a387846fcc991b1158e9734e8432d91b2b8f1f21f3db275f99","metric":"pass_at_2_accuracy","protocol_fingerprint":"17db96e23ddf00b6e41df1eea85980d0ccabbc8c9964e066d35e3272a5fa7a38","run_fingerprint":"cb896567d6622bfc7251db9ce619afc49ab243d3aa8d32c0827d2f61572b0245","score":98.5,"score_display":"98.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-09-30T18:53:20Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"48431d219c6d7971ec81e59fae72a7117a3439271d21f58519a824d9e965d317","measurement_key":"33112a4ea1deb1f74a557066ba9effbaf9ef6735792d2a61167c656c8021a45a","metric":"accuracy","protocol_fingerprint":"4adc9966b4f2a764c90a6ac1a6cf7f028c814f9d7576eabe5c7198b7d98f41c8","run_fingerprint":"957931474cb6458de726e16f61d5c8c69855bdfc4b8ed642e01125595ef65466","score":89.16666666666667,"score_display":"89","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"064240a7b13a958c650b93bd79e2b5fb9749133803215982b77e9973bef45f12","measurement_key":"9ca107431072822ee9d131cc11422e559b7d8d2c63183e2b058cf29867684236","metric":"ips_score","protocol_fingerprint":"b073c19fb3796e4d64756f6f913a7498a97ddf1bee81a4ec61daee204a62d9f0","run_fingerprint":"a26abb6893d940023cda5ee16e3cf73cbbda5f993af823af4afeeb99c1c3e263","score":0.026495450925865173,"score_display":"0.0265","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9baf7bd7b9b206c75cb4c0377e5975d1bcd936a9b139183346b31893c93df1f4","measurement_key":"6a3543aa174cf929830b6cb5936959d085391cdfb5f8f2a9c6342f07edeb0733","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"800447b476fe890ce244fd8a666391f80d2c2e1071637172582f331a3ec4bc9b","score":1495.9450931791241,"score_display":"1496","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T12:39:05.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"53c6396e58a7d13ffa576e4b89c351b102d87888c7e9326f302c177918ad753c","measurement_key":"1ae47bca638d565ffcb6a55efea0b5231a8573e788b374676e0929f92c386d8f","metric":"mean_score","protocol_fingerprint":"86392548d9c7be0dd49e24dccf71a143090ca81ca435cb34f7d75388d3c6b430","run_fingerprint":"56935ff99f09ab44f32ec42ccd0d4abdf5a98ae3d617c7b043317381a3186352","score":57.99999999999999,"score_display":"58.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9b9406005cbec6f7edd3ea2b48cd5fd2ce9d42d00f0dd500f2a4414d209c7431","measurement_key":"003b4329ed998e1180d8bbe9dda1f68cf97200cabba4e0be786057677c54e340","metric":"accuracy","protocol_fingerprint":"db92ffb6647156a3f7a53f013696ffabbd5e467bfccdb9fd1169caafb8462bbc","run_fingerprint":"e998643de2b3f5f01c488fc53d411e939727800ab35994922defd91ce122d66e","score":18.2857142857143,"score_display":"18.3","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"cursorbench":{"benchmark_release_id":"release_9acebd5b002e9c3f18a30606","benchmark_version":"CursorBench 4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"32fd2fec306edb96ea5bb3025a1bd4f41ab097b1b20aa0110e4676441a51fb8f","measurement_key":"295beb0b91fc37c5e8eaed34c006869979b311473feffdd67eef26c5a05a1286","metric":"score","protocol_fingerprint":"8e4831fcb7f1529b499ad06448224021e0de9d56f07a8d4b6d660034f45e079d","run_fingerprint":"32a0f9048717254aef938e84da5409c858531c2fef97e760dada72efa0b659dd","score":39.6,"score_display":"39.6","source":{"id":"epoch-cursorbench","name":"Epoch AI mirror · CursorBench","url":"https://epoch.ai/benchmarks/cursorbench"},"source_authority_tier":"B","split_or_window":"official-current-suite","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":59,"at":"2026-09-02T19:00:09Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0ef64a9deb630477bdb9934a18e2c80865dcbb13eff92446b3e52ae56c9edf2d","measurement_key":"f91f7b89c3c98adb42cc4dce3585b461bb3604cb9aa8633698de88b976b28ecb","metric":"pass_at_1","protocol_fingerprint":"bb706fd403a809640e72b3480dd7b01fc30d05d6a6ef39a0eca2982aad7ea2f5","run_fingerprint":"f991d213bad7176a6025690307b002e94cf1fc3203f20c047473105c96d32976","score":73.8255033557047,"score_display":"73.8","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"77968597608fa7aa15e90dbbcfdea3ea59949f57e9070ece7b115f4ca04bd11f","measurement_key":"f19ddde1de3917830c690a777400e73ecd00e110985d612116839c27bd358efa","metric":"eci","protocol_fingerprint":"b35cb1b50629a6306d4df1f211a6fea82770620aaeb92502763c075c1134f73e","run_fingerprint":"d686ddd315e19af6f5cc38d211ee1910951c639ed16980b86be4be493905e64d","score":157.64,"score_display":"157.64","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e5abce6ad7b99a4c5dd13f88","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:01Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8131ec43c04f482ee5ba4f68a85ee3dc18f19e7b965d970edac1a8c3178bd184","measurement_key":"7edb3f5063e1c78a1fd90b4893f1a4b5be39217f5a8ca57e6a4e275e472977f1","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"e13f7845f4e5319ac18544de8a068a724cb9f1029b61ea5c40bfe7a7a860dd87","run_fingerprint":"415a858cb747cef45281a0f7ec73af0a9aee4cdf8c02acca28c09ab85009c55e","score":41.19,"score_display":"41.2","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_eb17f29c7f8397dab70e09d7","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T17:15:36.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8560cde5d38851de3905fafb44661198d8c475201cdfc4b523d05fb9f41ad27a","measurement_key":"fe6d934ddbadccd1f4f8b5083ab95288a8f3ed05f78f4aff2cc15a394dc7f65d","metric":"mean_score","protocol_fingerprint":"fd8b819ddb1e17afd50e047bcc1b8c90c78e246dca57235b7fcbef49bd394df9","run_fingerprint":"58240594590e36e7d13b65be12128fcf98cb0b93b9cd54a64875d13d7875f405","score":68.42105263157895,"score_display":"68.4","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T17:15:36.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bfb8bf3d0315f5c77b2de0afc4c4bfc5a1358d3c8cc796c7527a2518607a7bf3","measurement_key":"171e8d07f38329ed6fe47464b9a21d8c54d7332d3f053e04383de9f2632c1dc5","metric":"mean_score","protocol_fingerprint":"bb63df4a7cc1a4736fced56d574fdc35e3518f8449aca663fff044b6db3d874a","run_fingerprint":"05be8d381c7c72ef2344e4a734fdc7542a4d7a88124af82e7aad038f7707d51f","score":21.951219512195124,"score_display":"22.0","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"21e05b7a97583cdc9c9cc8b16b4373f92f101c0f01e210cd5d3f2a72f436c80b","measurement_key":"706cdff8d4951d341036e8c68e67f521845fcf52c50ce26d891db772b3ca3425","metric":"elo","protocol_fingerprint":"b063799c2fbadd40a0364ea59f31bd847cbbc1211136c30d0ea42ed4dfb677ef","run_fingerprint":"c62b9a4e1a3cef0c3c472ca5753a109b240e9abb32e876fa3af54f6e1fc2478a","score":1445.43,"score_display":"1445","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T19:01:46Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9a8061a3a1b4af2e9173e7f60f9f9aa31c4b8971588992065d56b4952925b360","measurement_key":"5b355870491116ea7bc5eb0d7e309830feea30e2f0477934557f77376a18b102","metric":"accuracy","protocol_fingerprint":"f9dbd2529835217eb544ff449b521be800034aff9e3f0dfefbae323c543c442c","run_fingerprint":"55ada339b371c7c74edf56f40a4726b14690f43ce6ea53fc7ea9c5f6e931f05b","score":94.444,"score_display":"94.44","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_8817af9d9a0235bce0826e22","benchmark_version":"HLE finalized 2,500 · Scale protocol 2025-04-03","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":52,"at":"2026-09-09T19:01:48Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1f8e5dbd07d3ce0d416d206da5fd27c020ce044b8300d58024c16068fa8c63a3","measurement_key":"21dc7f060a8bfd15469522be0fefb829c0f9854f4114d511f74cf9bb6cf69761","metric":"accuracy","protocol_fingerprint":"1ba317776e39052318754ad8154464f07f991baae2c2b3f38a8ee0547213671a","run_fingerprint":"68764dad01b009ef9f8368210b6562547b6cfd1f8df32a8938518074efe65985","score":44.52,"score_display":"44.52","source":{"id":"scale-hle","name":"Scale AI Labs · Humanity's Last Exam Full","url":"https://labs.scale.com/leaderboard/humanitys_last_exam"},"source_authority_tier":"A+","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_491d6d7d0d5b0ccd98ec2ae4","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"72d247f16eacd8431ca6808042c6969a28e3c5f1adabdfb7ba6c253fe56dd122","measurement_key":"b3f6f79f8238d3e46aa8d5d1b3ac00d2ee6b3cd28f92c2e5a30c93bf0ae70774","metric":"accuracy","protocol_fingerprint":"0d2c4161fd21057ae8cf2e5ae5ee148326e3b0e3135eb8a06a3b8b9b5f989ea8","run_fingerprint":"7a9fad8f5a6f750b218e91c5cfcdc9a0daf8595ae62297c2e3db01a34f2367f7","score":47.822057,"score_display":"47.8","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T19:24:33Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1919524c2c4a77f08bd9d2c0bd7f9e0f4d47b24e14bac372f5b816315b3bd1f8","measurement_key":"f6212597a1212bcfd4e30df38903a36f06f1295c57938aceb9eb5643c16e7469","metric":"score","protocol_fingerprint":"f17724c3bb48d0519fc2fd15feeb5705b2cbfddd9b5b7f6949c1ecee799fc396","run_fingerprint":"91c5ee7dfd069ecb8cbbcf68c42021ca1516bbb89e9160c396d225a86d69bfa1","score":56.944,"score_display":"56.9","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":59,"at":"2026-09-02T19:01:19Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ce40800b95539d3cc054c280f26d430b8f6b47f7084b2ea8dfd62c192c1164f6","measurement_key":"1c6d6e51288f18c1f9adcfaadc13fd338088f7163cf7cfbd9acead4631e88c1d","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"10f5a1b749deb65e6a21343eb1dfca56922166bbd62d6c17b19e398811252200","score":75.82852380952382,"score_display":"75.83","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T19:01:50Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ddab518472d9e83901b937db72475625c1544beb712e628770ffdcef18488efd","measurement_key":"b1dbcd392fe37c17083be2ae19e724aa0785b92aacda0f30122da403da6e9f94","metric":"pass_at_1","protocol_fingerprint":"e1ef6b16ab215600262ec2781d984365cf2d293c83904b7214d797c5ce9e6625","run_fingerprint":"68ce26c4a46f204b4815df0e911bf053488852ef3782352ad2147c3ac8679c5a","score":89.484,"score_display":"89.5","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T17:23:38.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ac1ce81702d2261540ab88fa83b0081c9f9cf16a05721992cc41bc19d0177ea6","measurement_key":"b3b108cf6c31844a551fd0993019bbb2723a3271150b58b637ff3a4bffbae534","metric":"mean_score","protocol_fingerprint":"80921b9acb99c020d9f8a8e498bf0cb8d2e96147c447722eb4b9c3345f038061","run_fingerprint":"63df43edd2b51a3fddf01283ee32358ee8b4bc789896b1d50c0b20a6c4a483c6","score":38.88888888888889,"score_display":"38.9","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T19:01:55Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e92e0517107a1d5403a6757754ad9b12cb493f05dcdb0a9017b9a4b1b0ca0e70","measurement_key":"fc31d15632fb0c1835adaa28a9f8ca1c1c85758a83c4bc806260ee8fa1936ccd","metric":"accuracy","protocol_fingerprint":"ced96f8760d6bef29d512a74852888e06ddcfeb5faa5c459628c337f13667018","run_fingerprint":"973b1c93671fad29bbc938c594a5796219b376d44ea122edaabb8b50846377e2","score":90.221,"score_display":"90.2","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"af7c015b76397e930dc220e7d1e8794ab0057f4f5f943c8b21b92733af83b7b2","measurement_key":"516f318254b300bdd62dd1be62859f0614c5bf1d5cceea90aa60c687e45241f1","metric":"accuracy","protocol_fingerprint":"b28886a06155ebea2908997dca972f96c6ac0851f12bca6109b614d63993176d","run_fingerprint":"39d80cf64ff7626d6459bb1a597d7da158c12a96b35d15574b557880d6d678df","score":89.075,"score_display":"89.1","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T17:15:36.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9e968784e0e19a3dfc8afbcf898385171b68d4c19d290782238254ba96a00391","measurement_key":"17b7f8ad29d02f42a99193c4c7f88412b4eacb928ceb840847e103bdf7d8e1ff","metric":"mean_score","protocol_fingerprint":"b42224bdd5801441ea632d9fc7232b935c6196270e058988ee5a4bffa469c6e4","run_fingerprint":"dd44165ebefaa49b7788de913da0e6fa2f7b7e2cf5de66918bb04cb034e0decb","score":98.88888888888889,"score_display":"98.9","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ada3457d22191d16e035a09c8d61ccbd420546d2a42e306530d3bf3b98d917dc","measurement_key":"85e876b4beda2367536032db9e97b367febc3b42738163b9fe99ccd8ac762466","metric":"fully_resolved_rate","protocol_fingerprint":"fce468e50c91a38d05e6a0489790c14462f16e1c2d2f95598199a0cec501a7f7","run_fingerprint":"5655c1785e4564f276016c7eac6c443eef1a4d678bae0c7c69b3e79f508f0ee0","score":1.0,"score_display":"1.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"792d38aecb3226b480a4dd3fb9538c168116026b2d37487294effee210dd1193","measurement_key":"bab7615b7ac43f1e3566ad38b32ede58504d446743c52a83dbfc6ed9cb9ebcb2","metric":"subproblem_accuracy","protocol_fingerprint":"0430452b7e8bc355286326ef670886234ae3e58c8aed15ecdf1b44bb26deea9c","run_fingerprint":"5944950d05df568b58d18046b800cf570afa688e97dd2a0b1b2754c0e6c0a13c","score":56.5972222222222,"score_display":"56.6","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T17:15:36.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"815a62bf70adf8ba87b4e46333c767a5841861100e22aae0fd99538a6260092e","measurement_key":"31b15cd2f3133c6f98f7e79f0f7a17c1b837cb51582fd5c948a0b7002eebedcd","metric":"accuracy","protocol_fingerprint":"addbe5e3a24d08a8962ffa2f57bb6b6881faef74d4cde0934b7d57db69e9d41a","run_fingerprint":"81b0bb66980faa473aab681bb2dcbf7abc65fc2c98047a1c88cc5bbf7ee2291b","score":69.69999999999999,"score_display":"69.7","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c3d89238e8102dbf6f2c841af46dfd8c328c3df9ac3c2f86504e3d230c9d1b15","measurement_key":"713b3b6b927a0ab64efa8359742a34c5adf4217351aac3827452c94dc8f15ce6","metric":"fully_solved_rate","protocol_fingerprint":"2f4cb7a86dd755e3a7c0ce47fd7ff3c19ba06e8cedb681d78fcfae49724579b7","run_fingerprint":"d6ca4420150911bd22bfc68c5270dcc92ffd9184cd1559a1a21cd68d8655fd4e","score":11.069,"score_display":"11.1","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-pro-v2":{"benchmark_release_id":"release_d9b58bd286ce316ccf0ed891","benchmark_version":"Scale SWE-Bench Pro V2 public leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":25,"at":"2026-10-07T01:44:58Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5719adaa3fe6a786e1118e9068671ae70b846e92d540c7fb05e44d2a3f018562","measurement_key":"43e0d5b2dac90d5a0f3cc75acea57dcbdca270b1e8a218ce151b6d87c06a0ae4","metric":"resolved_rate","protocol_fingerprint":"5b86cd3a00917922f68a2215a5e48bd262028020964ee00fac7b95dea20ea1c4","run_fingerprint":"456dd5396fcb90da9e7a262a266574b79f1c188f290cbe090bd1f0d92afca70a","score":94.86,"score_display":"94.9","source":{"id":"scale-swe-bench-pro-v2","name":"Scale AI Labs · SWE-bench Pro V2","url":"https://labs.scale.com/leaderboard/swe_bench_pro_public_v2"},"source_authority_tier":"A+","split_or_window":"public-v2-642","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T19:01:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e3e3082b41054ee38b51f80e7c759d8994c6abbef4133bc8c7b4b4122fa554e8","measurement_key":"1a65222b77b88baaf041543f0e0a6b1a555fa69806aa54b0f5462457424817e3","metric":"resolved_rate","protocol_fingerprint":"e418c746c9fd4e8e79df63f385cc082729673fb65ef8b112edfcd4f7ad090bc9","run_fingerprint":"4361c8c54c29cb2474622e1417a28e3afd235da84b62de4b1d195b50964c517f","score":80.0,"score_display":"80.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T19:01:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e3e3082b41054ee38b51f80e7c759d8994c6abbef4133bc8c7b4b4122fa554e8","measurement_key":"1a65222b77b88baaf041543f0e0a6b1a555fa69806aa54b0f5462457424817e3","metric":"resolved_rate","protocol_fingerprint":"e418c746c9fd4e8e79df63f385cc082729673fb65ef8b112edfcd4f7ad090bc9","reporting_origin":"organizer","run_fingerprint":"4361c8c54c29cb2474622e1417a28e3afd235da84b62de4b1d195b50964c517f","score":80.0,"score_display":"80.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dcee4e224d8b350c452a2a1ea72bca5c4ce683d934dae973d4f1095bf2b49c7a","measurement_key":"9d321615fe3352246a27a03b3bbcda14c53d53af9245fea64c053c72296355c7","metric":"pass_at_1","protocol_fingerprint":"4235fc7207c75ee04a543d4681312f3f8efade84a225648c6214468fe9fd6aad","run_fingerprint":"62f133a22b477e9791702bd70689805075a0b7b174ea9a795c4a61240d77954b","score":44.948454,"score_display":"44.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"649f040d7d44909fa0dc706cae401dea6a92a0ea5b731ab95aa3f9540362a966","measurement_key":"2d1b72625fe9decda466b1bfe02cf9f9d5f7e45c79f4d42ec49e186d4d5bbe30","metric":"accuracy","protocol_fingerprint":"b6260bfa498c9c9aa873df3331d3a5a7f0bd99b50f8145c96ab8f9b57d28e262","run_fingerprint":"7a0e8c97cad0eacd1be7d2bdbfecbfe86c62993ce3fe425889cbfa3ced747574","score":81.273,"score_display":"81.3","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a6a0bda4ed7ff6cb065249cf428e830e5584235204a34098e8d4caf7cd1692b9","measurement_key":"2e49cf31289c89cf3589b6e6e5bb0990f97e5b9b4fa5b73429c42a1579f803d8","metric":"accuracy","protocol_fingerprint":"156ae98d4ed1eeddbb768c263150f414c887cc09625e11b2003c44390d1a28f0","run_fingerprint":"1c5aa400b0180b2efbe425305990eb1ac3c36852484996e5613a462bb5ca4c62","score":19.697,"score_display":"19.7","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":5,"at":"2026-10-26T22:05:28Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a7889fa105f8a1a96ad0e52bf51278b55a3eae85a8e78da136c8c65e33cb11bf","measurement_key":"49a9020528e62120cfdcf494e3da9d2b82477f074f1f2216f0f4db76ac3fe3c6","metric":"accuracy","protocol_fingerprint":"8b6d70e96179336c971a9c15e7d86e28b71f07e2bc902b6379552a2a99e62e9a","run_fingerprint":"2f028da222dd86a41d55ce855ac03f2c0b3072fee82955148528b0c43e94db64","score":8.571,"score_display":"8.6","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:16Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"23a0ec63a24a1b8745b9e1b4c957cd828f15f561a23ec602f55db3be766420f9","measurement_key":"54e1833dcb61474d1c9fd7ff0f47b8e8db1113d9c81c1bc1a090851b1f47f744","metric":"mean_final_balance_usd","protocol_fingerprint":"97b9872436953baf92d74f92534fe81f89f3cce8d3f8233af47bbf14ef27df99","run_fingerprint":"587858129d9a12a342dcc4d19abca899c72df47653432c81f808317d36957a94","score":5093.793333333332,"score_display":"5093.79","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_cdf54735b765147ceab18bce","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7fdccf72fca10e02341cf2e0966bd71d68ff65dc18a0de8e162904ac8a581365","measurement_key":"05b153a083ed1382d79b1dd8768bb6e2902b5dbde06c44a7fd2885465dd09932","metric":"score","protocol_fingerprint":"c0979d1c41a9b6329d8820128a77d592ca24e49aa0fb7f696fbf3cc1e6466f11","run_fingerprint":"b0554fb7d1afbac6c13e7c11047ce0ace713feed28fd160929747ef71b0cebde","score":78.651,"score_display":"78.7","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6ce3332183e90b8568918a0cf2ee8031993b11b71727d9ab6d6afad5da5e09a0","measurement_key":"8f67d07f1b03c78b7cbb1dc5468275a0299db1479d03c1140f1d93b9e04df492","metric":"arena_score","protocol_fingerprint":"a04234ca002d2adff74fbdfec3209af34f7efe4323facfb4546a0037dda2a2ba","run_fingerprint":"cdc4d4fe95b920ea1ee3ae0fdf1239b05f11adcc90455aa23af6754086045f41","score":1583.2994176433617,"score_display":"1583","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:14Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6bf282189000dae2fb90e20fd195e6f6f2ff908cec3a1c848dd879295899d666","measurement_key":"f98551b0691971b067271787f7ba206805ef62761a053a1fc6327ffeb9ab26a5","metric":"accuracy","protocol_fingerprint":"3f9527302727eff742bf8f86a94d09a94a1c2ef8b6eb4e56d7455511ee7ff882","run_fingerprint":"632052bc13c415ad922081735ca77983308e8abfef8c388c4466f95df28f7c7e","score":84.81,"score_display":"84.8","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6aaa24a51270a2b1eabe94fdfd22ce359568de6a96fdcc8105568bf5ebbd6834","measurement_key":"ea3a25f06c2a3b3f3f46b14be3cbe4d908dbf36c07feaffb9c3909463e8cbdce","metric":"token_efficiency_weighted_score","protocol_fingerprint":"05f1b4b7e2df102c6c151f2f369492684f7e9204759e7d61eb444470c95a105a","run_fingerprint":"9b5f28438d911994bfc94d3d8fbd434c6f8a76750ce3649dbc814aecf10b5064","score":7.378749090909091,"score_display":"7.4","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_6307c6a5c62851b4f5c8d080","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"google/gemini-3-8-flash","model_name":"Gemini 3.8 Flash","parameter_count_active":null,"parameter_count_total":null,"provider":"Google","selection_rank":23,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:15Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2bb027b76ca04e8d629283947dc81da4961264e9699432278533bedbffe6b250","measurement_key":"9034f4747e3710bde33207b6ad94b6727bb91be7ba3f8eb8969ff52e6fa90a05","metric":"performance_rating","protocol_fingerprint":"75eaa8f3b1327dbc8faf02c4746ef0fbbdc707a0bcd4b9f0f58effcfe62d76c1","run_fingerprint":"d7829a34a125b4c19450a08c957b580e68b16730433d1b29136b348bd9335b07","score":1688.35,"score_display":"1688.35","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_78f4b55ed67e2456efcd3bf7","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b71a4e174a3dec3509b89841136c2afc4ac691872a9da7e5dc3d8d3a9751f9bb","measurement_key":"a896499e242d0d41e07d18933412a61189abca3b539f3f6aa6c523090cbf3433","metric":"pass_at_1","protocol_fingerprint":"6aadb29e85eebf458048f55a590ccc9fa76c1dc147d10d20846944209f9b0a7e","run_fingerprint":"9c246ad76719a109c561e59999641d0ad7033b2c0502048f62f2411ee0835c76","score":47.6,"score_display":"47.6","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a6ec8c3d77e3a16ad86378f5150ff1b425c0e139334db25084b0ef07366e7727","measurement_key":"3c6e8ce6e72fad156699c8c1657efeebb948196c40add48d71c9cb964fff0383","metric":"ips_score","protocol_fingerprint":"f68c48e1bf9af85e5a4b5469ffc59c4e300fd54024f5c72e96f7b077bfd95ef0","run_fingerprint":"bba25f4335124747ed80c315c5108033216c6bbfe5d92b6a06263b2f6547a54b","score":0.02593617325354452,"score_display":"0.0259","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0d1e23539ba9854f771633c91f89e306f8cfd261e5fe56d13cb23c3fedcffde5","measurement_key":"480b21098f2b148f34e7377c26f9b9f2a36a3a87aebb7b6541177d25db85fc08","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"aacf7e6fd53371bfaaada37d3764500a134a3743acdab54ac504ad24259567ef","score":1495.0456185334651,"score_display":"1495","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:00:28.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b7204a756d3a9b3d63fea3612bb18279a7ab9361bc03ae9dc07e1f924b2bdc39","measurement_key":"9b3f3b1407e59a1a4bedc3982cc9095279d91b7690d34edd3bc6151f8afdb651","metric":"mean_score","protocol_fingerprint":"698ca93537a6b601724ce4496086bea739fec21a751e296a8469e2a2b9e537ba","run_fingerprint":"5e780804a6a1c350006bc56fd629a215b41580214b8917fe796c1e86be4e3b1b","score":37.0,"score_display":"37.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2295e1731660cbb7309aebcb08426b3b93ad74b8805eda36932504b4075bb79d","measurement_key":"67d332675fddc7717c734d4c1a1d770f328fe0f4c2ac3949e14b4d7e60fb08e6","metric":"accuracy","protocol_fingerprint":"b55d42e298f853896bd90e96318536c810e5ef1b11c5a0011741a4c8873f913d","run_fingerprint":"559e83a6bb6a171b657e908173e5851521c702f2cbcc499a3a65c87b9a367a9b","score":24.8571428571429,"score_display":"24.9","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"cursorbench":{"benchmark_release_id":"release_9acebd5b002e9c3f18a30606","benchmark_version":"CursorBench 4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b550f8a3ba550c58f623dbde49d424e0a6ca9238be853a682b81f14c247f5a7b","measurement_key":"541198e04bf0dfb270c2d04c48a0390f60b26df1f6dcfbecbe099cb36a1581fd","metric":"score","protocol_fingerprint":"85242df049ef2b8b8c92f012e1abb8da0fc270a93b0880d2d566255bdc48607d","run_fingerprint":"ae0d1ba853339780fdfa71563fec850aa1e6582692a820dba46b51777e5f3c70","score":41.6,"score_display":"41.6","source":{"id":"epoch-cursorbench","name":"Epoch AI mirror · CursorBench","url":"https://epoch.ai/benchmarks/cursorbench"},"source_authority_tier":"B","split_or_window":"official-current-suite","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7ee3d24a02ce0fde60178f6f54714a45dfa5dbbf314061845e0e0c9edf2d6f96","measurement_key":"d6c5d14fd697dc70d27d232a2ff72b05ffd5ae52f283eb7b7a5637aaafc02193","metric":"eci","protocol_fingerprint":"12ffdcd126c0012251bf3a62e3b8bf5363a2b3adaaad2f1f8e42a37fb06f5901","run_fingerprint":"753b599241289ae7dacfa353366964e03357eef6bb096248e0a72975aae5fd9d","score":157.37,"score_display":"157.37","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0af9228b335da865d7243f2e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":43,"at":"2026-09-18T16:34:54.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b3389729fd1736940b7c2274391211d137c84405fd0054c106f797739f2e42f0","measurement_key":"a1fa9f2e1a653c6c6ef20c18b547fb74e3cb5d83d37e0e112e28b25b8ae75156","metric":"mean_score","protocol_fingerprint":"86c9feb2114dca3e6138829322e72fa076845a3cc3f734638a7c5460af8e3d54","run_fingerprint":"d69f81477ca97cfd6f7138d96f5233b350fa7ced44de95206ff6351eb0be9021","score":74.03508771929825,"score_display":"74.0","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":43,"at":"2026-09-18T16:34:54.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7e7549405a9339a1999f97c9cf2915f382920af91948cebc7f146860d6b1d2d1","measurement_key":"be6c09c447a7bd76f832f69428d5e7eba9d59ea4d4d0594063be7546b6b9478b","metric":"mean_score","protocol_fingerprint":"e0c81ff631e2766c70cd005a9495ad590823b345eb9f683bc4bd3141d697ea7d","run_fingerprint":"f966d5dbfff7f2ab08413c6b1c14e437c7100d892ddd1a516d9a95a6f8877be6","score":46.34146341463415,"score_display":"46.3","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-09T04:29:27Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f69148e126e31db678b1c96bd10a068da927100c7689ab158eae1b0d7437b7a7","measurement_key":"89080a0bd533ec0a54e150443bbfec4136e747af3a14d717e985e6f78a76d321","metric":"elo","protocol_fingerprint":"a87435ac4b12021f4f45aaaa031ef9013ec6da5155bee6e5f702e647e498850f","run_fingerprint":"9fc30eec6a043378624ecfec2393a146d1223c908dba7ac3df4b86320d5b6b29","score":1680.99,"score_display":"1681","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_f83cfc2a9e19b8d654d7b58e","benchmark_version":"GPQA Diamond (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-10-21T19:24:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"186c34c546021d551147900115eac98694cdb647bee4ba9fdce9b7a94016fa6f","measurement_key":"6c3f3022c5eba936c6d09db33e70327b82be5f552daef13d1ae98f08de039921","metric":"accuracy","protocol_fingerprint":"c6cd16978a52d1fdf8289811fc0a789342ecc7c8bf835f4085d77ac568a3246c","run_fingerprint":"88a3216f0bd124e0bbbe276c53ade1f0a1ab894648df2aa9b2e19f2c89162ffa","score":93.535354,"score_display":"93.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"diamond-198-zero-shot-5-repeats","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-10-21T19:24:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bf7547d8ed42670b39f2177ae22a5b64a522b0bbd72f0e51f54b932bae82e281","measurement_key":"c5818b7a55d4ae7944edeb1ea0bd1a5b950c46185d6991f76dab7baf6eaf57e7","metric":"accuracy","protocol_fingerprint":"d21ce42d35c7bf3d753ae910b9a95833f4ea328b9c3c09d906855b4d95d290dc","run_fingerprint":"0dce3b5b6fdcaacdfe636c10ae5169d373622a11dc81c28cbe763f22db7ab062","score":48.702502,"score_display":"48.7","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0d77ff9a9623b58142d669317f18f01813bab0c55cfecf51e93df133870c100b","measurement_key":"6e0106533b5044c1f573f1f5dd58d81d26c39021570115fa769b0ce1aaa55d61","metric":"score","protocol_fingerprint":"b73cb9cfd5772c0b4423de958b9d9b06ebe958e61dc8b01dc63fd59a05594718","run_fingerprint":"1d719a9afc7b43bb172ed68ee1b7d1c9c14e3e967aa3ebac5485beabb44544fa","score":56.556,"score_display":"56.6","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":59,"at":"2026-09-02T23:43:32Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a18d0ec1d1ce1dbb4e1620e5393cea5efc09844424234cdcf6bec176e14b4bf3","measurement_key":"92e686e7cec9e1960fbb8f154e92e4cd47ad5e95d27a723c56dafb43b1f0688c","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"5231292c3314541e269f278dad0aa3f3bca5ec1b68ad1779918f20e47b44bc4e","score":81.58864285714286,"score_display":"81.59","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_78f4b55ed67e2456efcd3bf7","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-10-21T19:24:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ab65660760b2400e2f30df7e1a5f5f6013414633b71048f876e1185079d88203","measurement_key":"cf91bc6c5d824284628d29ae2eaf611cce74d852f787bf35ad383f5a672284da","metric":"accuracy","protocol_fingerprint":"35208c66fbeab756a22596cbcc77f6a4dcaa0eadc438cb67e4c75620661adfeb","run_fingerprint":"d14611516dd3da9f3d9c19a944708be81210e25404adcc2d58a1f73f6a8a1819","score":82.023121,"score_display":"82.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_78f4b55ed67e2456efcd3bf7","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":44,"at":"2026-09-17T13:30:27.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5b135bc4beea9212489cd83bbd4ad3d8f1f7291c759ad44c3df59b9775af7c8f","measurement_key":"87a2438d7e7eee4bc3a8fa0ab38709b4e32877be77a08020016128067a71e575","metric":"mean_score","protocol_fingerprint":"33ceb2e0d810bdbafc77f518cba2ee9be1b6c409c51b20f9b5f61314928fff38","run_fingerprint":"d882217a9a0182bb2369b720bec44fb60a040c9cc091ca9273ae6e4bbe288126","score":99.16666666666667,"score_display":"99.2","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_78f4b55ed67e2456efcd3bf7","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ad953d5b0977a96fe7b35ac1aaf5b6183a6f34d773fee8d90199ca880402d639","measurement_key":"ba402a290f08d3c8a0569d8c73977f50a53a22776c8e822c3955dbc8bd1920b7","metric":"fully_resolved_rate","protocol_fingerprint":"5df792403d4b41930209ac907b58def1ab298e26079a1aa3d4a3bb2b9b408710","run_fingerprint":"121d627c7e0dfb78a17972b0b4902674344b45d1fa15f35f2709f275d19eca84","score":2.5,"score_display":"2.5","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"95202aae34082aa5e748736c63ca1969e6e58dd756aa7759e0a7af763cf1e3e1","measurement_key":"57bc6fdf70c5ebe92a426b67ef1e8fa7f4e1537a9655ab9fbc970ed7518e90b8","metric":"subproblem_accuracy","protocol_fingerprint":"58a64f5e9ce1fef55acfe29433e82b2f2faaa2005eedad9401268cd075663f6c","run_fingerprint":"e62696ad1467f31a11096015cad40f1abf8bf87484b528691672d98162012264","score":58.796296296296305,"score_display":"58.8","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8fedec5b0d3871db915178db3c72ca16bbb6b0c7295c7edc8323a678c754fbe0","measurement_key":"3d4c69e8dc3d32429b38e214a404b088c316f5387dd15fb25bdd11038cb96334","metric":"fully_solved_rate","protocol_fingerprint":"ebbe25af433b0875bac75018c458896a822255365f8166891193542b453ef192","run_fingerprint":"342a2ed27fbd79bc10dd87d33338ccdf743be9941ed77bb8a546556aeea5c5e9","score":3.817,"score_display":"3.8","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-10-21T19:24:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"054916c5c9b2ffe2940d54606e2cdf0d71724e0c12cd55a6022d37c101c1af83","measurement_key":"eade31492389bea400b2b9a41cded5023cebbdb2d909827345317907b15de6f4","metric":"pass_at_1","protocol_fingerprint":"adbc603baf07b6f79988c40179f4f48058e375ff7e6dbfc32b6f7e42de321d62","run_fingerprint":"50c00ac134b7a95b5ad9297725a664a70ac6647a3b215f3d638ce4c4c0e559bd","score":50.515464,"score_display":"50.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1ebdf57d07abe9356c64a5e1df491dac138da9cf888407a039d70c87e6e6277b","measurement_key":"7ad4253fbc9d26fada5f9083aa1d12263701fa917c9412dfce2aaad2fbd4f3dc","metric":"accuracy","protocol_fingerprint":"d9658cff2811bccf68b9e4b57ebcd2bd82735d1c94c3acf02c2469da836376ee","run_fingerprint":"e6f54626009d0ee547bdc7d45a334b4be4a07a26afd8d4ed58774f2e74a9f404","score":79.026,"score_display":"79.0","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b936684823ea05ab2a4b3b5d06861925cd601ebed22b74b8b86db70cd6b8b4a1","measurement_key":"9c52bcdd5347fbb81e8356d7d32b2d97c7ab70666c5863c8758946ddfb4a47bf","metric":"accuracy","protocol_fingerprint":"3f83a099e0def8f132d6683e45904e47eb86826819dd268aa71ac7896154e759","run_fingerprint":"0b76860469e426fe1f70ac4f67c0fd0feda772d955f45c15f0cb3cf832c7806e","score":24.747,"score_display":"24.7","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1e45a73002227793243d0403e274d8dfd6b7345a0fb28182f3727c34bac38c9b","measurement_key":"43dc03a5c5f2059ae111b7f5e0e2d5476ca7277e4825b2774f34e9f3d08881c5","metric":"accuracy","protocol_fingerprint":"f2455f9c64ddb394079d81288f0a4230b467995199f5f3beac580221cb2dc37c","run_fingerprint":"fb5440443a1ddda247faeeea42cc5cd25d5685c9c9c7befd2ddbfac8e3799d6d","score":10.0,"score_display":"10.0","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ce6de1d22bcb970844a24272f0beb852dfd06d6d884c5973e42e260ebfa1266f","measurement_key":"c4c228106f4e458338f326217c2eb23b5bcf0ff90e9af7758006299cf207dc15","metric":"score","protocol_fingerprint":"ed6e601f1834b4186b1e93aaa9189efc8c7d96669573db6cc9c9fa45d7bf783b","run_fingerprint":"277ae38969478f7dfd43c66e9c52148ed9113b5ccef6fe5c3bf9b6b06aec5d2b","score":85.856,"score_display":"85.9","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7719f84c257eda37adc39be2286d9b37ca5c18ffe1122e78ccf40cfb59a89d48","measurement_key":"f32f21ea063c2c41a8678883548eb2a1058882170a1d8640511c02faf1d2611a","metric":"arena_score","protocol_fingerprint":"c8f24338983fef57f4e349cc387b6bbc685ac247a220cb574337e0ad59fbcff0","run_fingerprint":"33864ec695e1af57b78c9606275b09334a91d63f4c536d2a098eff4b0bc20e19","score":1656.2348593321256,"score_display":"1656","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_942867dc5166c18b24f5834d","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e81a9c8a7fb1df45cde4c8f01a8ea81c691174d1d8af133609ea0b5ee80b0d77","measurement_key":"200e8442d8a61f536825873da2c2074aed97ee776fd5ae4fb11ed3b03991d5b3","metric":"token_efficiency_weighted_score","protocol_fingerprint":"4bcb0820c903884cef58ffa6b0e2e0561d1236a7edcf7885db45c8387083cfc7","run_fingerprint":"f63f2acb5dd9a3d3b128298ff50b07a23894f4c2c8143d8566be96ed7361aaa9","score":6.65496840909091,"score_display":"6.7","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_78f4b55ed67e2456efcd3bf7","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"meta/muse-spark-1-3","model_name":"Muse Spark 1.3","parameter_count_active":null,"parameter_count_total":null,"provider":"Meta","selection_rank":24,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c6c6c83670c59671c77bb3b9e7c782eff86df826087d45212f20cf0c62a6c55b","measurement_key":"da92115dbaeb1a195d8c93e9c06caf3e0ce53fad0b49d9a298de28a5e7fcd5ef","metric":"performance_rating","protocol_fingerprint":"a8155511d9bcff60b3d613babff808e217181f1c4acc9dc6eaad3cb20566ee0f","run_fingerprint":"357b5db906eac75c443a5ab4e92bb4c6a9d3d13810546b538158f7e82b172afb","score":1607.0,"score_display":"1607.00","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4e148d1e9dfcbfb1ad710c65","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7ea17d74c38f3588a534ef503b36d32d40f6620a73cef04cf43c2a83a95df11a","measurement_key":"64d868e5521da2c5bec48de70ce7538c8bb3ad6f619dc94433ff8f55d9086ee2","metric":"pass_at_1","protocol_fingerprint":"0797295966e38c58ce88640837d3115765dabd5b52a0e1dc75622c40ce4b7c40","run_fingerprint":"2efcf64f55b056ddea22b764b71d532d6e40c465c17667d10c8250d6cb21fe63","score":52.400000000000006,"score_display":"52.4","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_dcc0ba793d70c2baa40389f5","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c68f4d94abc7c045bb1d39af09c4e4f1e90fab82aa9ea4003411fa9c2d53df60","measurement_key":"76ddd6836a32d34fa084efbf473e5969a70d47c7d811e847a4f3269eb5802cbc","metric":"pass_at_2_accuracy","protocol_fingerprint":"69829db519a75c0e24f5b48887b1bc469c3e35ca16a2b02491018075b34490b7","run_fingerprint":"b89d9ae59f0610a45850cd9e58e5fcce3054b79d96ac1fdf44146bf0eaa365b1","score":93.67000000000002,"score_display":"93.7","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b25b98eb4fb9bee788833c102caa84bd72aea3b48f9b1fdfe88251a5d8b8b4ec","measurement_key":"8a6eb2b73abaeaf5de95b73ee84a5fae84c19f8959a56b19569eb4e4d3c76c2c","metric":"accuracy","protocol_fingerprint":"b78e285845cfd461df605335673828086cb4d79a24f9cc35618eb474ae942716","run_fingerprint":"258c95e02b03547c9dbeeb068b615f2c34778ad62cd471f6546bfc349bd30d0f","score":73.95,"score_display":"74","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"28d92b17307aa2678fdf87487cd357d683b4b8c3708b237d0ce02bf78677cc94","measurement_key":"5d6b16dd84f70cc46dd2caa7228ead43e2e472a55bfaf1fb1c80ca280a5838f2","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"07727ab00a9117371d4d8c3102820fbdae780b68f37ad4a3dcdfd8609042203a","score":1475.2741681865632,"score_display":"1475","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4e148d1e9dfcbfb1ad710c65","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T14:04:04.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"312702ff7355d31607aecec115d068948b4ab09dadfcc9e388a6881c1959acec","measurement_key":"02114f9544ed554bb88ffb790b82717d683acf294953b80aca2b79ca5c4cd4aa","metric":"mean_score","protocol_fingerprint":"fdcdeb0159024a2d19cf9bad29a8cd2bec3c7f9133e1920f1b99851790c43e51","run_fingerprint":"e49fe61384d80e5fbbfe5c5016ffa6a230989814e4572df9d92e8922814c6247","score":48.0,"score_display":"48.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:41Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4dd861b811d090bf207add0d6411c7a57da0ad2ed24f5ee9885484892a40600b","measurement_key":"773b502172c0284cd69c52b09177a97c75d3274ab6613f80712e54a41ec5b3e8","metric":"accuracy","protocol_fingerprint":"ea2b310e4119a99d31b5c3ff9c76a1ef091cea8acb261867adc06a3b38c981c0","run_fingerprint":"91bd50f711ea118509086fa74249cbf7f11b237ff11ca0a4b5ec5bdbf86f86c7","score":23.42857143,"score_display":"23.4","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"65041becdd328b9694ced5596e82faa38d8e071ea75c1559b7a4c40f589b0ddb","measurement_key":"40f311d98d5977ac3c88a42e910abcac0560a8eed21d6ea6b06e4f85d89628de","metric":"pass_at_1","protocol_fingerprint":"a7d2915ef00e671de2b4cb127c262c7196f5469dafa2a20cfc59b38fd001234a","run_fingerprint":"74b87fbe5cb9578320ea8f96d94326d160e719665b2a6ddbc54ac844344a2018","score":51.76991150442478,"score_display":"51.8","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"87dad09757f011f94e0011c7d851a6c0953597c7dcdb755ccb7b0116248d0865","measurement_key":"6f1f63ce304797f2364ad6b67b48198b8481d0ef31c42d3ca1aebaa82acd49ad","metric":"eci","protocol_fingerprint":"49879babe65dbd853ef21b681c6ef094aad3a806a8c870a30c07a97d5222951e","run_fingerprint":"8f88c05fdbdb5c40faec16f255577b54a236229cebd38a7d705ae6d5b22642ac","score":157.14,"score_display":"157.14","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_54ae75f31e2b8962dbf99cae","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":142,"at":"2026-06-11T17:55:45.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8d36297c5df51497e950da84dcbc6c7d7f5f476aa64c18471fc238b9ec0e4c40","measurement_key":"9221a1cdacda06fd3fb1801a2cd72646b8731391e01b2f31598afd40396d148b","metric":"mean_score","protocol_fingerprint":"2a49bf01a775f4a733f04972aced6d25537229525897b14e8d8946d46425c6e7","run_fingerprint":"4b7562dbe17429cb88b8fb007a92504eee1fb88540caa47a7d1fdc5514fb8d62","score":78.59649122807018,"score_display":"78.6","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":142,"at":"2026-06-11T17:55:45.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5eb1b131b31af8a035209d18347603fc859be428b6efad1a1e0e8cf2ee6f8808","measurement_key":"c8590dcb2127405906d0a6e1af55a883879e340879a6ae8626050799fa12a3db","metric":"mean_score","protocol_fingerprint":"27b31f681b895e22783a77eed993fda0f1bbc4edf584eaf1a399ee47123a3269","run_fingerprint":"70ac6238ebdad9bdbe904cb81679885e8282eac9aaca8ab368d2452156a87488","score":49.0,"score_display":"49.0","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"42d3de98afa534aebcbae0f0c57030fa9233b3a128f0c38ba0178d5aa1fcd46f","measurement_key":"e28056f873c7296aa4b8a003f7d91418b07e175c9b998b313f0c77f2a9013c79","metric":"elo","protocol_fingerprint":"4903a568fdc1a3224f403725fe11a5a9fef3a097f78c9b5f969dc67adf188102","run_fingerprint":"0853c11353a59527d185ba7d2331720a4241bcaa0c5ed816d0bd6c32849bc0fc","score":1255.65,"score_display":"1256","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c65424d6da18d166f21fbf969bcebbc0b1ef4c7a950a91705cbdf61c37898110","measurement_key":"af459f3963140d04fb7c30fad0332fc269b6a086ae617c0fa8ccfd27bb929089","metric":"accuracy","protocol_fingerprint":"21f3b4750ac23c7d045d92073fcbbee018aab65d5e544e8d2991d456a1f06dff","run_fingerprint":"17623886d22bc314d8b6a7a405988f3a64a2d70acd1a96c23ae773f76c9417a4","score":91.666,"score_display":"91.67","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gso":{"benchmark_release_id":"release_176f07ea4e9e0b8dfeede990","benchmark_version":"GSO current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":236,"at":"2026-03-10","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"141b28111fa1ac29cabe22bed3b30b29cb0198c91fa4f0e28f8a31f12cf07b3f","measurement_key":"9895f8236d60fc6c20e22812da040f358a35032bc5b6cac0a9a7a0bb13898512","metric":"opt_at_1","protocol_fingerprint":"cfa903819abdeebe393c5cac5f37e9e25b1d0c153e5cd7d29318ad5ecec2156f","run_fingerprint":"ec8f7d01cfdf1a0159da9b701935a4af520c490da4cad67fbca5ae4b93d57e10","score":31.370000000000005,"score_display":"31.4","source":{"id":"epoch-gso","name":"Epoch AI mirror · GSO","url":"https://epoch.ai/benchmarks/gso"},"source_authority_tier":"B","split_or_window":"official-set-opt-at-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"hle":{"benchmark_release_id":"release_8817af9d9a0235bce0826e22","benchmark_version":"HLE finalized 2,500 · Scale protocol 2025-04-03","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":235,"at":"2026-03-10T21:09:26Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"a17926cf4ea689c0ed3747216d37ca6716c15803e1c04ef45a320a9433206bda","measurement_key":"baa0ac7af87dc1476d3c25690a1c96f3392382052fa69a5fff370713708d04cf","metric":"accuracy","protocol_fingerprint":"ddb17c06202df24bf53bc15e5f62cfc30ea3b1622f3552ef1507abf1f4e49d4d","run_fingerprint":"d50c6875e1426443b071a12eb0bef57cc3a2f1e484261dd7f82d7232fad133bd","score":36.24,"score_display":"36.24","source":{"id":"scale-hle","name":"Scale AI Labs · Humanity's Last Exam Full","url":"https://labs.scale.com/leaderboard/humanitys_last_exam"},"source_authority_tier":"A+","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"ifbench":{"benchmark_release_id":"release_4adf348ac2f76539ed7ccb10","benchmark_version":"swallow-evaluation-instruct","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-09-30T18:53:19Z","last_confirmed_at":"2026-11-01T03:42:24Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6478a2d63e05d38ba4833bc40b8a15c9e9626e080c7d248bf6c0c1ac7a0c4a68","measurement_key":"c722203def9a354e27ca44b26adb6f470370213ed0892a621a92538224c39ea0","metric":"inst_level_strict_acc","protocol_fingerprint":"c558a93bada10f3c0600544169f1ced776f37708edc99457d40439adbfefbf2d","run_fingerprint":"966dac17bdcc7a606f261481d43ffb77a5aa92151df9604c53f3da35e81463a8","score":65.10000000000001,"score_display":"65.1","source":{"id":"swallow-llm-leaderboard","name":"Swallow LLM Leaderboard","url":"https://raw.githubusercontent.com/swallow-llm/leaderboard/c58a13a852eba061d639af7caf4ddbdff33b36e3/swallow_leaderboard_post_en.js"},"source_authority_tier":"B","split_or_window":"ifbench-test-300-prompts-344-instructions","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_e80950dca1866f561008c61e","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dfe97a1bba4c43d4d4f0a7a73d0b448597144234689d67d68de7ce6fea260bbc","measurement_key":"931654598fc1ec0ecd0fcbe8b387e9072d7f78e3cea59e27a0fa32ff23bf04a7","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"f11835e971a30ff05ba2d88cedc6af94873ad0ae2d0bb16e5755a2b6f3b68288","score":77.97244047619049,"score_display":"77.97","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3cd553504faa2c8760241526a6479ace02b70772877c83ab2c941674a6b14fe9","measurement_key":"bd4357861b586575d1c89e17bd577223c968559621ed8b6584b30f51c8aaf7fd","metric":"pass_at_1","protocol_fingerprint":"04110d937c9fa5d2e2c62e244586e564e413eb8467fbd1c0ff7d0b2944cb4e13","run_fingerprint":"ae32c38a5ac096d8a45260b5cabb8c7da89aa9962bf3bfef8735945cf9f209de","score":84.141,"score_display":"84.1","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":335,"at":"2025-11-30T18:41:10Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"e3cd235c5d50f0d3d09706c8210529e14e797d759295307eb1f57578d736dbe1","measurement_key":"091374d487e8c08bdb33a4c2d3423e1335175f3a0ce7ecccf8b7562b011bdded","metric":"pass_rate","protocol_fingerprint":"05109cb140269d19ba09e4f6a13c83171346320bbb454452e2edc084ee9c19da","run_fingerprint":"9e94b0fb83e9f1b9a5667411c064f1ca7b895cab8c0a9c23be242d65a2bc15b9","score":70.6,"score_display":"70.6","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":82,"at":"2026-08-10T16:12:45.299Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"757792585463f1d9993401d5de37afc923b1e036af7fcdefaf5185088eebc2a6","measurement_key":"d93cca6ed8581a091074f1c40080200b7977c306db70b9ad2603a30637c969a4","metric":"mean_score","protocol_fingerprint":"a501a42ac912129da6c4f1f0956794f1706aaccd3f4734f82fa0024d9ba56b28","run_fingerprint":"96b9065c218a2cd958159092001e62224bd61228b07c8409ce54f775dfc39f8a","score":15.555555555555555,"score_display":"15.6","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4e148d1e9dfcbfb1ad710c65","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"39a9743fa1de1cc0b14638cd7105eb4b16408e94b473f3016c1717fc47d13f8f","measurement_key":"a261dec45ad46059ccc5a679ba077e374f96d1165087433d3fb8667f0952a537","metric":"accuracy","protocol_fingerprint":"35280325a2f6f14176f254e8080c9cc9c5655c7411de4981e9b4957ecdb639e1","run_fingerprint":"9fa75062ad0ac5474f2da35608077adebb8e65d33c9b5a0698acc3cf7e3a5df1","score":87.482,"score_display":"87.5","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:41Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"31ae557ebc10437205e64d620ea4c14d747aa8fdcdffcf7ed16a8102348a872b","measurement_key":"440a5e944f9b1e5166d5920bc1ced5f4fbe2f5eb0d9b8090945f8d385dcb5208","metric":"accuracy","protocol_fingerprint":"d308797ef00d4b8edf39563a9eda3ea3d7a32f03c18b5871fb9242ae903f0285","run_fingerprint":"cc86630ce9c995e7e1ae8dd91de6bc7c314e06a66e98dd56e4da28ff02bff3ef","score":87.514,"score_display":"87.5","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":240,"at":"2026-03-06T03:24:03.099Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"7938c1e2ae152977a80bba79dbe96665c3ff74898c8819e2b15cc451bb47f622","measurement_key":"b3aa182a308dccfd1cbe54eeadb92408a0d32ba7948f65259c36ed55c272becf","metric":"mean_score","protocol_fingerprint":"5700dff2b509c55ed69571444ee543107a87208784ee03e6590b0fbaa8412924","run_fingerprint":"20beb5ff4191cbcb97149347d63903a5d032ff3f58529d47feaa6f9d930378c4","score":95.3,"score_display":"95.3","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"45c6bf5477c8c115f35b9cc2fb49adb9fda1fe0f3a7c42351eee62c5429e4fe2","measurement_key":"d99af4e42bc2bf219674ad79a5a354994841465e5322ddb77b9a0bee6d80ca08","metric":"fully_resolved_rate","protocol_fingerprint":"c6ed70bb0950e65097208c035c40c67cc32aa057c56675a727466025adfb2a75","run_fingerprint":"94766ac68b0fa5e2528e7690e6e11d00880bdd7842ca1077ba019fb6f26cb10b","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:47:54Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"17a5fc4b5490294cce6d99ba7d2429d6fb4723bb46ab420d67a0de9315c9d57b","measurement_key":"dedbbd9582b59e9a850f2c2df268802904eba13b559fd0a64bbc9be2c80f60ce","metric":"subproblem_accuracy","protocol_fingerprint":"309df13fb2e5d9a3e71e2cc00cbbef6270e23dd5d77129313564b2d1f25d0f62","run_fingerprint":"9befc756c6b459fe8a838ebbd39ff1bce5edf7b9faa4b202c77ee787539b0d48","score":56.5972222222222,"score_display":"56.6","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:28:16.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a3ed2716b4390de63cda63be2c38fffbee5e7ae7d215a8e7b38b827385539fb0","measurement_key":"1b3ecca4e9d868ee463b55838f5ea57a522f13e0c9ee79d3d0764b4371e7696f","metric":"accuracy","protocol_fingerprint":"af3b5b3df99ddad25db0a7afaba9b2d3052c3e051686d2c52d261ca34bed3a0c","run_fingerprint":"c376dfce5075b65a7c56862e5657658941d22ca53b01ac7bd26dc95ca3f9a478","score":45.1,"score_display":"45.1","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8830c3fdd57c563fbe114e3cea9f37fe4577063ca7e93d0e30c3363ef66e3dc5","measurement_key":"96499446a70bb0508bc49abe78d97a36527aada8abfe0b20dbefd66c7d402d32","metric":"resolved_rate","protocol_fingerprint":"0c87e6ff55e71af72ec817666cff3bb6c8377e7522c68ec7eee3fadfa3d46518","run_fingerprint":"b31047986d70d360bbc9fe5ece94cb80eb99eab41b400156db5db4dc608c3ee5","score":78.2,"score_display":"78.2","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8830c3fdd57c563fbe114e3cea9f37fe4577063ca7e93d0e30c3363ef66e3dc5","measurement_key":"96499446a70bb0508bc49abe78d97a36527aada8abfe0b20dbefd66c7d402d32","metric":"resolved_rate","protocol_fingerprint":"0c87e6ff55e71af72ec817666cff3bb6c8377e7522c68ec7eee3fadfa3d46518","reporting_origin":"organizer","run_fingerprint":"b31047986d70d360bbc9fe5ece94cb80eb99eab41b400156db5db4dc608c3ee5","score":78.2,"score_display":"78.2","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_84d7ad8aa122e93390d30e06","benchmark_version":"rolling-v2","comparison_lane":"supplemental-post-release-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7eb56263d626318606faf06a0ed6b3f2a926d26b7699077886d1108a08226e9f","measurement_key":"76bcb3fe65e30713528b522438e99cb5891ccfe2140e0b570cf577ce53c793b1","metric":"resolved_rate","protocol_fingerprint":"9ba14dbc07b4734d9269ca0619063b4d06c575561ea00192c192a1576772ae1e","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-03-01/2026-05-15":{"benchmark_release_id":"release_72d764965dd7baf34f983249","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"41fda1e7c7c6a549acc20fac035d2cd02239c0873e4fa2b92ce373fde50ec443","measurement_key":"8ae336527c1a07b2af98898d6fa2ddb4af6c8e475ccf2e200284526b95e13ebf","metric":"resolved_rate","protocol_fingerprint":"ce8174030f583c6075758ab72f84c5cfc1f787e782478ec97705b870f291415b","run_fingerprint":"02e5d2157cfdead40490fcbf94f722e848997ea142f9a285ec4ba966452875bc","score":54.90909090909091,"score_display":"54.91","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-03-01/2026-05-15","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_e80950dca1866f561008c61e","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"}}},"run_fingerprint":"1fd030adc5fef5cdf1b1088935b77a6b27fdde33f516138b63c8e85df83a81d1","score":55.957446808510646,"score_display":"55.96","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-03-15/2026-05-15","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_e80950dca1866f561008c61e","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":179,"at":"2026-05-06","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1628f893717bb52c2f06eb359ba9fe5678ab68c362a3120d471484efff3a13e7","measurement_key":"68dee340b0ddff16bac76dbb852e92557b7828d4fa0a6603b5642e18cff5216e","metric":"pass_1","protocol_fingerprint":"1f2c749156758dd2cdd932f2c0fcb8e343f009eac9e98fe705311767aaa43ca8","run_fingerprint":"6b7528ccbe40b45ee7f9ec205979d824c64c678aec94c9ebec1131c19f6c715d","score":39.43,"score_display":"39.4","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"29927af4509f931fa6fcf3538d7d2c4abdd9739e49f8eaad2303920238137617","measurement_key":"c25b5bfbcac76085c2c87c29cd982b2e433dd9de387162d95cb79590d15f8c95","metric":"mean_final_balance_usd","protocol_fingerprint":"262915de42a64a04effa6b5004cbc4c44985ca1f5c71ead94e759a23fff7f15a","run_fingerprint":"fe74521c9674bbf0e26a595ecd51ce734ede4820426661d68a4c60e999e9319b","score":6144.176,"score_display":"6144.18","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_cf26814a19699b9dfdf18c84","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"edf58376f407c614eac11ce231fa3a70ba32eff207f943b0a161d1d21e3a48ca","measurement_key":"771ab0b75a85e7151ac48cb629772661251c1b6483581a8a9700ebb3fc78a17c","metric":"score","protocol_fingerprint":"8bce169aec517da4f954b54edb939251ecd1bd77886b039de2aad04ec2a008db","run_fingerprint":"c2a1eee4d0c931e57d488726ca52e4ee436b65dfe111018839641785ae9b0a68","score":67.421,"score_display":"67.4","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6378a85ebd342fc603d10ef94c22e5162d2be1893bcf502adb15324ecdf6e867","measurement_key":"7bf96e5552798428321a30831b65d1c9026f4c9d9953a720476638c3281bf477","metric":"arena_score","protocol_fingerprint":"29ef6a59018d3edb57c1650e74cbf849ab7ab12c814c4fc0ae4fecc2c857e8ec","run_fingerprint":"1ba73b42bb057359904a21cbd62e45848fd8ec1d7fcc68ce8fbcaa576b765c82","score":1401.0886143328514,"score_display":"1401","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e5f556a0e36183d119678e30","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"228f85e5f977a5e38c23a6b2ca51e78bc9efee9a4fae1cc9a24e33a314060cbf","measurement_key":"1cc7fc0603d8dddc37db82a3ed1fb40f381d5b40d63f8c1cc21cbcb306c44166","metric":"accuracy","protocol_fingerprint":"a2419b920174c9dae8ef843b6ee83c439c8799f276a1531e3f5f834e17649ceb","run_fingerprint":"6f930aa2170fcbcc26cab0538705f34540a5ce27dc79924aeb313aef62795333","score":77.7,"score_display":"77.7","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d50b48d5936735014a249939","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"openai/gpt-5-4","model_name":"GPT 5.4","parameter_count_active":null,"parameter_count_total":null,"provider":"OpenAI","selection_rank":25,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"34dfbd3face68fc581570ed7cdffbc53b00a1c961ac47faec3ff16c62843e7b8","measurement_key":"5e091bf2a05149ac2ba26a606a72fea8d99c1f4be4f4dc9c3c572223b2b24a40","metric":"performance_rating","protocol_fingerprint":"7ddf2d974e629787f018a6349f86d2a4ff76f2fb2671251babcf7840475de123","run_fingerprint":"ae9794c6f49807909d054b81b884906e4c5cf0afad94b331e7f5b178da00ec4b","score":1463.12,"score_display":"1463.12","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_37845fc871b455ab26fa8ccb","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"362eee998580fc803ac2397e73f1e74ac358617edb2ecc83d909107f6dad0e73","measurement_key":"3d04053a624674adce88301fe8c594c2272f806b59f963ffe0912c80abf4d32c","metric":"pass_at_1","protocol_fingerprint":"dcb2f17904056ad343ca011fe417e55a50597ffabe534a3f0ab7ede9dbe3706a","run_fingerprint":"0e85356d3735f0b8842244161ecdf675c94bdee3c95aa8f3c156b1dce4527baf","score":54.50000000000001,"score_display":"54.5","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f8d65b9fce47c16194d9f6c1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c9c4994e60f7ef26ef1157904faafc060a334fe539daf732956d883f0d8b5313","measurement_key":"ca18fff9789d8076e2d2757783fec1eefe8e7eb1ddca4f536328b0c2fb4df540","metric":"ips_score","protocol_fingerprint":"9cf8d3866831a13891eff4fae17006c8665285fbe0e1a897654e40b4a30d6a68","run_fingerprint":"a7a58b18604a7da027f2de847071b007e0bbc802473bfea273d4e466dd43f1e6","score":0.02940963023579071,"score_display":"0.0294","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_37845fc871b455ab26fa8ccb","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e0455f8bed986998de983124434dd9d8d97597f986c09becb466fd36c1c4d83a","measurement_key":"b9bffdcb02081fdce3ba73aff774834051df499d96dd34d2b3ad02b41b7e3d43","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"4289978b73894ce9c0735c92185cc8c49d87c11b2e4888101e4abbd87597fc7d","score":1461.7446227242526,"score_display":"1462","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_37845fc871b455ab26fa8ccb","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:23:26.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"302a36e46b2aa4530b30a25a39114aae1fc7cfbb00f0b9568500e1ac7ef763c4","measurement_key":"37c45baee5f309a7eb5070036fc42c3b8ae40a7a0e3fecc9e5f38d011bf0b50e","metric":"mean_score","protocol_fingerprint":"5c935fea8a8010f7c182e214e2196f2f47751199bbbe506cac9838bf3134738b","run_fingerprint":"bf8f4594923317c12eaeb311424698c495a5481dc42aceab37636fbea6656f4b","score":45.0,"score_display":"45.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:41Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cfb63c9805ad5d5e87eb6d09f2c29273676dedcb62678e08b40e2617519b985e","measurement_key":"32c736d87301cf953c5f573fa812465cbc7211705ac96219f260a23d77aeee4d","metric":"accuracy","protocol_fingerprint":"c8a8bb2f7d7f4090d5bef01b45161f888bcf65d20d5e142e5a9fa7f6f8e5e422","run_fingerprint":"1043a4d5a217fb4b356ab48fbe51fb64670aa5063356de98c8e9263bf669505a","score":16.8571428571429,"score_display":"16.9","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"cursorbench":{"benchmark_release_id":"release_9acebd5b002e9c3f18a30606","benchmark_version":"CursorBench 4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4c33abec313b5204c5eacaccbc0c7b9fb79e3b0039579e3f3d4038db1aad5ee8","measurement_key":"a65895a06a5917e534cd455046568d52862dc54bbb3e89750000d24fff9a0c93","metric":"score","protocol_fingerprint":"2e625518e528044afbb746d49b116983badaf752a1427c48d7f9a1ab0857d19e","run_fingerprint":"59a1f810d36314c4c5b16827ba5b3bee6c7645b6596e37b51dfaa826288a0a95","score":34.1,"score_display":"34.1","source":{"id":"epoch-cursorbench","name":"Epoch AI mirror · CursorBench","url":"https://epoch.ai/benchmarks/cursorbench"},"source_authority_tier":"B","split_or_window":"official-current-suite","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e110c10f9a8ac05f173262f4589ef8f3131f54d3ea01f9fabc58e424bbeb3400","measurement_key":"41ab80f3b78a0f0a0c4adc6fcc2a35f05aec198a572bb46491b99533295b53fa","metric":"pass_at_1","protocol_fingerprint":"c661237bdafd6d2237be5b74378ff13ee23b9c201c5eec402ab9f08e20a77824","run_fingerprint":"84c961b29c5c2ac49ea59f3160fe1a15043f1761b204d4a151e8b6fb1a7da2c3","score":53.84615384615385,"score_display":"53.8","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"56c0a6e91a10defc2ae13df979c3135e2786be424940ee8a767f01cc1595ed85","measurement_key":"2a6af19d873a131719e8c9a2360e13af50b8cc0230c91b40cf2c7749f82ce7c6","metric":"eci","protocol_fingerprint":"aa701862fb9aeaa7d5cf09aae504091a34c1a944abcae36ef3ba1fc0034bbb88","run_fingerprint":"5a16605f4e3edfa91339ef07c8ababbb0e27f9af773daf1ab8d9ac1df8d94a8b","score":157.03,"score_display":"157.03","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6600b24d6b7955f517414625","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cd4d4a4448406f46fb0106bbe9f779153685a7cc5e3b75238e48436b6f0a7c37","measurement_key":"9d475eec8c8876c7e9089119928fd3eace0d1f618d4490569e18a51daa1b412d","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"f4bcc4c61f272444f58d4638e48d10753414346ab0260cfc3f2575c95d1ca708","run_fingerprint":"7987cdb551a6a637701e730febb2a51982757a0de97ebe61eb7952dd36885e20","score":42.730000000000004,"score_display":"42.7","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_24d6255a6b90676ceab86615","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":123,"at":"2026-06-30T21:54:08.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6d2fe2547482cb0b3e9fb0e8bcf78438d497a8f6ec224a3d786adc72d558f613","measurement_key":"1beb490c9744f3d8dca8e8a0f00229fa7901ab58653ccb179e79445eac18adaf","metric":"mean_score","protocol_fingerprint":"6f9eaaa7835e7dbe8796b8a67e624a1fa6c34db8f6fda1c04fc3d72e22630fae","run_fingerprint":"a67aa567eace0552194963a23b766931e17da26faf6345c7dc46dda72d918d30","score":65.6140350877193,"score_display":"65.6","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":123,"at":"2026-06-30T21:54:08.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9f7ff9bb9ebbfee2b987676455cf8bf6bba8e88fc53f24e5620a24d718151b26","measurement_key":"16b009e18c2693e30313d0d7bd10632e4fcd67b3fc53fc2fe3d1c6168e280ef3","metric":"mean_score","protocol_fingerprint":"dbff2f02936d4e952441a601d60d08dd5c4312aaa3c35b3fd6c65947d0f45232","run_fingerprint":"74cf3918e83600776859688ce0fb683e65495a968a5609a9b7c0963d8a498a83","score":29.268292682926827,"score_display":"29.3","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5006c5024a3586951731bd45e40fe61e7a948cf179691ccd98bfbd442138ac99","measurement_key":"4b9756711065d71e6fd2341bbeb285a07ec7598eb74a72f610aea9c16bfadba8","metric":"elo","protocol_fingerprint":"7a96862218c72c5a19a246a11dcf15546a7172bc0b53101874fbe0436dc40a61","run_fingerprint":"92f7b1d2b10eadf5b16037c06f570afb8b656a7683cfaef564e5b843954ed097","score":1470.38,"score_display":"1470","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c3065a56d69cc907970650321eb14f6c88320c504f3a6b3a6b20973c12fadd22","measurement_key":"65e93bcb8473e6bf06f463a535915dc702a5cef543b97dc0ac782b8b07ef3185","metric":"accuracy","protocol_fingerprint":"71f9cc6e52bb88501e383d272016d2d5a7291de8546458e998292ce0597ab958","run_fingerprint":"ec505904fe4e029702d28c58a1d02a1e3a6a9eb532ea5258d40f358678892a77","score":88.889,"score_display":"88.89","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gso":{"benchmark_release_id":"release_176f07ea4e9e0b8dfeede990","benchmark_version":"GSO current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":112,"at":"2026-07-12","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"267d2717f73c3d4a367b20b9c837c9043072cf1e791662b4aa65c2e40e26b4c6","measurement_key":"42e9e1e80bb3fc0fa20f1fdfdc011ab299e41d7b201569917d7f9e4894c6083c","metric":"opt_at_1","protocol_fingerprint":"18b94ab8f540d424f8ed062411389259b95dbf9a9d86613682c99b284484d325","run_fingerprint":"9c9fdcd25075adbebf3c4b73b4254aab4f8c7f892b7e7aabaf5be552bfe1d438","score":37.25,"score_display":"37.2","source":{"id":"epoch-gso","name":"Epoch AI mirror · GSO","url":"https://epoch.ai/benchmarks/gso"},"source_authority_tier":"B","split_or_window":"official-set-opt-at-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_cf91388c08be94a36c0d7705","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"hle":{"benchmark_release_id":"release_c1afb6c54b8ceec8bc1f121c","benchmark_version":"HLE original full multimodal","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":124,"at":"2026-06-30","last_confirmed_at":"2026-11-01T07:28:19Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"df52f43c4637cc137c0de302e32f045a622d5946f587cc4a36535ba21d3312d2","measurement_key":"f97c1511a4e0981b5138a1c942c39718722d3c048b0d3ac2efb6fc7ece5e5a31","metric":"accuracy","protocol_fingerprint":"f3369573ec5fa708c2fb1887738ca58a6da3b6f6fdd4087151c44904e7e0c723","run_fingerprint":"2605369b70f9323d0ce43d5ab7823a5b1c278b4b99eab65a19ceb25a78532f61","score":43.2,"score_display":"43.2","source":{"id":"anthropic-sonnet-5-hle","name":"Anthropic · Claude Sonnet 5 System Card","url":"https://www-cdn.anthropic.com/283ef97c476cf442c91d9a37d5b214242a55bb92/Claude%20Sonnet%205%20System%20Card.pdf"},"source_authority_tier":"B","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4c1dd3ba4a09a30313d8edfd","raw_label":"reported","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-17T14:33:50Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"98a742595de64e1dcc26fbf8d98e816d8b0b6b6a2494aa82232f42ee62c8a29a","measurement_key":"3eea1a7ce8f8eef1d7a4d4b90f7e423cccd58a64c1f0acfa4b6de027b1c815b6","metric":"accuracy","protocol_fingerprint":"d11b49e4e05aeabf126d705998497fd9f0de58914840fc8ef821a3ad6cc23b9d","run_fingerprint":"18cd5c41199b06e0b246f42608f3332251f8be263c9be870c0d540ece109085f","score":41.28823,"score_display":"41.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2024034771784537095bfb787fd4d78d5c82fff4962c418007152c59cade5d04","measurement_key":"09b6133f4a60a10e438ec26b7e402391c156856a161388679cd394ad762fc3f9","metric":"score","protocol_fingerprint":"7b7877c6cd8d806fd5e297f748adf27c6906c2238b73c7eb85666ce58a3154a5","run_fingerprint":"c71342c466083035df905909d7f09a161ed1baf7470ca234d3f487de3c65563b","score":45.0,"score_display":"45.0","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f9ad0522dc0663f9930e2a58cb0ab6f4353c860095f6533d9d6d9be67e69f6d2","measurement_key":"45eca6296e73b6d38f1992eb5d55abedb74c9dc82a79fe71c2b8ef8e458d645e","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"4d247784bec449462655bb882bf1bed4a6725f5e1aa8e42f50d5c238105a3e88","score":76.03971428571428,"score_display":"76.04","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_24d6255a6b90676ceab86615","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f5022005af7a25a16e2e55a791a1de422531186d70c3376b37ae47d0374a8f14","measurement_key":"e51f87ac2ee616377aa257a02eb668937461fd8b8fe4f172ad27850638ffe998","metric":"pass_at_1","protocol_fingerprint":"915d56928cd6c0fb4eeec545994c0ce5e2153b3ea761cfefebecebd425bbe34e","run_fingerprint":"d6e608d68c588d5e2b4a6094cde74780ff2c4455486a45af862a041a1fda99a7","score":82.429,"score_display":"82.4","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5ec8ad845678b45569d5eeeb0205a230526645b04888cba1ad3908322014fac5","measurement_key":"58a7ac8bcf40c1980bbccf02a41d5387a81fe0db7520763e67a21dbe579314d0","metric":"accuracy","protocol_fingerprint":"23d9a7703b4749f46277bb2c68fc25c08c0ae1d6fc5058996339007404083e5c","run_fingerprint":"e0e22ef7e05442d676197111faa296024ed14ec1f7d6630d875e1cfc85eb7316","score":87.545,"score_display":"87.5","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8a5a40287eac36558ec880c5361e38ddd5c020d144df17d2810d46c1968bc110","measurement_key":"0f0e80d3b85f70d482808a0eefbe255bf6edd3798ebd9f868d0c25133263f10a","metric":"accuracy","protocol_fingerprint":"6d8f926de952f64d2866b17d0be9e79385bbf1a99ae6ab095ff54cb8a0fa51f4","run_fingerprint":"bc441b56b0bce2079a632aef7403388bc9f72e5e57d3019dd68c67aad59e4cb8","score":83.006,"score_display":"83.0","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-06T22:21:48.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"86ba1e466866af1c590528a651c3566b82619f303b73a7e4d86db657fe288c9d","measurement_key":"f2abbf2cc574faa14ab59d121540e665ccd77ce980b9c69a8666239b6c605723","metric":"mean_score","protocol_fingerprint":"9a0868ac73fde87850c5807de8f84ccbf2a2cc8c57e6b1ff438531fc033606e1","run_fingerprint":"0df49ba275a724af68f42cdf01d8d94b0aa3f9ac788d24b9acbcc5f115abdbe8","score":80.0,"score_display":"80.0","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"60c450e2dca87353afe3c179b2b066270df8d7ef2ff2000bd076bac4d7177f68","measurement_key":"081dc41be3013cd23433a7ca16e65f77a78322f494534366e752a57e2a46b486","metric":"fully_resolved_rate","protocol_fingerprint":"0a70f05d2d4764e578d6f76c9f60026ad2300f607aee73b45ad5b78713fa1eb6","run_fingerprint":"6304cb1a87460ff4f9e809cf004a30c919f97639755d7295d2ebf76f496d91cd","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:47:54Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3b55b7cfbd88ec46d5f0012963c1d9e06c36625d6d1aba610a7a2ebf17ff5997","measurement_key":"23e6418eb5d920fcaa12c245dc358a002c06cca0293ea6518292100a4c756082","metric":"subproblem_accuracy","protocol_fingerprint":"fcb876f2caeaf3498f1d2ff110b7eb80fdf6e8769742151b4e04f79acc0a5133","run_fingerprint":"9a772716f3d05c739eb3c7788ac2d0395336ac2af3762e68eeb95a42f4a13ed7","score":53.587962962963,"score_display":"53.6","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5f1c3c4e36e86e5b0e7207ea9c08c12734a6c6d81fa596d41d9833836d9760fa","measurement_key":"f97cf04a94f6d374b7fcb976510b1e329296c633e2bddd7cedf4b5b4b9f85b2e","metric":"accuracy_avg_at_5","protocol_fingerprint":"cd468ee7668bb194c17795fc612b46112ede3da7738b362f51a2954fff51d4e2","run_fingerprint":"3c22e5025056f2718e065b6c8495fa42dc9dce5aba920738db31d46d27be17f9","score":60.6,"score_display":"60.6","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7249740ffb460d0140f7c11a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:27:42.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"76e1ee39ac80f3c5f10b5705f85254a989160adcee403938406f79e31e120df4","measurement_key":"1b793e7b8b3708e6fce2b8cf8ae6e3feebcdcd9e4f6fb8510b38e93b3927e6ab","metric":"accuracy","protocol_fingerprint":"5861f9a63a01aed2d1972491628359bb645b56f3336acfb048a5a99449787c3d","run_fingerprint":"811f5ca7cec66fb7145925317e829aeeadae09ac694abf97c52a5fe69db1fe83","score":33.7,"score_display":"33.7","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ca8a76a76e4d9354c784f6d11e0f9809b6cd13c630a00a709936b62a1d2cdb1b","measurement_key":"efeaef71b8889f254f71a7959cd9dc542918201c084a5f6c873047e958638ae8","metric":"fully_solved_rate","protocol_fingerprint":"ff18c8034eb68af61c56b72d375035faa786f4ec54ed8d6c54a68bb7f5cd4f5c","run_fingerprint":"7779cd38b95878909086d034344a1173e2dfa83ade7f16c5326ffaac3a4bbaed","score":0.382,"score_display":"0.4","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-pro-v2":{"benchmark_release_id":"release_d9b58bd286ce316ccf0ed891","benchmark_version":"Scale SWE-Bench Pro V2 public leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":25,"at":"2026-10-07T01:44:58Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a5c625e4f80b259ed50f26df5bc28b05033664928ce756b28d32f20ae6b5df5a","measurement_key":"5368dff26f3483751181cf1d339a2f4d3c09e7a09dd233aeda84fe58e47c138f","metric":"resolved_rate","protocol_fingerprint":"f838d3a13b1844d9467d961b2c681c68bac2001354679f7edfeee68651ff5950","run_fingerprint":"847123f137b598a2aea795ead13b2210b93c1f166d20bdcf8cf5d49b77108424","score":93.15,"score_display":"93.2","source":{"id":"scale-swe-bench-pro-v2","name":"Scale AI Labs · SWE-bench Pro V2","url":"https://labs.scale.com/leaderboard/swe_bench_pro_public_v2"},"source_authority_tier":"A+","split_or_window":"public-v2-642","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_24d6255a6b90676ceab86615","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-28T01:30:56Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3c1f07d258040c7e97fc3de22b06fe1b1eae8e9847a718b3352efaf0256148ff","measurement_key":"1882e4373d63adb5a9a8e931bb0d0d806b993057f33133a5ee83b7c3d084b989","metric":"resolved_rate","protocol_fingerprint":"4c397fe6e38b8ac4551eb446d2ee567de90d131360f871eb741c5207d829ef8f","run_fingerprint":"86aa646db03b80057145ba6e5d6313848e82276831ed960d42edb05f69a318ac","score":79.6,"score_display":"79.6","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":{"benchmark_release_id":"release_ed49ef6cb40ad079db5a0835","benchmark_version":"Anthropic 500-task evaluation","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":124,"at":"2026-06-30","last_confirmed_at":"2026-11-01T07:28:19Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ed2c6e9a49e5bf0713ea90d00f46f20516e794943238d12da1fbf4c80d35f793","measurement_key":"453b22c9f563e313ce618aedd0ec6a52b2d306cbed935898b5b58796b88562b6","metric":"resolved_rate","protocol_fingerprint":"d5cc9a90256ee91e03c40fe9632ce24357887404d2ae52765ce6a78ae3e40b84","reporting_origin":"provider","run_fingerprint":"e0dfa8c8ce25b948ab6d862f76dd7c609689de30c1eee3dacfec90e0f1047af2","score":85.2,"score_display":"85.2","source":{"id":"anthropic-sonnet-5-hle","name":"Anthropic · Claude Sonnet 5 System Card","url":"https://www-cdn.anthropic.com/283ef97c476cf442c91d9a37d5b214242a55bb92/Claude%20Sonnet%205%20System%20Card.pdf"},"source_authority_tier":"B","split_or_window":"verified-500","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_83831be53778e89901c24ca1","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-28T01:30:56Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3c1f07d258040c7e97fc3de22b06fe1b1eae8e9847a718b3352efaf0256148ff","measurement_key":"1882e4373d63adb5a9a8e931bb0d0d806b993057f33133a5ee83b7c3d084b989","metric":"resolved_rate","protocol_fingerprint":"4c397fe6e38b8ac4551eb446d2ee567de90d131360f871eb741c5207d829ef8f","reporting_origin":"organizer","run_fingerprint":"86aa646db03b80057145ba6e5d6313848e82276831ed960d42edb05f69a318ac","score":79.6,"score_display":"79.6","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"contamination-risk","conflict":null,"directly_comparable":true,"display_role":"contamination-warning","evidence_grade":"C","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1fb2caa7d4decc0d4cc7ea4ffbf25902cd01e205d85eeb456548710b3c69fe2b","measurement_key":"5bd8e13bc6585df8bd63c11e603cb353f2d9212d9b896421a6a3e0594e3a33fc","metric":"resolved_rate","protocol_fingerprint":"94196f1040cab460930695009cb99a0ad38c89a5898c53c3815a04f1b2eea6fa","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-05-15/2026-07-01":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"contamination-risk","conflict":null,"directly_comparable":true,"display_role":"contamination-warning","evidence_grade":"C","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1fb2caa7d4decc0d4cc7ea4ffbf25902cd01e205d85eeb456548710b3c69fe2b","measurement_key":"5bd8e13bc6585df8bd63c11e603cb353f2d9212d9b896421a6a3e0594e3a33fc","metric":"resolved_rate","protocol_fingerprint":"94196f1040cab460930695009cb99a0ad38c89a5898c53c3815a04f1b2eea6fa","run_fingerprint":"64cef58baa68cbe36a9f59574a3c5acd45ef7c5539dd8f08c1e8cf2ea31dd092","score":56.75675675675676,"score_display":"56.76","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_37845fc871b455ab26fa8ccb","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"}}},"run_fingerprint":"64cef58baa68cbe36a9f59574a3c5acd45ef7c5539dd8f08c1e8cf2ea31dd092","score":56.75675675675676,"score_display":"56.76","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_37845fc871b455ab26fa8ccb","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-09-17T14:33:50Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"039bc64cfc487dd60834a4df6779eb380d1321629ae1033b7db1405d9d06c7a4","measurement_key":"b6f6c8a8b25f59e07cdfbf57c00298486df6e90bd75d6596a7e9335d2a9010c6","metric":"pass_at_1","protocol_fingerprint":"c0f6bd8ea4403758b061764ef6a9fc9c9d6ebf7a4aa362b3eff4ce5cc27e35da","run_fingerprint":"a877fd190cf44fefa7c7a4673c2941bc5f813389c9f04a2c4dba406fb952cfac","score":37.319588,"score_display":"37.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0e03b4c7fb76d9aef1645c5c094af0b922036eeaf331a499ee00a79bf56d1365","measurement_key":"da25881192696fcdfcaded75d5e1bdc0fed86feaa1e55adf6362ec62cf263b9f","metric":"accuracy","protocol_fingerprint":"1fe860f5c450e0296f4b8821bb3841d06a17dd27afdb4a370e28be5b2c8268dd","run_fingerprint":"ef2f154f1a1926a764dcf2f6fefe9d3f7abf12c2af0a12dc742cbdca8be01ecf","score":74.532,"score_display":"74.5","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-3":{"benchmark_release_id":"release_ceb36f25882d8cea2c9d084a","benchmark_version":"3.0 · b936386b-4afd-4ad7-aa7f-6b52bcab9853","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":80,"at":"2026-08-12T21:39:34.661007+00:00","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5fc4d38e5cbf9f6e67dd7365b8c4bcfda39b00dc2fcde76413c9ee60d8ebd0ad","measurement_key":"2b83b1e61628251e74a8d5d303638ccbc042603323857715c20118a34ae702ff","metric":"accuracy","protocol_fingerprint":"25f28bd29e55217425ef1850eacad7c52d96511c3d9abb79c78a195ddc7fad33","run_fingerprint":"4448b4dcbe691b01f052cebcc4c29723835582278a9910e49bb06f3a8ec555c6","score":14.59,"score_display":"14.59","source":{"id":"terminal-bench-3","name":"Terminal-Bench 3.0","url":"https://ofhuhcpkvzjlejydnvyd.supabase.co/functions/v1/leaderboard-read"},"source_authority_tier":"A+","split_or_window":"official-74-task-leaderboard","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c50329c6d2a4f67bc984dd0d1958de45f909657c2d8785efe5664f1a8084cfc8","measurement_key":"3b9c060aea588338a3026ac5d58307dedce315076837a661c9a21fe33d0abd2c","metric":"accuracy","protocol_fingerprint":"cee89bbb1dfffd81c2e6537b0dacfc018e4103f1eb0d457fddcd46530181641b","run_fingerprint":"dbb9de53b9aa49d67da22513e8893544dd624fd3f153776fde05ef403a672a18","score":10.606,"score_display":"10.6","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f22344345706e268414163c9aa85edd583d49d8263e806e54a26cbd3be179e6f","measurement_key":"cc5b3339c7dc5d40bda0cf69e3b2e2faa522d8518468e7ae37650cd67287049a","metric":"accuracy","protocol_fingerprint":"bb54ed2d9d35c00dc023cf0200fdc4b97893439ac73542911a208892dd6db315","run_fingerprint":"cb1dc2002f7b13c9146231fc620945630cc5ff27359d6e04360c4e8fd2744479","score":5.714,"score_display":"5.7","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b050fecdf81abbcd3d7b33a37acac0902df65e7d788a0b7f6eae541516aaf93c","measurement_key":"e75ffcb47e317c5defc2b50f9ada78ddab50846f8191150154d4da2501abf223","metric":"mean_final_balance_usd","protocol_fingerprint":"7145326ec3a37c3c686b6b29841d280a2481e6f2ccf82d77a0769f9153e1b663","run_fingerprint":"bd2c212d4e07365f21238f4043c6c4b9c30f2adfe88cc763fd571df295da0679","score":6377.701666666665,"score_display":"6377.70","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_145e1c54c865c8920fcac152","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ede57d594c814ad24f0001c66d56f7b588c883e5e00a96c8ebc4e61551c6e84d","measurement_key":"81a064e0007b1117bfc19efa498e5ecd2e729481d175bc6b190beacf898d69d7","metric":"score","protocol_fingerprint":"2e89812b273d4614f96bf5abeb68e542a312b55a3b6ba6cc17e27df21a29cfc9","run_fingerprint":"3bb6a1766847a8e7af1210d390444488899a035000f45342fbf6be3be080e27a","score":81.325,"score_display":"81.3","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_289738e1411638bab936a9b2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0e50effb27440a4ae349b281216e472d854148007f71ac37cf90a47b90f02e15","measurement_key":"49b8037993636097129391a9507eaf19106c6e6c01ea26ec485d78ebcef5d130","metric":"arena_score","protocol_fingerprint":"24141190a703b11cb1716a50a817cf0992e5b12d13586bac598d26a05f8d5648","run_fingerprint":"b00fb3e4dd43b54b5775d9d4b4c759bb68457290f723c2e920a83698798be0e5","score":1540.090043634944,"score_display":"1540","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_37845fc871b455ab26fa8ccb","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7455899ef5b37b79c2df4db4e5f0b29728c6ca84ec39208e662e308b1eae9c55","measurement_key":"40ad4f62a0da2943d92889dfa9f9d13d66deaf5b606a29052f4d316ed6604759","metric":"accuracy","protocol_fingerprint":"19f25720664102c965f733bca8baeea6b5ec87314087432ac558fde76487ce3e","run_fingerprint":"107c709304daa8d7b4a73ae19cd6c6d6c26328c26c8a78665b38619828d672f5","score":68.78,"score_display":"68.8","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_37845fc871b455ab26fa8ccb","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"anthropic/claude-sonnet-5","model_name":"Claude Sonnet 5","parameter_count_active":null,"parameter_count_total":null,"provider":"Anthropic","selection_rank":26,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e760db9617923047b9aa7472bf6e51b435737f43473ef20d2e43dacdc46d8a5d","measurement_key":"e10926a4831b70b181cd52c24c96ac8270a552d443a1d46733b9aa993f38815b","metric":"performance_rating","protocol_fingerprint":"c30da6b2ea8861545a89073da5255befc4b15d43db77b3f5292f4dcc43404be7","run_fingerprint":"d2e6c16631cbe712cccfd2e84b4a7deba258c4f82820d1a8f342af234dd66a2d","score":1508.08,"score_display":"1508.08","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_466c9201a70dbe424a06eaf9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4bf6d535b7248e39a3f8f840e30dc1bc7481065533a09206cd085a5c8bfd7aa4","measurement_key":"834d73deb293fabd9c2a853a8a3ac344c8346373c8d21c8146fa9c0ca6295502","metric":"pass_at_1","protocol_fingerprint":"7de066374ca85de128d967ed102edf469b77fbbd2bc137abd8ff65b2409bf0f4","run_fingerprint":"90413110da253b13cdd69eec5ee3e362b034051470b13964a3099465b3712fda","score":65.3,"score_display":"65.3","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_42c5eb67e57e5181f3df3cfe","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d065a43663d65c9945d3840c0940eb3eb550fa560ac9f14244c6b07847e4feb4","measurement_key":"fac9b5d696562298a3b5043d7081eacf8f3ad4243f7a3d2f62fdf6c344ce6b8f","metric":"pass_at_2_accuracy","protocol_fingerprint":"67febf66d31d5521c9eb0190150dfdad3a229e9ce81cef5873103d59a6c61678","run_fingerprint":"2fcbef936bfad58617cea550bccb91ca868e005f9c15f6c1f698da177fc8e2ed","score":87.0,"score_display":"87.0","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_466c9201a70dbe424a06eaf9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"96b4262b3ca65d762ddd216b89564c618e2fceff025cdee3d84d34fc0c9234c8","measurement_key":"dd327c91e21cc7ec2a5bd092949c3991157dd8d998210ac5d2aa469edf7bc3c4","metric":"accuracy","protocol_fingerprint":"f2deb1a5fb373735d8e5af609ba2b55d428ea3ed188e7920f86f3a3b19d1be5c","run_fingerprint":"5ef851b8417d4a6c2a65534464f51f84a793cfdea9adaff0b49f718fa6f3c7d5","score":67.08333333333333,"score_display":"67","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_466c9201a70dbe424a06eaf9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d96f06e478678c45f97e0e5f5689a3993357faddba3e230ce5bbe7c2d9c37235","measurement_key":"d318129ddc45d30154cd657f449e771cd663217a322bbe7cd3b7dd697f651400","metric":"ips_score","protocol_fingerprint":"4a79c613fb4674130515f1400b113b92055eaa183769dcbd5c95e124fe88de47","run_fingerprint":"0ed6552370699e5cd2481a9a1fe57baeb6161a882d51f6a5e5788925214684fc","score":0.004874136743475029,"score_display":"0.0049","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_466c9201a70dbe424a06eaf9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e1939a07f59946d63ec5082dbd5dc02fff579ac2fdcbf67579fe913a17907bab","measurement_key":"01b33c5fa92a36c84e7194bbfebfb4b52fb831da0f8bd703b8a46efd0ecb99f7","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"3ecbeb7d416014624cabe9c71c58b1c4b38370cca0525874beeb63c17603585c","score":1455.4817158656808,"score_display":"1455","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bf39f31a22c70a3b0ed8abd8","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:14:03.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a898b1220afaed3c63acb3152cfefb9bc5fb3dbe363d95f4e577add44ac1e69f","measurement_key":"d97ff7da409876505bc56117c8f828859e6ce7f2ba12aff7e5974e04e97f7309","metric":"mean_score","protocol_fingerprint":"e3f7f249f7399c2a8c0d9af26f62a0f7271255c991616b72c65b2265d00e5297","run_fingerprint":"7c45647d4f11527c626472ed311e29c2e551a700ad425ef703093cca4de9ee93","score":33.0,"score_display":"33.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_466c9201a70dbe424a06eaf9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"de465e8ba9b2aec95be1ee536932aeb9fb7bfe545e7c6f78e0b16f13d01f1d83","measurement_key":"4faa99f1876e308c498782a9aae40db6e2185c12d9bf177cbf2189766c337bee","metric":"accuracy","protocol_fingerprint":"02e1e40fd693a38356a09be1fdcc0d17fec0ae803a060cc84b5343877a99af64","run_fingerprint":"2d10be2e0e8c6bc67d3b960994c9716637a9a43f62bf5dd4685429451516023e","score":19.7142857142857,"score_display":"19.7","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_466c9201a70dbe424a06eaf9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"cursorbench":{"benchmark_release_id":"release_9acebd5b002e9c3f18a30606","benchmark_version":"CursorBench 4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"af4f8da2100ab931efcb850beebef9477058f56b4ede4353aa0ff89677b6bbef","measurement_key":"b6aafe88b025548e1536794922c4dcd750a2f5cfabb80937d2f16f1d5c25198a","metric":"score","protocol_fingerprint":"e3754c0d659acd22edab1be7e7103caee011039ded39b4c5528aaf07dba237d9","run_fingerprint":"e62c80f6a0331e8b59a20d71dd74f237c328d2808485389c127c535a2abe5c76","score":41.4,"score_display":"41.4","source":{"id":"epoch-cursorbench","name":"Epoch AI mirror · CursorBench","url":"https://epoch.ai/benchmarks/cursorbench"},"source_authority_tier":"B","split_or_window":"official-current-suite","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_466c9201a70dbe424a06eaf9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c7041244874e56c537e91fe46a135aa4d9048b753fbbdfaceb0d592e00e46787","measurement_key":"730908207cbf36cfa9aac59faea91df998cce7796d88ff9931cda348ff1eec47","metric":"pass_at_1","protocol_fingerprint":"951d29baf7cfd97c4c65aa4eddbb9245d35b13cfb7b196883aa8dc2e169aa296","run_fingerprint":"8c32674f624aae890cd7972acb429e7445b7f4811a32e542dcd723e9e6ffa727","score":66.74057649667405,"score_display":"66.7","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_466c9201a70dbe424a06eaf9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"82e64d16d53ef2f84f3674a71c5acc08c7bbdae29648dee993c76f31dcc0bea4","measurement_key":"9dc07075e12316aee0aba00874f8c21580af5d5ba179f7b823cd5c83ce50de80","metric":"eci","protocol_fingerprint":"149f217f6efa014b48eaf55dcdebe61f968caff895e77b0fe2ac433823de791a","run_fingerprint":"cadde62535d03985b8539aa239a22d6d0d53d95666e5e1e1ffde4e3f5f126d2d","score":156.91,"score_display":"156.91","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2c4fefa8eb830ac7d5d0c014","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"095e91129eeb6dd5ddf8efa114df0a5aa297ab31feb02d44f7d35730dc46d820","measurement_key":"94b798a15ef9108973530e80cc7d4e6149be247d942ceb7e1c8106aad519b99e","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"5b70a8512e640283f3787f677a72cf593d4e73fc125f674ceb0c28906a2bdfeb","run_fingerprint":"8f78ff3ec5c52a4a78ff03fea09d0c3b761bdfcd0c7ac0c974cf9b72f3c30851","score":48.010000000000005,"score_display":"48.0","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bf39f31a22c70a3b0ed8abd8","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":78,"at":"2026-08-14T15:46:50.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c457fc2646fffec8cd18e0fd18c22d5c90e2ed52e8c39370ef7a999bbb9a66da","measurement_key":"f0d0da457fc9156305edf82350978ee3ec99ed2f911a25fc61d4f2a607c43f6d","metric":"mean_score","protocol_fingerprint":"1d70122469f92bc372a5aa8789c446f32984b20e1520f06417885ade1646b058","run_fingerprint":"e7dd26eccd45645f2383cc60eb1a1b3c6e0381883d43062199c83a812320ca2f","score":65.96491228070175,"score_display":"66.0","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_466c9201a70dbe424a06eaf9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":78,"at":"2026-08-14T15:46:50.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"414dc1a81efcce65fb7bed778f0d6696e9bcd5718483b5da647bfc036fb94ba2","measurement_key":"4db31151345705853b9fad057cf0480e4f0bfa427db062aaa8fe87b54e04fa1a","metric":"mean_score","protocol_fingerprint":"6ed3f071c5e7750e1f2076ddd705f98a41b812db3c402e1f7fec0f3ba3bb28e3","run_fingerprint":"8dbaed9c3766375f3bc8e7f695215ce7c62b0f8c31f8d0e145dd6d4f7f4c23c9","score":31.70731707317073,"score_display":"31.7","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_466c9201a70dbe424a06eaf9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8bab972accd291166cf2c627f6d2b9e5edef6154cd35e34fd4ff2188208cd3b6","measurement_key":"5a53d3f039e2e42e7e5b60133f7efc49561593f3ddc33715289b1a7e86e8fda3","metric":"elo","protocol_fingerprint":"e51220aa02b5a4a0606a516249103fb5168f4b99d9480c17c405094b1aed30be","run_fingerprint":"2ea02a0268777204f10388ec0c9ee45c902f588a95c8c091292470409dee7278","score":1654.15,"score_display":"1654","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_466c9201a70dbe424a06eaf9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b258d959bf041dec098133264f0b62c0b2b455a0ba7d66bccbe1d9bdbf7d3bfd","measurement_key":"f1dd42a620234ab6868a43d197011fe53059bce539d3042eb6a9c97e7e21cd6c","metric":"accuracy","protocol_fingerprint":"c13fcde4446d6a6ff0bf8d8d0146b862a68bd29478d6cec5cb871fa8a72c9600","run_fingerprint":"8dffaba90de43e133da96228ab296bc0da0c67072af3227b0da56729fe71de7f","score":94.697,"score_display":"94.70","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bf39f31a22c70a3b0ed8abd8","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-17T14:33:50Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"81519fb81c92002bafbac82796c2769911270db8281ba0aca711765685b991ba","measurement_key":"6d3c2da9a453f08d144c37824bd3f17c7eae104ec1f5734cf464419d5638d121","metric":"accuracy","protocol_fingerprint":"cfdbd8716d06d4eedce197dbfe61da5d07716d5493fde410304ed39f2f4a3e62","run_fingerprint":"c90adc67a939d048c185dd19ba8c3a7c17678fb4c75f67e58339d39270de659b","score":44.068582,"score_display":"44.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_466c9201a70dbe424a06eaf9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":47,"at":"2026-09-14T23:34:42Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e77157d94d32664caa3d13599edc52a3d73f0e60d21bd0e58d9f166c889bfe52","measurement_key":"76bafaacfbcdf74a557553e17fe370ed50ec86efe70c1938af41def25c3213c4","metric":"score","protocol_fingerprint":"db9af69fce7968024fa9e31b3d72c863c46c068cbc1d68aac93e81e5d97c7700","run_fingerprint":"21ba530bb0cff724ad20af90f125f29bd9c6f8197dc66527eafc717e656ba93d","score":47.611,"score_display":"47.6","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bf39f31a22c70a3b0ed8abd8","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"94040cccfcf79bfe932eec9d2ab092a0e742fc524b4b319893ffbc4a8f79354e","measurement_key":"f3dc2764ec6a75fe919e17ef7592e29c6a504f33f7842195f6711d8d8dbf3364","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"b6eea57dd7fef315547e9e206f1d162574b824e68c53c4d57aa8e694d4bc2bba","score":78.042,"score_display":"78.04","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_16f1405d00db208b1c4a51a1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d5402037f631f9ed4bf7012905e2dd6a89b8623bbba26af1c548af82cb330ed3","measurement_key":"5ddd1db3e488881308507f70e2fcfa201f32af72a14518c2472885c8bc5d3a57","metric":"pass_at_1","protocol_fingerprint":"0a315b318696d5c83e1a5b03c9fa7c64aaecbf69e5882ca81a74429f866386f0","run_fingerprint":"f2ab4b636c9bee47f3d7a767f496384b101bd27213bd3f6f3e3265729985c5b9","score":88.224,"score_display":"88.2","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bf39f31a22c70a3b0ed8abd8","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T16:48:25.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a59e2d561518fe62afc7fe8798ecb12379339937b8d5272ed1d4faab2e6eff4e","measurement_key":"b4297793c02663e8a8f28a7ce207fd90256767b051f07746988d5979c08fa366","metric":"mean_score","protocol_fingerprint":"54d4c78e254afafd6c54d3ab82a18e60308491b654ad93ca9f9d0e896cc59b43","run_fingerprint":"c6117af0569720118381afe03ef0b8e31af635706166995716bd28b647a0f16e","score":41.11111111111111,"score_display":"41.1","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_466c9201a70dbe424a06eaf9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"99b662c0dda473d55aed96672238c814e9cc9a9006b667f001bf991599c704be","measurement_key":"a78a4a0a6344f5f7ff8c41895e0f1550eff42d421e1b9ebed88a6718ed708241","metric":"accuracy","protocol_fingerprint":"c238afa94e515e843c09035f27351d1e0b396c255da87edf0172065d11d9dc3e","run_fingerprint":"e20b1451a6bedcf0b124868488a586f434575458ab0e81adfbe4be2b93748836","score":89.4,"score_display":"89.4","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bf39f31a22c70a3b0ed8abd8","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":78,"at":"2026-08-14T13:47:42.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d837ba58f98f3965397b3ec568984f7eac97b316d24d082428ea3547d52ecc41","measurement_key":"517a3bdeade5c567a781b76ae44c74c66d2d2f3b92b104ea799962d092b5d69a","metric":"mean_score","protocol_fingerprint":"c93bc277c165a94c5c0d5cc658ffaf45c61cac8abd5fae1685dd16212920b64e","run_fingerprint":"73e1a2f5c882e984c727799374e51e5de3210b8c14ef884bfca233af43e13e33","score":99.16666666666667,"score_display":"99.2","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_466c9201a70dbe424a06eaf9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e235f7cbcd9972dadd6830ed750c4bad9ae452b5cfff3a0b075b4e7ff5e71295","measurement_key":"3e0f7cf61f2c0bc2b8ac4493a9185eebaf0ba28260531aebc243df3ec627c2e2","metric":"fully_resolved_rate","protocol_fingerprint":"8d9925817fafce60c704686d6bd4d4c6f16de1dc898c939ceb740aff75c03afd","run_fingerprint":"8debe7667f85c956498fd7cca528c4785f4852aee4ace97abf5fcc36ede060c6","score":1.0,"score_display":"1.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bf39f31a22c70a3b0ed8abd8","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3eb8a6649fd58f62cc587179502f697d8807833b29d1f2d8660022008540b04b","measurement_key":"607f29f3df184e13d2e3f22d1d444a0fadc7df445d90a53c33fb10b70fda0129","metric":"subproblem_accuracy","protocol_fingerprint":"78ec003137b0540953266132999d87a5b81cffe8adff60792b3d1571152750ca","run_fingerprint":"dae123af0fe09d9b0d5a26689e7eed800e1a2536f58a86ab5ac1f73a3ff5dc99","score":53.0092592592593,"score_display":"53.0","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_466c9201a70dbe424a06eaf9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5a16f18bf9de515711e931045d46170eb32b7fe983d9b3e5d65c5a5477f7b624","measurement_key":"eaafa44bd50e4332cfd46cb5c591997d91c58d8b8ab0e8a9067951bda581402c","metric":"accuracy_avg_at_5","protocol_fingerprint":"6333f90af491572b991ae0a443247ffa5468890e9143e9ab7c4cd0c3fff81cfa","run_fingerprint":"c9146da17f50da205540536c98c535ad8635576651e75664a1d7c5d40ecf81e1","score":75.9,"score_display":"75.9","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9702996790d011ea744f76f7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:29:19.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"75ef1504ea6d448658071128034b2727ff70fbf52defc8336d7813fec909dbb8","measurement_key":"4c0778c6c1814fabea9fe4fbc2503e7c0b95d6c714b107f955e309ea794694aa","metric":"accuracy","protocol_fingerprint":"da916f7fcb980502d9849f78cb0d5296fe195cadca371274fe57d0a51007ab2b","run_fingerprint":"f84084e21d3b0c30e46cf9b41e5b4bbef77cdf3f77d5cee052c13f7c1791eedc","score":48.9,"score_display":"48.9","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_466c9201a70dbe424a06eaf9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8236fbdfbf810d9832dce5956d7a2bd0380b7f6be56743ba7636d8d9842195c0","measurement_key":"dc3e615e8d8b951aa8752feb6f26a5d84ee7282d21b5b283f73c9e9e87318a34","metric":"resolved_rate","protocol_fingerprint":"f81711268b3c272ae18ed117647dd4ef08a0fcb2f8a8f6b28176dec36e465d02","run_fingerprint":"e365639172ce2cd9646ecaf47f94cb660642dad1333e85aa81bc7fde09dc7b7a","score":95.6,"score_display":"95.6","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bf39f31a22c70a3b0ed8abd8","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8236fbdfbf810d9832dce5956d7a2bd0380b7f6be56743ba7636d8d9842195c0","measurement_key":"dc3e615e8d8b951aa8752feb6f26a5d84ee7282d21b5b283f73c9e9e87318a34","metric":"resolved_rate","protocol_fingerprint":"f81711268b3c272ae18ed117647dd4ef08a0fcb2f8a8f6b28176dec36e465d02","reporting_origin":"organizer","run_fingerprint":"e365639172ce2cd9646ecaf47f94cb660642dad1333e85aa81bc7fde09dc7b7a","score":95.6,"score_display":"95.6","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bf39f31a22c70a3b0ed8abd8","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-09-17T14:33:50Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c26ba28734c52659922edefff8815d79ad683271418ddfa087e9ef56349ca6c1","measurement_key":"b8c09f2fd88978b8ca1aa0d759f5d1d6d10bc5ccfb64b2300fb5cf8053c181de","metric":"pass_at_1","protocol_fingerprint":"849330db086932ad1604dfa534e630eecb6bd61c5a7d8bcded83bb69a578f5f9","run_fingerprint":"2ed5bdfa5ee7fdd13b36a56dd668e47205f0eb44844e4249353ed6c826d83403","score":43.298969,"score_display":"43.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_466c9201a70dbe424a06eaf9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1dc3ee798592e803269ec80f39cee2ffcf61c3f005b63546849dbc8443350f22","measurement_key":"ea5eb2711d52691e3df35b8c1d18c0e14423d87634659d1fb7222f31fadf1c1c","metric":"accuracy","protocol_fingerprint":"24d04cfd45fe816969d620f9b1a0e9abae525a985d6b3a68b2e43580a9a020aa","run_fingerprint":"57cd945b688d5dad9746d0bf643cb6603da4229a20773b1042dd0fd37ee90027","score":78.277,"score_display":"78.3","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bf39f31a22c70a3b0ed8abd8","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-3":{"benchmark_release_id":"release_ceb36f25882d8cea2c9d084a","benchmark_version":"3.0 · b936386b-4afd-4ad7-aa7f-6b52bcab9853","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":80,"at":"2026-08-12T22:31:18.697086+00:00","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ea737046f2ed875df0461c20cf6120ade4fcb00c85ef37916db65f211a2c46af","measurement_key":"bc61f836bdeb6dc72740dec6abac9f6689ff3d810eb37096a30464e05f5084cb","metric":"accuracy","protocol_fingerprint":"cf3c5bbd00982510245a76df7e2e0a8eafa12c3cdc98a1b67f186bc10a9160d2","run_fingerprint":"0d7ac4f6331e114e3c830017f0228b9791c6933cdef6d873db8a4695bd46724a","score":26.49,"score_display":"26.49","source":{"id":"terminal-bench-3","name":"Terminal-Bench 3.0","url":"https://ofhuhcpkvzjlejydnvyd.supabase.co/functions/v1/leaderboard-read"},"source_authority_tier":"A+","split_or_window":"official-74-task-leaderboard","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bf39f31a22c70a3b0ed8abd8","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bd5bd3dcde731797e93deed89e5ef04cfc490598189d3787ef1c198c2c244acd","measurement_key":"2c6cab268ed633577275a215c48f9d3204e357ca0ba2002becc0450cf18ef494","metric":"accuracy","protocol_fingerprint":"1e5e078634102ec500327d1141cc3106a52938d355d6995fdf8e0ee54a7e3115","run_fingerprint":"da74a87cf0df39fe3a06c3f3d3a9ec970f3083098e4852a4bae5f83354a3c1b6","score":17.172,"score_display":"17.2","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bf39f31a22c70a3b0ed8abd8","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7147c7373767915799d8fcfeb54cd707cbc2dde03e9442e50e30464d7f44ad40","measurement_key":"53b016b766ae81b7101c358e7cb56ceedfc6f89e5d2ce514d13b7d04ac191314","metric":"accuracy","protocol_fingerprint":"ea7aa94fce34860455d5930f77d7f0779744e5c64f59036b79587b297dec79e4","run_fingerprint":"bd332329443966e6a810e8fb945051b768ead9d12082d3e02ecfeff77cbd0530","score":11.429,"score_display":"11.4","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bf39f31a22c70a3b0ed8abd8","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6f763412f1a4480c09ec643a48abcdb609af716176a0e21539be788f91da2049","measurement_key":"9141c3438ef1084e6743019fea609173c9fc757215d87b504499cfc7af6eb552","metric":"mean_final_balance_usd","protocol_fingerprint":"a904ed276dd3469869303926a854441ebe2a2f6ee78e0ccb7665fa02faf182d4","run_fingerprint":"4f985f16a80fa7feab98175dc7016670de7c45f511bb87377f00e23209d40162","score":9047.032500000001,"score_display":"9047.03","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_acb04e327788bc5d55cd1774","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7db9c879364828e26f3e7543a218fd9c2064b4aca4ccc2874603cee569f0dd60","measurement_key":"efa680455d39c7bc83da9fd1f9c0302ce080b60d5d08b5b3352fdf44a2fb0604","metric":"score","protocol_fingerprint":"38d83417ee8b353264646e28c5708757ab3cc92ceee3eddafdd46f26512113b4","run_fingerprint":"813870c0494145ce46e9b34ef756948e0c0d9bb44c2f7525459c6686d0a2c12e","score":76.239,"score_display":"76.2","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bf39f31a22c70a3b0ed8abd8","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d9ec62881b507eda71a8e5ff9cc5fa2d049d663a0cba73fefb5dcf3d7e4f7e93","measurement_key":"d231932176311fc606798958223c7e929782bd0e1ed8c6f1a1ffb8e53b31e5fd","metric":"arena_score","protocol_fingerprint":"3c439afe3cd7d7ae939af8ab5b79d883c1c1b10904ee138f6ee235176521c39e","run_fingerprint":"32d6a38a21887795dc4cce8e1074e3cdedf70bd01a5f2fed0360b390caeb5bed","score":1616.3867226095672,"score_display":"1616","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bf39f31a22c70a3b0ed8abd8","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d0af1496283121a4bda9b5fabccbaaddfc1593a45025ddb1a13ea70fee02fb3c","measurement_key":"b3d6fca4f23a79e51fbee339ff5aa6273e1284c39ddeb25be8ec3d3ecc9b7035","metric":"accuracy","protocol_fingerprint":"97d8f516d27f31969b45f7d72b7d15b3004d5a73f2cbdb2d0d84de6d1740d7eb","run_fingerprint":"9dd793496fe7011a8c6e46476866e47f600f29791c59ed737043c49d5999a875","score":67.29,"score_display":"67.3","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_bf39f31a22c70a3b0ed8abd8","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"xai/grok-4-6","model_name":"Grok 4.6","parameter_count_active":null,"parameter_count_total":null,"provider":"xAI","selection_rank":27,"weights_status":"closed"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e09886d7e6355da790321c6149d40caaef73ef17a58d9f305f3701df194fba4b","measurement_key":"bf3b6add1f47d42985a2598b1f174bea5703cbee031da1b5fe3c624d72aadbb7","metric":"index_score","protocol_fingerprint":"6ffd600efa000e10de64714a486bee8c481258e5f579139fda551925122bcf6f","run_fingerprint":"494feb1723c78a055ad16b4b6880740c3d19d7eb9e121d7ca51954a38076cd9e","score":27.7552,"score_display":"27.8","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-10-01T00:44:58Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3d615a3401f14e269d1943ef450debd7ec5c3385a357fda2efdf3bf409eb3477","measurement_key":"cc6060527e8015bfa59c614ad668f66e4fa0185eb01463d64fe0ee1af777ea06","metric":"performance_rating","protocol_fingerprint":"187f849bb54a75712c9a6838bd1bb2e80773d3ef45aa8518c75a7ed32b8d41bf","run_fingerprint":"bf2bccf600bc93ff68a17d58b384f0bdee4170448f9bbb246885291533c588d9","score":1576.92,"score_display":"1576.92","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c3fe93be8d4fa0fd59bc2d19","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-10-01T00:44:56Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a16e2fd04a73bd62231c79b058394a3d875ef21269a2dd48ab4723305be8d4b3","measurement_key":"7a895395a53097916ae5630f3f130608ea15289a0b78f3473adb6ec0ee5c6e9c","metric":"pass_at_1","protocol_fingerprint":"209c3d5c6e7827761c8410e15af99e9f7e7e411b29820fbc293b2ac9069cc81f","run_fingerprint":"d6b1ce8006a614db7ad817a933f8e6a3cd1810ecf5c890299650fc52f8a22201","score":44.3,"score_display":"44.3","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-10-01T00:44:57Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"04c524067ab8c581a9c387cb8da0dae9e9dff55387e0b1c908fbf2f886219e31","measurement_key":"ea7bc0c2ecaa14776e00b853e4b6331d36f0eb405cbdea7e44a0b285f75f359c","metric":"pass_at_2_accuracy","protocol_fingerprint":"eed432f169eff7b8754f49763493b877a3d28a5bc99b079c4137be046585d784","run_fingerprint":"0b3921c0379dacc3bfb6c7eadeaf40f5a4c5285271464e3daacafef68f71f269","score":86.66666666666667,"score_display":"86.7","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-09-30T18:53:20Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"795c290b8c25680d491dd81b040900ed7c15ab9a3fd46861360bd519f74ad5bd","measurement_key":"0304e449640710fcd42324ab646970bdbf0ff6cb62aa90935a4db5a8b89d7b66","metric":"accuracy","protocol_fingerprint":"acc7fae2580193dd8d8dda87d8933ecd7f1fc199f9fbe30a6a65459cc2f0fa72","run_fingerprint":"45393279f940f58cd0467d4d5f0ad201543cacd0805f4e931f86448659be7dc4","score":59.30555555555556,"score_display":"59","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"345692897f8bd0a4beb7f18c816b28b0823531f673aefcf55188087574f64816","measurement_key":"16412d03abb1e5463a13f048ce343ba6121713f235328c3c8aef25a5c37cee4d","metric":"ips_score","protocol_fingerprint":"a3509388d1bf9f5b3b0b647b1835a5b447a2c0d552cd02567dff967b409c69f5","run_fingerprint":"fb49145da4ceb168ba89c13d96fc5d5300d600f21889f04ee7540e59c20cab05","score":0.02225749002662884,"score_display":"0.0223","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bc3b8b1de789210d94546f46918673e69a257f5513f92a29b4fde865c4558c0f","measurement_key":"5832fdaa4de5d7abee1cdc528f31f0b162f4ab32382592fb83e003ae4807e046","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"06c0a110759dc893e920afd636e66df20c374e8a5d78ac155a8f759004516dab","score":1440.8674264272704,"score_display":"1441","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:37:06.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4a707e2253ba0cd0921194991d1ae7617db6b218e41a06224af9a1965bda6e37","measurement_key":"0de3f8bc38078b21e4756807ff50f8cc7e5aa0da7c44693f9e3cf5fa80731bff","metric":"mean_score","protocol_fingerprint":"e08da095d58a95c9091dee9f5c6a93caa4c6b0f281204720f5e8776ef081e51a","run_fingerprint":"a4de6cc3cfed96284b6eac0f57cf6151f7a6466f5bd7b5f30f7ead1bf11dfadb","score":36.0,"score_display":"36.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"af1759b747fb2371a6f14399b2ab9796696775a41b8fd8c583eed901f8a4c247","measurement_key":"6c287ec60a9291c44a2c0bd128eec915b0d1b81cd1f65032b23c533bd6a16a13","metric":"accuracy","protocol_fingerprint":"f1290bc68b31cb81971ab6b7a7ff1de1a633d71dd1b7c6e10adaa7be0f0a2d21","run_fingerprint":"85d51605446326061aca78dbb6c5a9561b2814c7d17ec6f9f0f9da5a5d23f030","score":19.428571428571402,"score_display":"19.4","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"58b41329324326883a753c685a5059ca581d7add5463ff031346e633474aad76","measurement_key":"18aebed80872d861680573ff280808e4b73bd2d6941b062b122ff6147fd7950e","metric":"eci","protocol_fingerprint":"234c9b3e03a9180a88b15cc6cb61881a1465a2879362b31247cca51149788edb","run_fingerprint":"0413300d73706b511925e5d3ade2573c0f82646810845ca0b86b91ee16afc2cb","score":156.75,"score_display":"156.75","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f89a3ff70a89c2059aea00e4","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-10-01T00:44:56Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7f7dcdda4f46afdd60236e67714fa925506b5d6e74468757b4013b1bc60421a2","measurement_key":"24cdad352b873c75afd40a363c81620a608ec8720380526e5f6a0264ea42f89f","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"0a6c6cc0cc8cd63bee36b5a54e5a6696b3e36023dab704c63cf28436f2c91adf","run_fingerprint":"04e2c930c878264e31ca5cbadb889b5d891b4c1382bf6fd6740db8d037341fb8","score":42.42,"score_display":"42.4","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T22:14:05.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"15085814b4109cc7e5040e5998967a7eeda3ff68a773a06a27f870c5f7f2ea2f","measurement_key":"e8dc148e80f782e263dfb344dfce09cf1f9ccda3d14cb338dc53581c7fc90348","metric":"mean_score","protocol_fingerprint":"afddc02d7d2d96b25d4a0797f0a91eb3d6acc65cb504e2ac84997901fb605d67","run_fingerprint":"e6905cf6cfd7f15411d63affa2df1a6a8a10f0270a1c5b6ab49de46e3adbfb06","score":78.94736842105263,"score_display":"78.9","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T22:14:05.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dc0f11c97ddb4b659e3f200cc9fc99c8d4aa292be7ff65f699382edc9927c45a","measurement_key":"2605f37df0534a67a08340be44a8a4584ab35a705f167fa625a0e6d4b0919541","metric":"mean_score","protocol_fingerprint":"521221b6baae86dd00715ef32c0e7fd47ce2cc18b3abe424e51a2346c132866e","run_fingerprint":"c88c3fc43ac8e0a2a4b8c840fdce5de1c917993c23de81efb377449dfcd7a791","score":56.09756097560976,"score_display":"56.1","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d4abe2c8d3ebdb6a36b3bf0666bdb526aed4d8a024bdb951f0dc74686787d8fd","measurement_key":"1113fcfdc73d5042fcdecd49fa4b26864ff27b2a773e5be3a0002500a0d12a5a","metric":"elo","protocol_fingerprint":"b89e84b47d5fc884417139aca664494be0c6374fd97530e1cbc3ff383f574a23","run_fingerprint":"ac55262cc6bd2957b4938659af0137f51267d4c2eec5b3ff3679306fcee1bb78","score":1444.46,"score_display":"1444","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T22:14:05.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"41ddbc414abecbef3fc362f3d176e4382f3573674e8da2445b465b6200a915f9","measurement_key":"6b5a287c1cf8c3dafc9e0fda60a3278887606b0bde5da835ef721857ca5018e3","metric":"accuracy","protocol_fingerprint":"4f8894782fe7146bdd6e7823b91e16cebd928ac74a010334a517c63a28e2063d","run_fingerprint":"6b091a572b5dea41b3780605c126f851a6ed77e7e051789b471043bdc0cce284","score":90.46717171717171,"score_display":"90.5","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8c7c223d97cb2b7760a0681e7533d6afb2edbc25ecba5f1aa33121babf5c0274","measurement_key":"80e51476fe700a6e1709b8593a3ad89c89b1f84bfd5d0da54f9a9143c3a0d13e","metric":"accuracy","protocol_fingerprint":"1f7d8f877d274bff3d1936f26c62e7a0cd51413f01b278407dcbf65da8e1ce74","run_fingerprint":"128403799703a9a8a4b2aaf71b38e246295a98afd8e0d3aadc353ca243564e2f","score":38.507878,"score_display":"38.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-09-30T18:53:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ab33740e10842577d841872d8ee2bef4d381bc885d2c9f835e5957e612d60efb","measurement_key":"9cf1abd72084821cc9fec688c21e834090fc444103ad50825d869693654200e0","metric":"score","protocol_fingerprint":"47fac0a651f82a10bce6311cd89567a2e78c60765370744609e45aa13c63cdda","run_fingerprint":"bf3745f8d0ebf59ec31f40137629b2b8b02f60907c04484040c7e0259617aa09","score":55.556,"score_display":"55.6","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-09-30T18:53:19Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8fcedb4d33559e8cc97f3dc7a373238b46b044b6bdb5455b51aa8160fd54453e","measurement_key":"a8d7bc5c820ee4f23cbe1023aaedb1098ac72209853c9ea5a844bb422fd48e6e","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"ed3738fc571fb52e5bd13f0071816bf3890b8bc8073b4b03d486729f70619117","score":72.02647619047619,"score_display":"72.03","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T16:48:12.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8895df96ff2fad48b221e5e48ae33a5ecd45bd555bb215c1892facae2ec795b6","measurement_key":"ede4d84664b24adecc1e26385b033e8d3ce03884e41f28e0baabf394105ba65c","metric":"mean_score","protocol_fingerprint":"1601ace96b6de60c5987767c19084e0d476b0a5ed13701b20147bc0650d63f00","run_fingerprint":"c3c9f23b6c468b57f64377402ae69df6fd8871718c180194678428583641b9c1","score":26.666666666666668,"score_display":"26.7","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":30,"at":"2026-10-01T09:31:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c0b8e9a1fcf3e011eed11a2392c3169b3e9ff3d0a5149b62d9bf5bb06de430be","measurement_key":"29a0ac872c9d4416d8e70ded8db2283e77f4b5f52c57bdd912569af7613a5be5","metric":"accuracy","protocol_fingerprint":"06302ee11935871f63c5755b7d04257ccfa327f736e4e7c292bc3bdd296f64e2","run_fingerprint":"74c30619d54051e1ac077bcf11d23efb9660613b173692bc1efa846f545b0118","score":79.653179,"score_display":"79.7","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T22:14:05.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"df00660f1bedf20388788b9b95d5518e8fe1f37679643c66c44280fc3d45cc98","measurement_key":"fa85c2688f9cb00b855bdca77e518a91d44011ba6108a15b0da11c63ea0556e2","metric":"mean_score","protocol_fingerprint":"f54e9344c5dcccd9c9099f125e8e3dfabc47aca4dc7b6a2376d820bcd2bc5cde","run_fingerprint":"e985dbde71475e7d462cb8ed985df5ba6c5c3e4296e3d6b3432a9a620559833a","score":98.88888888888889,"score_display":"98.9","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"544bfc19678add41f7f95b6485fd8b17c31f91ecc334fdf85640ab471b6d568d","measurement_key":"0ace6055a34820e552f2d1a36209eb1d9ddde61306b850a25615c4c27ed599dd","metric":"fully_resolved_rate","protocol_fingerprint":"49ed034cb414feddfc6387d7b5dd76669b7aa8f94e2c9d0ebbd45d8f6d012c36","run_fingerprint":"ce8036c001cdd89631bf451827f6d9c5bfa208fe473d56d7a392d30b1e757837","score":0.5,"score_display":"0.5","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"45af8f467debac540282971e104a397698fa736ec9268618deb89ba30bb216a8","measurement_key":"11e6f9513e04874a960f0586b38c412d69627d515ddee50e2d5707e8dcce5e07","metric":"subproblem_accuracy","protocol_fingerprint":"3fa5d2fd06f1e529029ee43e1ca970898dddf947620e3d97dcf61bae69a4ad2d","run_fingerprint":"2f64b38181de3b7c262a79b0f52b8bd319b004638c1cff4974d4313f100676d8","score":54.6296296296296,"score_display":"54.6","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T22:14:05.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0f238a1f48e79f466e9cc5f30d6c1f4e78fb659a56809f1f065e4040d74e6443","measurement_key":"108e1b72c1d0c98055af464a72926a143c3398eafe8e4cbb85efb1502cb4745f","metric":"accuracy","protocol_fingerprint":"e94db4081e6470cebd76cf723afdbee751fd5ab78aa7caf1dce8051428180c7c","run_fingerprint":"7b9428dc449b5d11d3ca4d4a1de86184855ac256e07bc69c09f59402cea94fab","score":41.4,"score_display":"41.4","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b73da222b60d7fa93f4163a36cb6d9db211db8215ff52104bd4134f1155f86e8","measurement_key":"bb7cc39a6a24014b16261f4b31fc1ba3db788b97b10f71e2077aaf038236341f","metric":"fully_solved_rate","protocol_fingerprint":"44257bd57b7d53c083cf30fa16edb50764c41fd55c5233eee3a88fd85e1451e5","run_fingerprint":"ab403096f5baecf83430556ec0a62ebca536e9e5695936f98c31087177a34534","score":2.672,"score_display":"2.7","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-09-30T18:53:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5e9385784f690a1e7c363decd3e17b20741bfb056dd8a00c59219b180d7fada9","measurement_key":"1c2d6df24164a98cb0f2bf91879ec0c316f0d8f37d273cec9b6935aac74d739e","metric":"accuracy","protocol_fingerprint":"b97b7878b69b69f88b14e51a1b50b7590089a145a20f3e54d6a7b75df4842fa6","run_fingerprint":"2d19a6065a7dab7175f956c4caa3cd701299ce6b872cc75aef92e9c556bc71e6","score":73.034,"score_display":"73.0","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9509276b8ccac1dfc11443e7e542e749daf0d8b2eb307e27b5eda134ce2cb45c","measurement_key":"c865f65ca37ba563dea495b673a796c298e4abf101e35d5bd23feabf79fc1181","metric":"accuracy","protocol_fingerprint":"34846358d5011649347f498550c1885ea19b167ac24b18f5e10c54350500ad3b","run_fingerprint":"d4f753fcb2320ceda48830d9b4e16e1d67d34d12f1ef8dba418f38e01d98a4b3","score":13.636,"score_display":"13.6","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"93b4e062a592a8a60084ddc5d6e27ea7114572efa2e8ed364cdd79000e6f86c4","measurement_key":"1d4f0a53d50c5664210af114a3e8e02e27ffea7cf961a55dc897f2c812ecfa6c","metric":"accuracy","protocol_fingerprint":"5c91c0e98fc01eafd618671ec69f135fe0cae45189ca7eaf35e078e90ba211d4","run_fingerprint":"925ff00c9ac33911632ec3c9706b902477ef67a99244d092c13464158e171f80","score":4.286,"score_display":"4.3","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-09-30T18:53:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4c1016408b1000896481170b61da3a9d87ca4ad49188be0efa5237e59b9d802c","measurement_key":"c5a2cc3241a7588f54371af69c1134c093d60d2bb4f001436ceb08a034cdbad7","metric":"score","protocol_fingerprint":"6990ae8177f7de7e651ad2f7bb9b3bb7275dab96423fcfb41783b28e9df4887b","run_fingerprint":"7d85c63980d57ffe861021cb90be62a164463b38febd2d4e70b405badf8de3c3","score":81.649,"score_display":"81.6","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d4643aec594442712a5e2da11346346c9e871776ed7ebe833fdc5a23fac6de43","measurement_key":"35ad123dbf99ba549732392f63017440ebcfe17530581e31c565305c79aeaac3","metric":"arena_score","protocol_fingerprint":"65bb3c6871b7029c925b6cae53e96692e7ff08278b3f245fe85e4829a4d9c47f","run_fingerprint":"ebbfb769276be162ac8f0ac3d971b55b4c4d0f4c75e0c35db7226e34ae3e2de1","score":1579.4041580064886,"score_display":"1579","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c5c378717d51c7077b3462a2","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bbb54fc6e87e82f628a303b748dd03eb6b53eee3c8d6cc2acdedfdfe502c4e6b","measurement_key":"47ed2a072d67cfd40fd726aeb88085fb10730e4eee1ac4fbfc36022e833565c2","metric":"token_efficiency_weighted_score","protocol_fingerprint":"b8828ae6627c35958f7f5f7a7b4a1d268687438eeb1a8644428696400b62e285","run_fingerprint":"8f5651919ff24cce6c7e024ef8cfafcbd3a8badb622318c8991be6afb234f4a7","score":7.874124242424243,"score_display":"7.9","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c3fe93be8d4fa0fd59bc2d19","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"openai/gpt-6-luna","model_name":"GPT 6 Luna","parameter_count_active":null,"parameter_count_total":null,"provider":"OpenAI","selection_rank":28,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3008c748632e2d64379da86146689b5c41fdd6fb6849502791e20fecf75bf8a6","measurement_key":"a957e03af82a2c5e8836802d8582ed9e2d009ff82dcd241993bad99284d5c7c8","metric":"performance_rating","protocol_fingerprint":"139cf0ed306fb30eb9c7474fb6fdbcba0ad7b6b87896baf0fe2b823b0e87b094","run_fingerprint":"731fc1abd9f3d76e6178794d821fea8ee361ebf72e6213205e103c2c5b4a646d","score":1323.05,"score_display":"1323.05","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_a98b3983e054c2e804d5eadd","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cadcd474d61558519bee7bace300c8d4f4e17b2b96fe4b4fee38dd9b077c04c5","measurement_key":"5983cfb6fe87a60e2a125104835ebb1bfafbec38bfc70806605a0233b11a0376","metric":"pass_at_1","protocol_fingerprint":"94ea485b152fe88074253db3ec0e335d447550a40ee7b3563c20392013ba4ada","run_fingerprint":"1fa31c554139b9d7ca6bc5b0c5510134f700bf2c0071861c77a39795a9f46b42","score":49.2,"score_display":"49.2","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"appworld":{"benchmark_release_id":"release_3fa145932216c0afcdd9dae6","benchmark_version":"official-c1f56015cf7c","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":60,"at":"2026-09-02","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cf02cbfb2563fa4f2bbca89b8d80a86dd0c02305f14d98aaad6b013623d36369","measurement_key":"e2a7401890a158f419738194bfcc893a66dcaba7c6f5301386ade6fbbfe7b74b","metric":"task_goal_completion","protocol_fingerprint":"a224489dfbe69501c48902cbd5c7303930991bca8273c1a7269f09203a141099","run_fingerprint":"efd7c4125bb761854b420db11628d2ffb03e05c078f3c082ff47ad18d86373be","score":85.6,"score_display":"85.6","source":{"id":"appworld","name":"AppWorld official leaderboard","url":"https://raw.githubusercontent.com/StonyBrookNLP/appworld-leaderboard/c1f56015cf7c3441ff1933f5bfbec879798d7bbe/experiments/outputs/_leaderboard.json"},"source_authority_tier":"A+","split_or_window":"test-challenge-all","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_82a761bb656269ff1042ddf1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b766a2a89245241c19f177d46308eef49aaaf481c4f757c4316ed2f540c3d52f","measurement_key":"529a72b524e3df0e56e37895a25224e5c11d755a907c59a3325bc5af8c714612","metric":"pass_at_2_accuracy","protocol_fingerprint":"9e60576dccc5cb95fc28b9550b2148d78cc1e9210cff2b06fa0049c9379b7c89","run_fingerprint":"11e3c70819fe67f6ec0f1ccc8ca54e1656c2e96cb19e74dd28fad40b7261020d","score":92.0,"score_display":"92.0","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_c66f5b82bd3045b91ad807bc","benchmark_version":"ARC-AGI-2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:43:25Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c852770962a8212b71c7e50843eead808829678661fc9b62fe2a4ae127ae286a","measurement_key":"748dbaf5dfdecddc4c69d671cdddaf89a3be1ee0574d12946b27b12c3fee9b96","metric":"pass_at_2_accuracy","protocol_fingerprint":"9600efb6cd1778acbe3b03291aa2b77de82c5d3cda92d4d59fffac24b028bba7","run_fingerprint":"e2e1cc58373390f67b0b48c92e53f3c49a3c404dede08737279234ddc4093319","score":75.83,"score_display":"75.8","source":{"id":"epoch-arc-agi-2","name":"Epoch AI mirror · ARC-AGI-2","url":"https://epoch.ai/benchmarks/arc-agi-2"},"source_authority_tier":"B","split_or_window":"evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5663cba391b4a5fc1d1af87f384ef087ab93b8bdbc7204b81b84b6e616e7e444","measurement_key":"055d22bb4bfac2c9fa6fca771d72dc845ee52bb4126482aa77a9ad876573f76e","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"9bdc6d0940f209ece7fa9f450d2eb825eaf66d4ae3490d2f727f6d68da712d34","score":1501.0497826033693,"score_display":"1501","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_1c905f9be1ce4940b60cc62b","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:36:23.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ba091838f1d5de2f9843b21057ab3d30b159a5ca51db397d9c83aadea2c25d48","measurement_key":"0b4efea728cd3c890ef1af9fc711ef93c27d02e550a90ce3fe1074a457436328","metric":"mean_score","protocol_fingerprint":"1a210fd6ee7b22d9f39554a073841e2ed8d6a6119a7263dadb15eebc9ae20663","run_fingerprint":"f6cc02c57980fdb88867f6baf75a5d5f5049486b3d8889049c9be98df11debf6","score":41.0,"score_display":"41.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:41Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f107668c2e5936aa4eb6cdf132d83be520796eeb48c9f62987c9863988ecf4ea","measurement_key":"000d23ace0ac621d5d4260b4754e79d9e69cf269b5da64bef9fbb7a23c873585","metric":"accuracy","protocol_fingerprint":"ebdb1826134f5d76dcddd272e4fbf9800158d6132a12d69d58d186d1f72ec275","run_fingerprint":"156155c996486e4d40d9c4567ad459bdc7df766c03f9cff33cdca8cd36a4f1ae","score":12.0,"score_display":"12.0","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"35d8632e5ea678eb1640aca31a18264fecf0f7edb481c1376e3381bc61c96e22","measurement_key":"f24921067deb9c887afb061a870d29e14f5bd9dabc96d6a466c0f130871ceb73","metric":"eci","protocol_fingerprint":"f57751b0fc61399bd3c3114de36e13164d73dfd2eb59793f912ea07282dfec2a","run_fingerprint":"6b3171eb6ad1617f6e70303c9c7ed923010e38cc02722748dfcd460da86ff277","score":156.7,"score_display":"156.70","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_bc89e06c89d745c77565b69e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5b2286ff66f868bceb66356e28dc3e0b0280a3a13db6a06e4a4868b032f2c19c","measurement_key":"95d9a2b31eb5c4d342724aa38dedae2becee8269d99cf2f97cff7c3a32ce3735","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"cfb3195eafc5e45231888af39f986755ca83f74a702dcb5243a8852e0f4f4942","run_fingerprint":"ef5b62ad3d0a3c66ed21fce0541efc47239ca09adf7e4adbeefa22ed17e0eaba","score":38.54,"score_display":"38.5","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":143,"at":"2026-06-10T21:41:54.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3cca82bfc2e31c1e3ef47646d76ff3fde98c81642483c137d7ecd461d9f772b6","measurement_key":"519f3ac7e27a1e1344bbb1635bb00193d7c92fffd0aa99f0b5f038c32087b026","metric":"mean_score","protocol_fingerprint":"2af8f172defdd8b9838fc070e6004727cd471180369f89d718b207d85964416e","run_fingerprint":"3bc19aade29220eea03c05e75c099cf382eddf2d6ba3c9099fb64c2573bff137","score":70.17543859649122,"score_display":"70.2","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":143,"at":"2026-06-10T21:41:54.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e4209f74b4d1092572b29f991a795e7c6794c7dbd936717393ef3c20968e9bd9","measurement_key":"4de3909b3800a2646502b7e07e45cf135637f538665e581aa3de28b1aae3fd6f","metric":"mean_score","protocol_fingerprint":"4b2aa72f1aa2a2342d6972ee79194b6b97e00904c2418a36cfcd8df4fd9e170f","run_fingerprint":"03fb332fd475adc6666362391691695b20bdc6216a4b438d9a8b20286f7ba533","score":31.70731707317073,"score_display":"31.7","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"323743c629845edbec7a9035381315e60b9aa5ff4dbd5dcdff9f91da5d28b00f","measurement_key":"c238b76897c52a175a9bf2739f67fccc11be34ea27ccb03fabd9fe3b71b765f0","metric":"elo","protocol_fingerprint":"1e9829b67a89ac1a0e261fbe8c9449e686e2eb6f22d8dd00021d057f1aeaef57","run_fingerprint":"1c7a6787ddfe92847cfa7cbdbbc115667eb97870bbe6aca9d23692e9a88b8e92","score":1361.69,"score_display":"1362","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5c1d601cffddadf02729039030d3718677ebe5915a4b295504f0aaba280ee844","measurement_key":"b8d62b0b33dccd95379f8cbf90dcadacd3e214ac6d539006c439285ea753a180","metric":"accuracy","protocol_fingerprint":"728264391c56a8d3926c2278c00792a8b7b88e8f70764caee51e1c0c2ebc63a0","run_fingerprint":"2ed5aa681bdba878f745ed49f7ca58f7cfa898cc520ac219f3a70b75b4c0b98a","score":90.152,"score_display":"90.15","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gso":{"benchmark_release_id":"release_176f07ea4e9e0b8dfeede990","benchmark_version":"GSO current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":188,"at":"2026-04-27","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"f37195ed56d53df0e057c7fb0dd8d97066a9cacfff79338c22f65f13f0594189","measurement_key":"3daabfb10f72931b0102e93cd45342269b947d60b4895002732dd822c0bfe377","metric":"opt_at_1","protocol_fingerprint":"90fc44bc011dd559e0a60b3e81a8069f34dec6660bf522853493ffc7bb164ea0","run_fingerprint":"afd102f0a9a2b16aaca593dd510bc8554692d06bb419f5a99ed5c088c89eac27","score":44.12,"score_display":"44.1","source":{"id":"epoch-gso","name":"Epoch AI mirror · GSO","url":"https://epoch.ai/benchmarks/gso"},"source_authority_tier":"B","split_or_window":"official-set-opt-at-1","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_1c905f9be1ce4940b60cc62b","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"hle":{"benchmark_release_id":"release_8817af9d9a0235bce0826e22","benchmark_version":"HLE finalized 2,500 · Scale protocol 2025-04-03","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":192,"at":"2026-04-22T20:13:01Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"90a40758696fab9bc76127010b7823f84f1eae1813deb34faf636dc27c21ec57","measurement_key":"08ed2ba4e9c00fd2eb3e21a53a8376aac1a3be80c7976f24d9c7dbe5b26ff96f","metric":"accuracy","protocol_fingerprint":"57d4bb2eedd67eb8503193db96d28385e418a03d30a94a5add56f87c51741006","run_fingerprint":"d1226d0f1b3e2ae00aea32316670e098c1ebd1922dde8ffa791222c222a2b3bc","score":36.2,"score_display":"36.20","source":{"id":"scale-hle","name":"Scale AI Labs · Humanity's Last Exam Full","url":"https://labs.scale.com/leaderboard/humanitys_last_exam"},"source_authority_tier":"A+","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_706026ac74b842322735028b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2af77b2d33cf275249d6161ab0a6acabbed4f4ba677063e38dd780f43163e678","measurement_key":"3722dc594dd38213579769a329f63ce9b9743e1ccf13debd4cec759ac483a1db","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"2293a9b14524185d1921c9b46c48427c811977172257ecd0713dc45957db77a4","score":76.52935714285714,"score_display":"76.53","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_509db2bd77140fb589d8a000","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3c89f2a194433ef144d9badd5eebf607f36ef91f0a3435da21279d531a7c0f59","measurement_key":"77cd95c91c33410f7604903944de7ee85f226b66ca98a630685ada389b8a7c16","metric":"pass_at_1","protocol_fingerprint":"1ae76f45f3b5c3c61d867c81bebc9e2bb44abe31201237acc81dca0a65339a25","run_fingerprint":"d7ba21cdfdd82ca40b146def834766d6be069feb7177f1546298c99c1b78b803","score":85.073,"score_display":"85.1","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":206,"at":"2026-04-08T17:02:16Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"0c08ba50a045d3a1b605931b617f8ed4dd9eb409024e551ada6d778c1de7bca9","measurement_key":"f5c648e14baee80a1d70b23257bbe8272bba31331430ad4fb3dfba4fd3a3bbee","metric":"pass_rate","protocol_fingerprint":"c1e3aa1c2cb546884a5e08421510474f7a9e2453251eacfa69e20ed4f652d97b","run_fingerprint":"0db679ab659f1d4a609a10870c870437d36de7963fe77a2bd857de12a6c5c001","score":79.1,"score_display":"79.1","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":80,"at":"2026-08-12T11:43:31.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"91f410454a54bde409181114ff1ee0e5e5af393070d6631d8d40ac4405ef1df4","measurement_key":"63764fe394f04faf2295f68cbdcb643b6da9b56b6cabea6abb2da5418a608611","metric":"mean_score","protocol_fingerprint":"10132dca49c37c2b0b2fa9a13ab931265d36626de6efa155ea0e727836011035","run_fingerprint":"95cc7aee48bb869eced7f381dfb84a3ceef55d05b3fe1e80a40776302e5b3cc5","score":31.11111111111111,"score_display":"31.1","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_1c905f9be1ce4940b60cc62b","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2dc834162c5935edba463f2224ee000463744cfdd3c6472f633acb97708e17ce","measurement_key":"ceb46879829eec523a23e58ad94e628b46e98cf6fdc13990ddb1007f64f49c9e","metric":"accuracy","protocol_fingerprint":"68edbe85ff5ef67d9841aa9ddc87ad34f8bf362405194609df10299abe8521c1","run_fingerprint":"21c46aa232f825c2649b841669ab3b316a39066c0245d1758e57e7c05259fe95","score":89.871,"score_display":"89.9","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d4ad3c12a6259df427ba248724c058bd1efcd1766b8aacd0d81d1e4e75c39c68","measurement_key":"2e696778455ee59aa156adfe02f4ff21047d201b0a4d9ce8025b2ebfae2bc1ac","metric":"accuracy","protocol_fingerprint":"b4cef566aa48377ab1b8d58b351f9c4d8b19afbcb7540742ff46243b6eada7f4","run_fingerprint":"4bc2e129f74d42aac76cd883ad778dc497617b80e6f378b6a2e657d3f259dc35","score":85.549,"score_display":"85.5","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"osworld-2":{"benchmark_release_id":"release_15c5525fe39f33bc181dfb69","benchmark_version":"OSWorld 2.0 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:06Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cb71ec6d34381acf2255f48bc9ff2340d1b7a25099a10e700e34e37e77495544","measurement_key":"1dd220d7ca9e5b9eb9cce5a111865081dfd06fac468913f60809244c58f9872d","metric":"binary_accuracy","protocol_fingerprint":"8324b7d07a58972148ce8c7a94654e6da9a57c9a8f154331c3e283d10e6c2175","run_fingerprint":"9659a22d5f4c7011e9734d8992c0e3ffe5f4360a7bd307dfff8ed8139cbdb390","score":18.2,"score_display":"18.2","source":{"id":"epoch-osworld-2","name":"Epoch AI mirror · OSWorld 2.0","url":"https://epoch.ai/benchmarks/osworld-2"},"source_authority_tier":"B","split_or_window":"binary-accuracy-500-step-budget","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-06T22:19:46.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0b410752a4fc70910bbf9366b54de3db5aa100de62ceecb819a53927e5ad518b","measurement_key":"c2446391deb752618d3e31b26892b5499bd29ec90006e17ca39d6d99d364f094","metric":"mean_score","protocol_fingerprint":"783bb1d83e7d8cebef6c7c4b8de5e536862f4da779b369aefb639a940dfaab18","run_fingerprint":"229fb1e24a6c8898529f38d2eabf804fe8de7503e148fe55f30e21225daf1bcd","score":86.66666666666667,"score_display":"86.7","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d4895fab8f8dcd33a9ae263de9be9d8a4233dff4e7032675993bec61dd52f85b","measurement_key":"0ec420ebb9db1f3b727973d55d179b65a539fa478fd6c71add90749b13307d5b","metric":"fully_resolved_rate","protocol_fingerprint":"c0465d9da349e43c8a10e742788027dd69b0140de1f41c46b294b14f03d78e97","run_fingerprint":"a8d3f6f1c9c73b2a26abc0db61b33bfa69d2ad7efeb1f4ab7fadcf10d7a1a84e","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:47:54Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7c485148594a52cdda3cfcdbba12db3664ee5ed3529722fb18c157ffc21dd49e","measurement_key":"85e836342dca82661823fd0b9c6b2a3f1167bf081a5a12677e6988d368be9b7a","metric":"subproblem_accuracy","protocol_fingerprint":"5d8db5a2977ad2d5ef6e4b5cca401b12041207b8e5311c696ee76bdd3ca238d7","run_fingerprint":"80e6acb48785356be6402fd15d442999772dba5848d52741a0adf8635c1b378f","score":54.51388888888889,"score_display":"54.5","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a9c651756c08ba8330b8477875e5b834236d116b2df877de6ccaa7f9bb35bc8f","measurement_key":"5456d8a971f177acda851c884f2b05ec7d3bef23b4b355c91c15bbd84ba3777f","metric":"accuracy_avg_at_5","protocol_fingerprint":"6b0b62de4c90e22ffbf27aa09e82ef448940e448951663f30e2ebd7aa76798b7","run_fingerprint":"5f784cb9925a911e06cfc09dee368c2a2e7272a9982176217966a51fd3b3abb4","score":61.7,"score_display":"61.7","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_15740d2b88537909e84c3dc7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:27:26.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b43fd2425a7905a25019179af7fb445aee4acec37ad8798e796242c817130a6a","measurement_key":"269c868e558c8ec8ecb350ec020b3c50900837029c64c95f8f96fc91314b2951","metric":"accuracy","protocol_fingerprint":"f71750a6cf185b750ae565540c105f363a1e1c1a10d96ca8f6af6b68524e1165","run_fingerprint":"360a5deedd1ce1302fd5c20afe7337c2631289774a68e33839b3fe66d2c2dfd7","score":51.7,"score_display":"51.7","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_509db2bd77140fb589d8a000","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"skillsbench":{"benchmark_release_id":"release_093b45b8b752b3f08534f6ee","benchmark_version":"v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":138,"at":"2026-06-16","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ae76e7c3d72abd479e34a03252e1ace9637f404fd18702c3e774542b855620fb","measurement_key":"eaa6489b9837ee44164c7d40e4935d59d182cda51d8ef51c65854776e556acc3","metric":"pass_rate","protocol_fingerprint":"3b4651a644f962cc455e244c75c19a44ac9a846ec9096a32e403b17de579282a","run_fingerprint":"a637cb26046e8e5896dc3aad91f0828a337cc87c9525e2d17db01bd374f5b271","score":61.2,"score_display":"61.2","source":{"id":"skillsbench","name":"SkillsBench v1.1","url":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json"},"source_authority_tier":"A","split_or_window":"official-87-tasks-with-skills","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7135443fd9ef4d3d33bd3e91","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-28T01:30:56Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"13dd7abcc09c55eaaf075342e4d5ae44e8a312ca707122e997805c0b5ce948f1","measurement_key":"44d9ab464459eb1e95e12663fa7a0dcc916bb2d41dadf6c2c8b0ebba0c045ae7","metric":"resolved_rate","protocol_fingerprint":"202f22711959c37116e4d787c4aefd4536edda75ee58e33636241b10b9a6921e","run_fingerprint":"3d61a014a031a4aabf68d4fe68fa1b0646765f8148e8554c2c31bbf93ff69451","score":82.0,"score_display":"82.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":{"benchmark_release_id":"release_ed49ef6cb40ad079db5a0835","benchmark_version":"Anthropic 500-task evaluation","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":199,"at":"2026-04-16","last_confirmed_at":"2026-11-01T07:28:19Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"ca258432fb2356d75a16b041eeeeeb45dae0048aebd0922c46198d5ebb6a27c5","measurement_key":"337e6b31d20f2e96e41e28bc10083971a71a8b7ba3997f143a4463cd97373456","metric":"resolved_rate","protocol_fingerprint":"ed5a57a6d5f71c1a59d81da5bfcc604e7ded280f45dfc2a7429ba71f787e3277","reporting_origin":"provider","run_fingerprint":"2a11e18d4637c50c9d17b97b8f9546e1c129a2532aefce9b8faa277bb69b7bcf","score":87.6,"score_display":"87.6","source":{"id":"anthropic-opus-4-7-card","name":"Anthropic · Claude Opus 4.7 System Card","url":"https://www-cdn.anthropic.com/037f06850df7fbe871e206dad004c3db5fd50340/Claude%20Opus%204.7%20System%20Card.pdf"},"source_authority_tier":"B","split_or_window":"verified-500","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c93fdc26da7ffe52c4cf6b50","raw_label":"max","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-28T01:30:56Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"13dd7abcc09c55eaaf075342e4d5ae44e8a312ca707122e997805c0b5ce948f1","measurement_key":"44d9ab464459eb1e95e12663fa7a0dcc916bb2d41dadf6c2c8b0ebba0c045ae7","metric":"resolved_rate","protocol_fingerprint":"202f22711959c37116e4d787c4aefd4536edda75ee58e33636241b10b9a6921e","reporting_origin":"organizer","run_fingerprint":"3d61a014a031a4aabf68d4fe68fa1b0646765f8148e8554c2c31bbf93ff69451","score":82.0,"score_display":"82.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_332cbf0e979daa9e173de9f4","benchmark_version":"rolling-v2","comparison_lane":"supplemental-post-release-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4df263ff2ccd91dcde8f47b1aef9c32231f8c94af170d6d99bbc9176f3b84c80","measurement_key":"92a0928e5ac3bb487ec3d98995493f77d596d1384846ae612956d9a1bf53904d","metric":"resolved_rate","protocol_fingerprint":"56db8c9f4e6d312b6b00ad167c406430100335479f46b025cf03f8521d17936d","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-03-01/2026-05-15":{"benchmark_release_id":"release_72d764965dd7baf34f983249","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"41e07df6393b40cb2d9de4fb99e164dd440f0378b7730ef8debbaec01f499df8","measurement_key":"084c9b390381a4377d8ebd3ae14199853706000d707d56eaabcb7eb4e5656fc3","metric":"resolved_rate","protocol_fingerprint":"760b451c6ed4ecd9fc2438e6c69c6fb389c06c7d39100d7b8d503da895abe579","run_fingerprint":"af0265a00d59296fdcae917e9d3ae9ce9dc2112b3bc8cbfd4c6d43de4f40ad1f","score":53.090909090909086,"score_display":"53.09","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-03-01/2026-05-15","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_1c905f9be1ce4940b60cc62b","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"},"2026-05-01/2026-05-15":{"benchmark_release_id":"release_332cbf0e979daa9e173de9f4","benchmark_version":"rolling-v2","comparison_lane":"supplemental-post-release-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4df263ff2ccd91dcde8f47b1aef9c32231f8c94af170d6d99bbc9176f3b84c80","measurement_key":"92a0928e5ac3bb487ec3d98995493f77d596d1384846ae612956d9a1bf53904d","metric":"resolved_rate","protocol_fingerprint":"56db8c9f4e6d312b6b00ad167c406430100335479f46b025cf03f8521d17936d","run_fingerprint":"849ff548dfdb194ba82e9190319713ff80cf1c4cb070192eeb282eb8790e95eb","score":42.85714285714285,"score_display":"42.86","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-01/2026-05-15","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_1c905f9be1ce4940b60cc62b","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"849ff548dfdb194ba82e9190319713ff80cf1c4cb070192eeb282eb8790e95eb","score":42.85714285714285,"score_display":"42.86","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-01/2026-05-15","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_1c905f9be1ce4940b60cc62b","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":101,"at":"2026-07-23","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"014ef7c94f04f917320174ad17ff9530f50f0f4c3295ab45e37593860e5e3c06","measurement_key":"e5edd3245d941e76f8bf10b7d96db5df91819a11b07d7dcafeb78ef4184712f1","metric":"pass_1","protocol_fingerprint":"ce4e31865bc9890925719bee70ecfc72a33c3c49e73aeb5cd7164f1ed47c7997","run_fingerprint":"a6d4426ce88163ba9c8d81b87dfadef2578753ad280d745b0749ac7578b97155","score":40.20618556701031,"score_display":"40.2","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f5a73224e0a5689f745ff9d536515e9f79962276f7fb29d9ac71a00d99345af6","measurement_key":"3a887222347e9ea5f0d321da20a9add0193abbf174287c1c146bbce24a0f7169","metric":"accuracy","protocol_fingerprint":"b4457f1bd024f1e1eb514ac715e52c72b74052b9ad9095ea552d5f5ce51a718a","run_fingerprint":"ffe0947b2353363c651c656f3794605beb9ccc89db067188bc09ed3ec1c8a0ef","score":68.539,"score_display":"68.5","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_1c905f9be1ce4940b60cc62b","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8e829b7294e5d366c01ff2cf79d31a8a7baca058dbdb3a57c5d137d4b6838809","measurement_key":"16ef4171d4a0752e1843b432c8bdc12df5e77bd456215e1cdde7ede39fb268dc","metric":"mean_final_balance_usd","protocol_fingerprint":"7e827b07d7108076c5aaa4751be97125bb1c3766c6300a4d9650a45587bcded4","run_fingerprint":"2d10ea0959fb574cc661f181f9c7faa1f4d5b56981d8d22ab91172a85025041c","score":10936.763333333334,"score_display":"10936.76","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_5560a7522edc54c726d81374","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"13664c031a0dc2a1a7d56e091325dabc277ed2aa9859ccb646a543cff4722d6a","measurement_key":"931d3e335c9069711936e732d7d836399e835cab1cb6b09ace720cf2fc458954","metric":"score","protocol_fingerprint":"88d0f1020e7a012eedb4911b4551cd87edf118d18a31665492e1aeb5530e3926","run_fingerprint":"ccbe797fcc5a4830fff69681e64aed555d5b47a08f79596fd175b819adc37b30","score":71.003,"score_display":"71.0","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"27aa3525de1e923c87f9f37fef84fa79c43e88efcf5b840a4e887a1a029bd01e","measurement_key":"fb8b609e37c70ee2d7715e9d2f114e957ede818f919458324db9bc92711068f7","metric":"arena_score","protocol_fingerprint":"edef1e738db058717c7980cd576a620849ac7491b3457fcb4d990c8680a7947d","run_fingerprint":"799dcbb9fd7def8d7a5d79e4c28716dc073567799ec11261dcec6160a4fca7d1","score":1557.537773306169,"score_display":"1558","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":true,"normalized_effort":"high","profile_id":"profile_1c905f9be1ce4940b60cc62b","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ecba4cbfedfc3c475f0041acf4221feb096ddfe4b18836c373d8498702576d0f","measurement_key":"713f2eb52f1ec03eaf0101eef6a0494c28a3776914124ba4aa13c8f49e86a515","metric":"accuracy","protocol_fingerprint":"b8796d5baa9303df1dafed6e88dba11f1571c9db52d952b1f14c7739aa7ee416","run_fingerprint":"5226176b3ccf6c07be121bf86925074cc36781db027422fefd7de120e4728975","score":75.45,"score_display":"75.5","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d21e5b67f44d1fce22bb9f73","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"anthropic/claude-opus-4-7","model_name":"Claude Opus 4.7","parameter_count_active":null,"parameter_count_total":null,"provider":"Anthropic","selection_rank":29,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bbd6f496c02d0d5f8c1d031ad531350af0bf1d28228c9cca01108bd489e4efb5","measurement_key":"a68d275eb3e8446d48a0e58a95eb28b0186c0c2369e3d1683e7c1c09e4f78642","metric":"performance_rating","protocol_fingerprint":"8970e59b1071083f0b89273e65b29adb3f889938ffb6a4156d776dbbfcfbbafd","run_fingerprint":"8dd1fdb4e547098fe8445c99c588b8d540ebac746e198a37941b63283c5b5359","score":1667.4,"score_display":"1667.40","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:12Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5ee9253ff5f3fd0d850634faade9036fcb5107ba80e8b4295f0ca835c7402f05","measurement_key":"decc7d716699dc246d2dd882a0be1785788484c80eccde31c3acfb0035e6bfad","metric":"pass_at_1","protocol_fingerprint":"9f2153b6c7e2764fa0413e9d6b9456680fd759f2d7c9f834cad0639ef8eee045","run_fingerprint":"05c84099bd6aa60c3681b5bfc4ab8970335e649e8cd95156ffc85bdec16c107f","score":43.0,"score_display":"43.0","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9179a50784f1edd95e286993","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"appworld":{"benchmark_release_id":"release_3fa145932216c0afcdd9dae6","benchmark_version":"official-c1f56015cf7c","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":85,"at":"2026-08-08","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cb4146b5c08b1dccee907b1c3991f2eaf2dd48142fc33471381bc2f0a19717a4","measurement_key":"92145c3bc776083996d74a1703d8bae66b04cbd1a76aed89914747fc8250feee","metric":"task_goal_completion","protocol_fingerprint":"ef1dc06cb4f5d702032de3e7246e740e9fdbc27cb185f697fca3cb42f4d74a81","run_fingerprint":"45c45e459ccf4e11c60e8a2f4bdae7f5c11801921418694f5cfa13b1f3d5a78a","score":73.4,"score_display":"73.4","source":{"id":"appworld","name":"AppWorld official leaderboard","url":"https://raw.githubusercontent.com/StonyBrookNLP/appworld-leaderboard/c1f56015cf7c3441ff1933f5bfbec879798d7bbe/experiments/outputs/_leaderboard.json"},"source_authority_tier":"A+","split_or_window":"test-challenge-all","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ae9c2d1f81bc6fd257f16a98","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b8fff8a7304ff8afa12c298a1209f886a2974b684c0a5175346541d5fc95a843","measurement_key":"7d9b310dcc840db060db71f7a6f3fffa4900968e96747cae2bc4e83179a921e3","metric":"pass_at_2_accuracy","protocol_fingerprint":"833b5eb9853713ace12830a8bb02a8f907235c2ed7576989e479d4f57ffbb594","run_fingerprint":"939508c80b4ef2cd545843da674444e2b6df7ab076714189b206c3e3cbee2ba3","score":88.0,"score_display":"88.0","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"efb2ce103eb9f40c3a280c79b54edcb51c99668678df0ff56b89abdfdab596d4","measurement_key":"70826a16ca66b849641cd2df7127f60647e60eb7f41de875eb872ae814daa861","metric":"accuracy","protocol_fingerprint":"f1bd525dceb8715c61fcc62b3b1067943be8d659f1b593e5d8d640e1fb897110","run_fingerprint":"a53a3ab522f1aa955abcf6ab72e0599cf9660b953160f129dff83f867f2f976f","score":59.583333333333336,"score_display":"60","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f1db6d1043e37def76072cbe89975f2a3e0566407d02a76997a65c36d96f6ad8","measurement_key":"96a3d9a4c30be1f9582676c48a42ab15925a521b6512f2d3236a7011d46ffd0c","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"95f9431095803d39b2c4e322fe023feabd48ba7d47b2f85c373ea031e72ed72d","score":1453.0205808990422,"score_display":"1453","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_e57bf627bda67d6b38ba2302","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:53:45.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fdd460cc0589840dd956283272d34f122fb769c11722b3575fe5dd4671fd1b97","measurement_key":"00717fde13417c3201e8057dab375c419e00f136ab19a6ce33db0c786b7668a9","metric":"mean_score","protocol_fingerprint":"0228e713ccc4c27cdcbb407447229c9c7e60289d0cec66b446152ea13c9446ab","run_fingerprint":"2023ad3153a714ec07d521a4692c4b6ba28d278ffb0fd6f83cb1b28f040ca048","score":43.0,"score_display":"43.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2b6c30aab4c3e0e8310013bc6d8d32f05e8b30a205906319eff4a11e0d003528","measurement_key":"d1c8f07ea797e509146e6c91a18b72cb5e8198a8b744a8c6937385f6bfaf341b","metric":"accuracy","protocol_fingerprint":"662f76f2ffc17c94760e16b2d64e236163fc20f32c09920d6a6beb7bbf320099","run_fingerprint":"42f806c6784f5c54e532c66303eff8487fdcfd310ef0fd6bfe66915fa8dd8a00","score":20.571428571428598,"score_display":"20.6","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"cursorbench":{"benchmark_release_id":"release_9acebd5b002e9c3f18a30606","benchmark_version":"CursorBench 4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"76d31ab04704bc1c5b549aa5cbd945397c5f7111badbe801b9f1bdf86de95809","measurement_key":"c5bca8ef393fe2cbd1e4aa581757b8435c5eb4afc61104dea8c43a621de352ea","metric":"score","protocol_fingerprint":"620792494e9d2469a68dd2138d94612d534805260e1d9384cb95369af7f5ff37","run_fingerprint":"d6468189aae46b5373e9cbbfb7d04f726fff4b39a42cf0d7746582da3b6cf0cc","score":35.9,"score_display":"35.9","source":{"id":"epoch-cursorbench","name":"Epoch AI mirror · CursorBench","url":"https://epoch.ai/benchmarks/cursorbench"},"source_authority_tier":"B","split_or_window":"official-current-suite","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c2c4746f44933525a55f0f6be757ec250707ca5f933a1407f614ae238ed6ff99","measurement_key":"8b167f7d24424b8c2966f19e39ed216f8b2b8b6b5fb09fcf663eb3c6ed848e01","metric":"pass_at_1","protocol_fingerprint":"b4b94369640b3c39e71eabb0fdb8f097be0b63c1b2cab8ccc91fc7e330628e9d","run_fingerprint":"b05c3659f52b5854b8ae228d95f895551d8cb65c05c044570ea2f16fd45302fc","score":67.1875,"score_display":"67.2","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"88d7653dcb6b85ae26fbe0a2e553cf88200732560a379be55641656534a6a8cc","measurement_key":"080cd964df860608fe5c5684a9b261c3878f9753ca85cb2bdebf4fe7d568cb89","metric":"eci","protocol_fingerprint":"7b6e5dc0282d24e90e1b1c66c7da5d0e6ed42578e3cff7978a29c559dc387272","run_fingerprint":"ca5e1215d4435ee1b59010e6b3e35caf5295dbcec0dd8d79fa87b63971edd3ff","score":156.67,"score_display":"156.67","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a3d98e32adc7050a02790a04","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1ee67dec805121ebb889a512a9595ff5408439571b6d8f38089c6cb17bad497a","measurement_key":"74453af5f66fc0597c76dc896bb9311626d2424b8a08b8a6f27620e6a17e3dc4","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"97f8a238f9c83cde2459efea5678c908db5f00a8835b0048d51e297bd9df0c56","run_fingerprint":"02a4abb16f933efdc6499c28c3a1cccbd4040332848e285b68f2d577bdc5e34e","score":39.81,"score_display":"39.8","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":114,"at":"2026-07-09T14:18:35.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d1f5f2001b6880dac8a273b67dabe365b96e3af2bef509a626b26378fe50acde","measurement_key":"5f1c6fc895b34538390835f3a83bf2fff2206efdc6ef05e40c8566d7ad073778","metric":"mean_score","protocol_fingerprint":"4b8b8ad290dc029c8d200cb56c5ff20f2f2dad01315a27e7ec1afd440109a271","run_fingerprint":"3c7e725ea4ee8cf88a942f1305d3d52be3f05835498432f69529b3f59d905bc4","score":82.10526315789474,"score_display":"82.1","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":114,"at":"2026-07-09T14:18:35.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9e752b048490fefe9a253eb79be6f6aff6b44fd18656120d3da1821e1c670ff5","measurement_key":"e02bbc6d7205c9373d09e300be14a980a63af15471f0c9fb20912953d2643b84","metric":"mean_score","protocol_fingerprint":"940a93eb7d331a9efe6e8ebe8fca4d3617f421d867cc2d2dab2b94a82cf24e2f","run_fingerprint":"1ea1dd3b0da02a5865046bd630afc7e699f94daf966989c5395cc7266d8b9ec2","score":60.97560975609756,"score_display":"61.0","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"728674e089a5ff91ea75ddf5f649a6f656dd00a915d6437e9176cf15d0a72158","measurement_key":"b6bcfb7aa6bb55693345fee60083afcfc121d36d3e312bb6182707a971be2ca1","metric":"elo","protocol_fingerprint":"39898c15322729386fcb38382ced24f5855b59ce9f0c8805f4818bf0c69be5d5","run_fingerprint":"e0c5c50a92da7dab8943cac05900188d3812f6df566016e58774e1cbb88d1224","score":1468.24,"score_display":"1468","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9c9ea0eb34bbad0c29c6a30af3a804dc4d8c48ae2ec534dc3c41081c3d11c524","measurement_key":"7868b22ccb7168f6bc0b0be53979b45ef0fd1ed17285e76d070ce1eb8ed18c49","metric":"accuracy","protocol_fingerprint":"555753c3f1f3f2822c8ed4e22fb234fb2adaa2cff3e3ddfd7906dae4e00a9c16","run_fingerprint":"d60f56ee494004f974ecf74d555b1c2fe2d65f7a7e64ce17b94268b3d924e8fa","score":91.666,"score_display":"91.67","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-17T14:33:50Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d0647267215974e27dd5cd2fae2ae4bb447154a0db485ef96a15ceb2ffa2387a","measurement_key":"b8f16d9d0c607a7503710dc3b219823116f2dfd6a6254a6732b4eb419da02217","metric":"accuracy","protocol_fingerprint":"2f6f8d9ce3b94eeeaea3d2b381f04047a9cd2860aa84db51286b1dcd0834e383","run_fingerprint":"ad93cc86a26aee9067176fb1148207bff02db6b4d13617d096c7527bbd8b2a90","score":39.481001,"score_display":"39.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":47,"at":"2026-09-14T23:34:42Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"873165a97be933f9498b90a17a72d57f0380ccb1ad30b10f133c74871618bea8","measurement_key":"4466bb3298d818a323746c13f7450a097f8fb2e4465feecee1c7fbc80faf71b9","metric":"score","protocol_fingerprint":"a868d2da333e27cd8216cfea65643a42b41e5fc16a7076219dfdef899cacf073","run_fingerprint":"1fa719d755dba2df7ed9a72c558fb0fba28f1ff845c0b6a3cd378cb8d3b744aa","score":61.778,"score_display":"61.8","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e4c53da6fb89ac015d075b66560c4e74e8fb74383205831452aefa5e7aaf598d","measurement_key":"8cd6e1630fe701912614cf6012f72bc03b88ab06e9062b0426f376e273b7a7e2","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"0ff7e56bfc94de147e78de4016e2ab5b008ba000061b25699df458831e1135dd","score":73.55938095238095,"score_display":"73.56","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"844bf8007ba19e3d3c767f201ad56d40df24cdeb7e44bf0073106d0c38526fe9","measurement_key":"444ab53c724f1f9e703bbef4587235adf8a30353131665c8d94cc1b990102bc2","metric":"accuracy","protocol_fingerprint":"da56b1fdaa09eec0b14f50dbf76c5fade490cfa3db7dd410766d09eab63928a9","run_fingerprint":"d45ac48176245c45cb0eafe5ecac6f95b9b9b79f970712d765d873f4b02732d6","score":86.036,"score_display":"86.0","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:41Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"244ffcd1ccca476218c933ea49b6e2653e1022e5bb67c3bc2ed4fe3b9f0a5497","measurement_key":"161f6ceab4a2826cb67b7a805ba898947f2a7e9e0a0965e3012c95b4bbe68928","metric":"accuracy","protocol_fingerprint":"a741782697281ded2df15e8b50e7846d3426a3b9f6525d9429dedffad330c9ef","run_fingerprint":"ac3e2c671fef94e523b036154fbc8f891bcbdcb0090236f9c9bcb81c0fd847f1","score":85.029,"score_display":"85.0","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":114,"at":"2026-07-09T13:36:49.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"58b3c5c724390b300f1661758308331e83da4844b871a4058d316c8110140038","measurement_key":"c7e1d525b6a57a031dee0f1553b764456345bb9231d77d766173353b3462a237","metric":"mean_score","protocol_fingerprint":"0308d85f90369d2eee9ad2f5f23e877c1b2ad27b956eee9188603f10586fd690","run_fingerprint":"210e8309abd8f562a3f5772f7e33d8192f8861086126618bb1760cebdca056a5","score":98.33333333333333,"score_display":"98.3","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"907667e1b8148fe8542b4d28cb51f948e9f16203391917a1f24f7b498983fc3a","measurement_key":"1e1da88c14bd4476a22cd2261c211969df61ba63e92dab9f46322f66098f1d76","metric":"fully_resolved_rate","protocol_fingerprint":"ea2449a6fbe41b0fea8670f14e3e8982ba381fb1c692faeb9f9418d580610616","run_fingerprint":"6180c2b6dc7792303b9dfbf6d41fa31d30db8bab3c313ae48ee5b04261b8d8a8","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2b9b6814f4a40e73ae944590f3aacfeaa3f6fa6ab940c4646aaac8dac1ca6588","measurement_key":"5b9955141e636065ffc01470b62f31086e7070f76d60b944f0421bfb1816b163","metric":"subproblem_accuracy","protocol_fingerprint":"5ca8a356da506d1968447df78690233c30bcb75f017227ca34ddc2a4ae210539","run_fingerprint":"075482b31daf64c2fce092cc98bd700158c2fcdee64f3e5a4006cb06843c3f1b","score":53.587962962963,"score_display":"53.6","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f93627841d21fd1aceb3b814859107a685b4aad286cda30dde52b157a49b1c04","measurement_key":"6755175bbc0fdff6abdda3111f1dfb18e0b3d655187ecb9f92bbafaf333bcd5f","metric":"accuracy_avg_at_5","protocol_fingerprint":"1648b670dd9e109a8ca13ae1a8d575f070c45134efc8688a0b7f8d6e92abd9cf","run_fingerprint":"7e8d6432b16f5a6d5a9c3f8475a5a5023ce0d84d18a96a86ca9894ffbac3f717","score":46.8,"score_display":"46.8","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_e57bf627bda67d6b38ba2302","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":82,"at":"2026-08-10T23:44:20.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7c6c48b2b0a4f32db4a1b85888f68a6594aa30419d93167ee4ae89c843656167","measurement_key":"5e48ad20c28bd26de3f776dd38611dd13880e5f3ecbeb1847afe3d6d06f9def0","metric":"accuracy","protocol_fingerprint":"d410be56e6859f4e7081a0cc8ca85150541da72b651a27b3d98ed6bd89c2c16a","run_fingerprint":"b3f8bed4ee86a272d8d069989d198903f83596e34ce72814a4e210b6074b6ec8","score":41.0,"score_display":"41.0","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b63d2a3461f7a0f97bb28fcadeb3531b6277bacfb96be310fe86b26be556eb1d","measurement_key":"2a00374a44be1266ff9f5e5c2bb38d76125898aa5a334d2c3a3d084e113f51a4","metric":"fully_solved_rate","protocol_fingerprint":"731dc3293a276ff4a4e4f007852bef6fe69531edbcfe0b2af8192e3c94683e87","run_fingerprint":"6c5835b29d26372fdedfd5a64db440ffc467822974d1deac7a9e8d6f54e25c16","score":1.527,"score_display":"1.5","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"94c1ee6bcdeef6d06594447ac4c5e062f2af9583fbd865cdf6e8ee4158e67112","measurement_key":"8458ed4bfa1774e1152c66567e2963e0e55267197851f88ff0f4d5dd43cfda5c","metric":"resolved_rate","protocol_fingerprint":"edf0910f1683a1c6b396f030d187ef7ebab83f72bef7c33ac91d82991e8d01e9","run_fingerprint":"0c1c9d99bc233dba16e3d66b9f86ce29d6d72cf491e8b39340d47a5467533a16","score":93.0,"score_display":"93.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"94c1ee6bcdeef6d06594447ac4c5e062f2af9583fbd865cdf6e8ee4158e67112","measurement_key":"8458ed4bfa1774e1152c66567e2963e0e55267197851f88ff0f4d5dd43cfda5c","metric":"resolved_rate","protocol_fingerprint":"edf0910f1683a1c6b396f030d187ef7ebab83f72bef7c33ac91d82991e8d01e9","reporting_origin":"organizer","run_fingerprint":"0c1c9d99bc233dba16e3d66b9f86ce29d6d72cf491e8b39340d47a5467533a16","score":93.0,"score_display":"93.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"contamination-risk","conflict":null,"directly_comparable":true,"display_role":"contamination-warning","evidence_grade":"C","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5f3ea02a4a93099996523bccdf15507986235643d6f8618a5cf22be9d7d9e07e","measurement_key":"cb98fcd096c9a4064f22a52f91af5b885172b4ff8049016a9abc57417f992033","metric":"resolved_rate","protocol_fingerprint":"4bbed7a27d62a359466c297ea94c4763d7e66439d93473a4ab91adb70a3a02d3","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-05-15/2026-07-01":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"contamination-risk","conflict":null,"directly_comparable":true,"display_role":"contamination-warning","evidence_grade":"C","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5f3ea02a4a93099996523bccdf15507986235643d6f8618a5cf22be9d7d9e07e","measurement_key":"cb98fcd096c9a4064f22a52f91af5b885172b4ff8049016a9abc57417f992033","metric":"resolved_rate","protocol_fingerprint":"4bbed7a27d62a359466c297ea94c4763d7e66439d93473a4ab91adb70a3a02d3","run_fingerprint":"d6102f84c0897c12091cbef601a473d78c6f0d573d85b911dce232aea03f70d6","score":43.6036036036036,"score_display":"43.60","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_d00d7de512e3af291d4a5480","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"}}},"run_fingerprint":"d6102f84c0897c12091cbef601a473d78c6f0d573d85b911dce232aea03f70d6","score":43.6036036036036,"score_display":"43.60","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_d00d7de512e3af291d4a5480","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-09-17T14:33:50Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"73b8f8f3e6a692fd05cab2a16142a83b95fc28f1515d478e51c4aa54e3ce957f","measurement_key":"94ca9f6cc711de44a76aa1de5f0b990be25967a8654383e93b48df6083f8e822","metric":"pass_at_1","protocol_fingerprint":"2f0500d763c3ca201f3996008fa7227c097c74f25144824b446e5861f5e4bba1","run_fingerprint":"c35590786701e97bb0997ee8421949356d8e9adf38e44d4f5d0d7e30f6758cad","score":31.134021,"score_display":"31.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"005700f5a095c8e37e6a15c461aab437477957641bb2c200d9c41e9e14f7fc13","measurement_key":"078cf7b9d44f2404070f48debf0b5c1c15323a31b55d447878d16155a5b8848c","metric":"accuracy","protocol_fingerprint":"ee018f9481251503dbfb1f87ad00f3d1122406f5386764952c75e2f6856d2a21","run_fingerprint":"4239a196534b1d21b563bd83ba515761c32b865839cd3c3f86f3f591509362af","score":79.026,"score_display":"79.0","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-3":{"benchmark_release_id":"release_ceb36f25882d8cea2c9d084a","benchmark_version":"3.0 · b936386b-4afd-4ad7-aa7f-6b52bcab9853","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":80,"at":"2026-08-12T21:39:34.661007+00:00","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"81c952549a478f4ad4ffe2a7859898dac4e507f5f3357e10cce51cb3e3ed5ae2","measurement_key":"38d287a7307254b201bfd7a0a8c6302217d9df3b426a74dba04d4c0cd17c721f","metric":"accuracy","protocol_fingerprint":"7de4f97a12e9399bd298fc0584c86bda697ffff8673185d4fc32c4ed36b239d2","run_fingerprint":"dd0c64f78a79ef68fd9d3c1b6e28961c2be02ec9296d9f2456ed0633100e5b63","score":14.32,"score_display":"14.32","source":{"id":"terminal-bench-3","name":"Terminal-Bench 3.0","url":"https://ofhuhcpkvzjlejydnvyd.supabase.co/functions/v1/leaderboard-read"},"source_authority_tier":"A+","split_or_window":"official-74-task-leaderboard","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7aa49fbb948e5a56b146ac610392005b325a576228924e6c4ed90d883dbe3f11","measurement_key":"fb39e24590f165cd7eef104d42f9028b5bc391274392564d2c4d24838ba58c60","metric":"accuracy","protocol_fingerprint":"e8f29ec103b9c670b74c48456c127f4e5ef4c04756b3ccc4587ebb4a4128b22c","run_fingerprint":"78bc911f8c6775ffd2e5641579e71417f0a5bf41e474a2d0dd4d11d1ea99adac","score":11.616,"score_display":"11.6","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5a59647f4eaaab3ef9603702542aa95a9544f1f0275d7736c6321dd19a2dd8e8","measurement_key":"d5422546eec46c38602b7fd60e729c6f0453f3339eb5058b197887e99034ba6a","metric":"accuracy","protocol_fingerprint":"33bb3ae1c79060a290c4873469d7686da457b835b2ec1c52384e9e99af1b6c7d","run_fingerprint":"e588736461705de9daad4c8479d0c9d14f376246691e72844af054b2ae0408a2","score":0.0,"score_display":"0.0","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"34b0d9de58384d09f47f0c25b7d005c926c65952bb4818bb08950f7ba561c4ba","measurement_key":"8e519e4de9a6f821f39d79ba3a62f00652aa8219072abd74c49db3d9b499be2e","metric":"mean_final_balance_usd","protocol_fingerprint":"93ba9825f0574e5d080f2afb2c579a469251701b6b0e8ec17f61ee00ebb8a257","run_fingerprint":"4fb9eff4daf42ceef2c9b3b08a07bef60a6f8f9dca0fc8a730463906d93c0678","score":4094.7120000000004,"score_display":"4094.71","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e08847800071627e0e69db55","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"df872bb9130fe83a6194d3ef3c34a39cc7fef31ae923baa171391f3a4fd4790b","measurement_key":"d3ed4565a99ee0f7266932c25f7c3be5dbc4325f3c53b93040a8ad1c74934f0a","metric":"score","protocol_fingerprint":"e448637b07ebd58d1217a41467338dd4a7fff6f7b76f4b2169262ecaa088471d","run_fingerprint":"0b743b31febea04ab2097da57e1be0564962eafacaedff20957cc589ea4d9511","score":77.055,"score_display":"77.1","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_1b694cc32a697b0749e4e7f5","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5749f8199dd24eec699c6b80841556f9dc7db51a2934953e41b9a71db753d7f7","measurement_key":"1c9da7abd90ba5a546524891f7ef8d9c6815e2ec0b8eaf2a4fb21a78c2b57a91","metric":"arena_score","protocol_fingerprint":"8d5a80386a650bc2342c19dfcc983bf76f89db6c49e9bbfe3c5e6c497e75057d","run_fingerprint":"3b2645cc254f993053bf45d2aff01248963c2cdb9e30f8a048157f6f9a5f5a47","score":1518.9116265563573,"score_display":"1519","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_e57bf627bda67d6b38ba2302","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"52698e31d797c183a2dc7234c3ea1aa85b178bc0cfca676a4edc509c86574b73","measurement_key":"0bf872ee5601fa11e7c86c659fc0b6bbbc6a695b3b861a222d73c3463cb6f3dd","metric":"accuracy","protocol_fingerprint":"4c42f574a3937ca56a96171015b4b7db3075113a478e4f98ae2cbe31f2e26dbf","run_fingerprint":"53ce27ba152883d7fdf314f0b1e8274b4cf1d38bef604798157102b81eedddfe","score":60.86,"score_display":"60.9","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_0bc8d2a65f5e960dc81d9df3","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0df931576d178f7ce64ee627447b54c544b2d06922d0a86466624e5dff9ca947","measurement_key":"43d2ce68f3168aab2ea3572244d274d9e4fff43e3055f82914f31d98b7d0f4ba","metric":"token_efficiency_weighted_score","protocol_fingerprint":"ef82937aadfe5361b9faaf7035d33a37fe12630e408a5bed2de566f54bc60bcd","run_fingerprint":"d6062913e3fa4adf1a7e4b9bd59d1b1196ee9bb7e35cd42d396b88ef855a0d78","score":5.1579522727272735,"score_display":"5.2","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_e57bf627bda67d6b38ba2302","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"openai/gpt-5-6-luna","model_name":"GPT 5.6 Luna","parameter_count_active":null,"parameter_count_total":null,"provider":"OpenAI","selection_rank":30,"weights_status":"closed"},{"cells":{"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b10788223355f6a259a99b751e8f7db5cf703f36f3b713da73588e4901b7dd5e","measurement_key":"2148ada03c72d344aa75a1b75081a8ab7f482a24420290a2354d1d5779aad018","metric":"pass_at_2_accuracy","protocol_fingerprint":"254d25a57b3cc806c85d610086ba76a6ff094450b15629846f2053fd880cae07","run_fingerprint":"6cfaf4e7321da28395fdb28059d079239c207fc1e33328148f7ca9a61e653b7e","score":90.5,"score_display":"90.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_95ba440b37e9b02e11c009b3","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"42c03e91a948256e3da8779b8d3357d104ba43a9e1e8fe47fd846c36f3468546","measurement_key":"f7def11eeca1c502e57c44a86e5569cd24398bfbd1057fffdc4c80aa88b2a7f3","metric":"accuracy","protocol_fingerprint":"2f85e349795acf0d68e5ae22a7718ee829611fcb56986f06c43659bda088f931","run_fingerprint":"913d8e0f7f9bb89c0304dda4ee6c8d412e82bd6f62f36aecc12fc1562f32cdcf","score":54.16,"score_display":"54","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_2fa48c668af270933840111e","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":17,"at":"2026-10-14T09:56:34.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8aa97771b96d041a81a42bc87778ffe706e841379d2e5d33450a0cfe15804641","measurement_key":"70b91d76e4a8525fbe9ab52a2a634ffd1ad0bc4964ca6ecde32941fce7e0356f","metric":"mean_score","protocol_fingerprint":"71a59035921fddc10f2ca3cbb3a31faec8e62b04c8211cdc0f33be58d88ef8b7","run_fingerprint":"cbf43f1784c146f7b01250d6340fcfc5bd880891fb11333288f8a64f17bbf535","score":60.0,"score_display":"60.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_95ba440b37e9b02e11c009b3","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e7905afaf58de13970feb48d947ee2ff21911ea2a73c9174d98557b0ce77f6e2","measurement_key":"a00bc396eccf6d445cd47b1029254b94d298b6f5b1f3af84238c94ae5a920d25","metric":"eci","protocol_fingerprint":"10c454214b47e4038d955a2827067dedc2b2e6acf443358d9b2527f62ccaeecd","run_fingerprint":"d075cb933af429295c2a387f2a509e23c57daa1c5e900487a0c932fbc9e0e7cb","score":156.54,"score_display":"156.54","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fd182e68dd93da34ca6196d3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":141,"at":"2026-06-13T02:37:55.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7e8bcd2e04110e2bd9d0ed791519476e181730d2c68e9f8b0adbf09566a7c914","measurement_key":"3f33295f170ec395183952f9aab8b8f1ee440235bdf1361f58e822524b5431d7","metric":"mean_score","protocol_fingerprint":"8c74b08a97c0383941cf14c84ca5818f0c07fa819359022155073dcd71799c6c","run_fingerprint":"975675bf9249a52966cb429e8bb9448132001054c1c7ebc86abc723f2ef54994","score":74.0,"score_display":"74.0","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_95ba440b37e9b02e11c009b3","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":141,"at":"2026-06-13T02:37:55.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6b59027c5c5c8e0ce637cf8479fa03f9a96fbc090383a8826ebdfb7b5368f5e8","measurement_key":"615034960e521b13945a18585998bcad2591270bdf28650cff29dc797e45509f","metric":"mean_score","protocol_fingerprint":"97480455bd56f5d849116086cfed4deff8497a6a66c499469ade8dfd31e3d42a","run_fingerprint":"a37a83985293568bd92847df77570526b689a68fcfc72742c147aa03edf7937c","score":46.0,"score_display":"46.0","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_95ba440b37e9b02e11c009b3","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a9533bb9329263775a7ef5d5a8fa24722872aa189a4d18a92c4eb58f795c7283","measurement_key":"2496c7589411f81104b7aaeb267e97b7b703d6ad633e3c4c22477c39004a2f8f","metric":"accuracy_avg_at_5","protocol_fingerprint":"641e8efe24c5d7264e335e4f1b1372035aaed643f9a70ef1a1b65a599e3f5883","run_fingerprint":"ceb1fd7f3a64074c3d4f7d31bacbc8cfacfb8a41c5fdf4cfcf02dea6a65a6bcc","score":57.4,"score_display":"57.4","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f84193b5a06372776da088aa","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"openai/gpt-5-2-pro","model_name":"GPT 5.2 Pro","parameter_count_active":null,"parameter_count_total":null,"provider":"OpenAI","selection_rank":31,"weights_status":"closed"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"225a9d70f62f0df59bfcf42bfb25c1a8a1c01d0c214391d46d11f253d3ef6031","measurement_key":"b9a34860c94d995072daf3688d4aa5ff43bbcd7fcbe738f6872d130c20a035b9","metric":"index_score","protocol_fingerprint":"6f28b4845c47581aee73763fa418d85c5501ed8805b5335b093e3250ed66ff9f","run_fingerprint":"f0b30eb46b8c66fca5e07d007475ac7e96d245d4af9f511c681e615ad6798a27","score":33.554563,"score_display":"33.6","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fb817aa80071f23551b9a00e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:00:11.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"30cfec14fb0bd8b1e05c5fa8501e8b67d98e3d37ed9a55d080ed9e7c7a62e119","measurement_key":"494d73b57c2206f3b21c35d598afaa89ac4ce91a63b326beebf02da5bb911548","metric":"mean_score","protocol_fingerprint":"310d7c1fe372ef72f8287ff102420bf0ac6d43b3c2ea58b8af66fa51b5189ec4","run_fingerprint":"8b8c4d6cb97e8f99d82e0f45bcdd147d98a2ae2cb85893938db967fcaecf6590","score":37.0,"score_display":"37.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_164cbc78e507602d5ae2f029","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:15Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dcb72eecd8e01e6fd08dacac77b2308911d4e6bd0ddd75adc9a777cfb795a54f","measurement_key":"7f59ad0a60d2d7363ab4534c2ea5732528f9afaf6ee6f637f1761b225b118b97","metric":"accuracy","protocol_fingerprint":"a0ebb77a59f59ccaa16ca5ae119f6bd278c6d21b5a4d079aef7548607a6fa80f","run_fingerprint":"2619688410dbd05b702bac36abfc595c3479060fbf5bd3287c4effb79a174282","score":17.714285714285698,"score_display":"17.7","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f1de9baf1c06fe65d3662dc1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e2c5f180f368acc7f82dec05f09c3ead3fed24cfd46e0aa893b6603c43de7a32","measurement_key":"f9741b556894369656825bed559b5afc07a74491611c96c1a1befa3c1b3873c0","metric":"eci","protocol_fingerprint":"ac68c2a4f63454d624b58a86d09e59ffb5e262ee2a590b2d1f2a57974509741e","run_fingerprint":"8703b4a4616e7f9a3f84181b6ade51763048412007bde6444fd9516c6ff754e9","score":156.24,"score_display":"156.24","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_164cbc78e507602d5ae2f029","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T18:04:58.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0c3fdc568eb4eef520105eaa577882e21c26b7056dbd9167e61fe0939b729d7c","measurement_key":"3be8b7a88c617a16f0c0ff602d9cf8d62c3571297311e5075dc8540b1c4484ee","metric":"mean_score","protocol_fingerprint":"15eb55a29c8b986596dfb10383777044168822a0790707a85eea498f76ca2d71","run_fingerprint":"4cd3cf47b84dfeeff0e6f4623b7a7f791081583e25cb7c4a247ba44387085757","score":65.6140350877193,"score_display":"65.6","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_164cbc78e507602d5ae2f029","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T18:04:58.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9fdd9a529c79db11e34fbf24126a8ba8b8032e05846620ed5794991ba804aa3c","measurement_key":"cd2cd46d4a8db5978f56c572d020cdf2ff784f7a0c03d02ea855df0855feabfc","metric":"mean_score","protocol_fingerprint":"3929c6c9d56ad502dc10a72e084c4ff9e06c385d940b2b5bfe9df5f695a338e0","run_fingerprint":"af3ae58a58e2a08c0cc18fd617b3295f68192f73b153245002d402cc0f8f016e","score":34.146341463414636,"score_display":"34.1","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_164cbc78e507602d5ae2f029","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e8718935978739c9220123453bd7ed5acfb516f93bad23fc56e7dc7623fabdb5","measurement_key":"0fab4edb3d7dc03e04a2dba2810ecbf47cf5009d91ca6812079c378aadb1f1c5","metric":"elo","protocol_fingerprint":"d55f72ce119c2dc7e07391184d28c792e9618eb970e0b9d0e23ec89ac8e39ace","run_fingerprint":"0034436775a9c287cd3d170175ddca51931ecf6324beb0f4342142ad681670cc","score":1673.9,"score_display":"1674","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fb817aa80071f23551b9a00e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_f83cfc2a9e19b8d654d7b58e","benchmark_version":"GPQA Diamond (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":44,"at":"2026-09-17T14:33:50Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"914fde793f0d3c6e125a6a3fd4edb44534f7d8a8ea06b63f1f34bb748c2687ac","measurement_key":"6ebc8f6cb78c59caedaa1e7a51d393d55ab84fadbd43deb91b70865263399f51","metric":"accuracy","protocol_fingerprint":"bb6eddc715728ff54e0ab07a9085d24798298d07221648218b40613d1993e431","run_fingerprint":"9c713899881c03f9cbe097a0aa8f3386c8dfab8a4f5c4f48b4597bde519f463d","score":92.828283,"score_display":"92.8","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"diamond-198-zero-shot-5-repeats","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fb817aa80071f23551b9a00e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":44,"at":"2026-09-17T14:33:50Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e565a4f8ff08338be3bfad603f79baa2c42549e8b2a5b1fe0da7288449e6afe7","measurement_key":"0114b347e30f13de750be1c126403ca8df1592e98e2331fd8a58b73a37d4a86e","metric":"accuracy","protocol_fingerprint":"668a953aff1136f3db12265cd018cc039a645e3612b87ed0bee2099776aca051","run_fingerprint":"0e5e73134c779a80096c16d8581eadc76f25ca474ab4c4056a26285105ed68a2","score":43.095459,"score_display":"43.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fb817aa80071f23551b9a00e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T16:48:52.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"30ce4f06f00bf84e2b2ad39e1076aeae08dd56f53724756637b98d50ff61abe0","measurement_key":"7b27223bc4de300b3f3802601fa56534cbbeaffe1296198c153a6270c47bb007","metric":"mean_score","protocol_fingerprint":"70d000462fad855cc44a1c07f1350b4a6d456ec0d4b9dda896cea5d6d2c369e5","run_fingerprint":"bd1044e5688049de45b40ef0746674ce7dda87c19927169c8005704234861216","score":47.77777777777778,"score_display":"47.8","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_164cbc78e507602d5ae2f029","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":44,"at":"2026-09-17T14:33:50Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"890e4aea4fcc48a7396a21a9e416781054ae6df25628f6ddbd8f554d783a793c","measurement_key":"1ff0535cabf10c49352bd3c6212f26cf44ad5196cad6b9ba0060bf504548dea8","metric":"accuracy","protocol_fingerprint":"23b3f8c4e2a454fadaa2d7f0dcc88335ddb5da53419649f9230e9ad5dcfbc92f","run_fingerprint":"8f4bc72538def87515495b8a905a428c460dd26a705e023bedb92970e18f0fe5","score":82.774566,"score_display":"82.8","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fb817aa80071f23551b9a00e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T18:04:58.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1367c717928a0a5693d4ba2784e4a4fe895117713568e67d5f24e7eab251bd4a","measurement_key":"07c5351e68cabc6bc29728aa9b628ae24046a8815643ba43b2aed979191de461","metric":"mean_score","protocol_fingerprint":"540abe7eb1643f4b49284343fed302469c7b111c03a249b3fb97f0619b2a8dc1","run_fingerprint":"602f2e8909bb0aa4757a6fda32495dfee6fb73eb5509d436b08873a4f545f2cd","score":100.0,"score_display":"100.0","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_164cbc78e507602d5ae2f029","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:15Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ef77e647191d3cd29a61654e8736cb39fd84d256355ced0b4f50900fd3f0f05c","measurement_key":"74ebe1ea9349093043fd370e1078e270d52ecd0a4e86a816fab838fe1601062f","metric":"subproblem_accuracy","protocol_fingerprint":"9d299d21e0ff661f498a2b851f71bc27ba9719c7c26e255b52bfa2384e3ee0cf","run_fingerprint":"bbf96a30d0b88fcf2041215890de357504d843e5927c9927374c73667a7d01d7","score":52.0833333333333,"score_display":"52.1","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f1de9baf1c06fe65d3662dc1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T18:04:58.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8716b12b0710a7dc2e737d9142dbf3de6efafd64879184123405f483599b913e","measurement_key":"dda36448d712b9b244f8988dfa2fd81c5b6e34364c3a9a808eaf9ddabfb53318","metric":"accuracy","protocol_fingerprint":"7cad23dc5e0345efa51a17c61f2b76c4524b68b9bf3f9a669774a1e64a094e38","run_fingerprint":"920c44e510ba43543ab94756a5a1f079cacd010b48cf179d1b913eca8e63f375","score":47.3,"score_display":"47.3","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_164cbc78e507602d5ae2f029","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":44,"at":"2026-09-17T14:33:50Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b871d0749609b783a8e2c0a176b5427dc6c4227118fca864ff54de68db0cbe22","measurement_key":"e5c4a1dc7ea458116a69bce16518fc1d2d4ef03c6e9c8742ab79fbd23eb56b86","metric":"pass_at_1","protocol_fingerprint":"59a0ac53ab5cac2d61eb20995da6e7bb12016bac50f745ad6ed1953dc2f26fde","run_fingerprint":"37d9c31a0abc4b782ce9ea8813476d839ac1843679594b37ef242bef4121f4b4","score":47.835052,"score_display":"47.8","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fb817aa80071f23551b9a00e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_c53c830678318dc1763793c8","benchmark_version":"Terminal-Bench 2.1 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:17Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0780d25cbef678a3dcfcc3ecd811be0f7b011ee12ea0b40859f535fdb0b3ac53","measurement_key":"faa3dd988cc50b5a50945781a7d2d01f06292d6f5ec4ba27c320ac96b055f8fd","metric":"pass_at_1","protocol_fingerprint":"8200447c61e9b67007e665430d3d50d523b15381f508bb3f41ec0bad61d2618b","run_fingerprint":"85967bf66bb7e64c428302a2886f5244573eeeae20ac13292c26a42ea67f4f5a","score":88.764045,"score_display":"88.8","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"terminus-2-89-tasks","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fb817aa80071f23551b9a00e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_b7d9ab744ffac0cb856e114d","benchmark_version":"Terminal-Bench 4.0 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:17Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"461a800c09c7a565aaff205a884b5d0803bb2b21d179bdfca32adeff783b8bf1","measurement_key":"b7a434eb791f8d1f2ed767f041dc7644e90a671b3c4391703fc40a033786b609","metric":"pass_at_1","protocol_fingerprint":"89b9cf67f38aaa76247bbee6f2b9e496dffef731190faaa872210e621ae2e005","run_fingerprint":"5d617ed784f6edd62449b96293014c3102cefda35bb313c1ca6c018b4d6aa1d7","score":38.888889,"score_display":"38.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"mini-swe-agent-66-tasks-500-steps","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fb817aa80071f23551b9a00e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bfe73ac9e75a256340ff0c8db1b9bff739e5f541e30ad403c4bb167f7877df8a","measurement_key":"98cc74557c689226a54d5d8a3553c19d3e10d708188323570a4939bec92e9995","metric":"arena_score","protocol_fingerprint":"929f644a025e713d598d602ffc1b9d61ee52a5d0c321036bed7caee267ec1c08","run_fingerprint":"c81654f696999284ab5382ddd172853b313fab5882cf3551cc0639e6be053fd7","score":1675.9355584770149,"score_display":"1676","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_30a83a958902d8055b81e819","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"alibaba/qwen3-8-max-0902","model_name":"Qwen 3.8 Max (0902)","parameter_count_active":null,"parameter_count_total":null,"provider":"Alibaba","selection_rank":32,"weights_status":"unknown"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"591933a4eb7e109ae720c3cb943cc72fe06c8362c746ad3b83c450cabe8fef3f","measurement_key":"74d8cd2a1ebeb753f1ed32d62d12c81cb18fc07d989ff2426da96ad35522f558","metric":"index_score","protocol_fingerprint":"d7566361e184617ecaa4c04a7643627fd68b08138e6c6ac9ff36b0984d316d5e","run_fingerprint":"2bda056ebecbb69f32258058aad6f74e2754dc1ffec9abea8878765a06052c2c","score":31.653382,"score_display":"31.7","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5c29266c84f144d9cdfafc9f4ad40d400de72a1872b1bd4412aa6b98e00a046c","measurement_key":"5a924f321109eb83f522896fa11b6945babcba41dd46682582504176ba33c35e","metric":"performance_rating","protocol_fingerprint":"daa02bfb234208aad8d174c45bd774f76c33f7031a76c9bcbe564a266bbe1a38","run_fingerprint":"1333c4df07e57cf1551407e7297e3fd1656b889138a1e3d321fdd15a8caee27e","score":1317.4,"score_display":"1317.40","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_7b670530e689719e8ea1db1f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"adc8c43cab1edab5240e75bed2bb554b90cdf99e6b4ec09db28d541da7550043","measurement_key":"2aaa00f0a80bd7cf0de087e85a48d506b1a980f00d54d6b59d6cf719a1ac8dc7","metric":"pass_at_1","protocol_fingerprint":"1be876096f3e5feefc445a69de9145dc897e11e1c7be0ca8ff733629b5b28915","run_fingerprint":"d828f11900a5d001a57e8d7e2bc3b0ea023479d2083b1a8edaee87918b10c5b3","score":56.60000000000001,"score_display":"56.6","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_628c201ab8499b38d223a8c1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ddb481236ad71f744b55eed285c0285bbebd28f97ccaecc3edfd8ffc700e1654","measurement_key":"92078583c1308ab8be2f88b0ab8ae9b048aee2b6fab3e2bb0d587e7e66b55503","metric":"ips_score","protocol_fingerprint":"a527c9953e6c80676206346d2808a609b0af34c21ebdcf4143dde7fc98008a2c","run_fingerprint":"38a6a72d4f9e0cd1f6d6b38c0fb75ab7e0e5b272d4df548409849629aaf2679c","score":0.009119361444542019,"score_display":"0.0091","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e3a2458690dd12ee9ece72d3ed27bd8fef456b914db26748cf4f5af7ab7dd0c7","measurement_key":"837696df29618e1edf26ea5e7d033ed42209e874e5cf92d7f6d94ac38d6e80d0","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"e4998e8309524c25c0004c046baa8273cf384d74ed0007f1efabae7c857803e9","score":1480.5693804560872,"score_display":"1481","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T21:22:18.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6b9daab7931a606a56ba1734ccb97d51b7b207674f3623faa571c2efc28adf9c","measurement_key":"cac7bbdb62d0420b527c4a9c992f0ae055d8573796e96f288db8b144a15f501c","metric":"mean_score","protocol_fingerprint":"4272568acc80114e6a26c9f1f042cc432b86e263370ada55e55018b2cad07dcb","run_fingerprint":"810d886a602ceca7b2b8a70d0c260f1a22eecd150fa4c3ae38c6c413f587dc60","score":37.0,"score_display":"37.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"af994143f85ba361285a16c3a8f5cb6fd6853fbc19b4787647b4590b3aefb373","measurement_key":"5ccef40fabf322cffec9f348e7898541a17068b91dd73ad611b4148eba85374f","metric":"accuracy","protocol_fingerprint":"398619199077233d6b9028afbc063cd29b8646598ef0c5d52f409695f4492988","run_fingerprint":"be50832f36573a7097c03565a6f235dad9a80b274bb99be3877b1e2c4226c56d","score":19.1428571428571,"score_display":"19.1","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"cursorbench":{"benchmark_release_id":"release_9acebd5b002e9c3f18a30606","benchmark_version":"CursorBench 4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:11Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"73d5e870964f7ba26f9e76904fb9e6049018d056cf80c341d247b4008b62171a","measurement_key":"4c50ac6f3625c550d55715f8d483c6d365455674c6f6d19a8023250b18a96417","metric":"score","protocol_fingerprint":"8eb1cb1268f25dafea962b50eb8093ad40a0bac8d9ca7d996701b49e0e99d0d5","run_fingerprint":"a8acd540bf973d558e97adc2d8c681fe7d565eed676dad2ae5d6007da4159b73","score":42.6,"score_display":"42.6","source":{"id":"epoch-cursorbench","name":"Epoch AI mirror · CursorBench","url":"https://epoch.ai/benchmarks/cursorbench"},"source_authority_tier":"B","split_or_window":"official-current-suite","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1ede9aebd761ccea03f90e5410016eb80c9c6caabda5bbd03d56bfccf473e609","measurement_key":"f94243341d37779d96f8ffbf6851ab74f2d326fd989498b7797ceb58b5f1fbeb","metric":"pass_at_1","protocol_fingerprint":"76a7e4fafabe3bbe3146b6c402e8d8e6542f2b5390eb800eeb16eb81377c59dd","run_fingerprint":"41f75462411b9de0ecb0ba1f07a859047626474a2948fe71336e06b9b58323a7","score":68.95787139689578,"score_display":"69.0","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"62ebc6866790e712a6ec7a9792ad18a76aabbb35c87855326b4be3c71d14f197","measurement_key":"12ca397dd31cc00f563bc323df2ef3b4ef1561c25c73456160b6180167e17db7","metric":"eci","protocol_fingerprint":"fec0e71e09e52e528f088c2f0d829a3dd273550d7b9f914f88bdf9e31ec32914","run_fingerprint":"f0ec68b0ff8db4b585bb5480555fc80301a6163c7c9a4dd931954015772bf556","score":156.17,"score_display":"156.17","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_35a37f6bd374e637bd675128","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:01Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e6d3508da7b4b1c8570279590da0dc8fd116a154b1ef14a57688d3b4433d903a","measurement_key":"0dc5ec848811396a96bf481f04cf95feb2308cf3123897415a90be2b89ee3dea","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"a98c3ab7e44c58a2e935e799cef17cb35518538038c6947533bbe5a02312f726","run_fingerprint":"cac1c8f52c2b5ec92ea2cda1953d216a82ab7bd6ca817134217790e7c573cea5","score":40.14,"score_display":"40.1","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":67,"at":"2026-08-25T14:20:20.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8087f469cabd2dae072eb7c0f00fd489b88b09c298b98d0cc5db2bf918af047d","measurement_key":"dd17dadcd4af167a6468869bcd930e348ab518e5a1cd58d5eb2efdf8be36bafd","metric":"mean_score","protocol_fingerprint":"baa8b449e7584a3a04da45802bc5a09fb052cc1712837ea86e91e067754922a0","run_fingerprint":"7764a9d85197e18373753df8f9b45b4420481162dd78b3dd0c3e093298e698ff","score":68.77192982456141,"score_display":"68.8","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":67,"at":"2026-08-25T14:20:20.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"efbee2653702d66c1f7d35345c87bd00bee592e8c4440b1f710bace3a181defb","measurement_key":"e69f34725f8105a1dd7c65c95b8ad578561bcaa821226f22deaa86cc35546513","metric":"mean_score","protocol_fingerprint":"7bb80b144278a2bde3d74797f51778f83a6e103dec6bf21308a03e696749ae13","run_fingerprint":"7cd3ae737ed59f10025e74c70dfe3bdc9bc1988e8b254d39a6d13a7c1188ca2b","score":29.268292682926827,"score_display":"29.3","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3311f2d27627581d8ba418eef391fbb09a8c36c716b34b066e1d6dc98edb9694","measurement_key":"98660136041f0ebe8c136fcae63fa03390fca65990ab0eaecef410423c8b6d2b","metric":"elo","protocol_fingerprint":"29d3145b34e4316d5ca415e192139ac1c8d29c637c6ff46799a03fb9557bdb01","run_fingerprint":"3ed9e895470f302314638072fae00b86d07aeccaf57842afbb045bfb21aa2636","score":1656.88,"score_display":"1657","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1e7d0c6260914d9bce1545ba9cd7c661b7875a71c920eb8ea574c19ec2c99b67","measurement_key":"bdb6988a9eb2f443feb836101114ae88b6b300837d5615d3c67d931a871d046b","metric":"accuracy","protocol_fingerprint":"8b2d4366d6de0d0b8d9a61ae129336054e62c571c9c028b715847b878e9f7f5e","run_fingerprint":"582853ea98d21d304a03873332326f1e240113ddecf27a9aff8a9159cd3511fa","score":88.132,"score_display":"88.13","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_fa9e908ac04b067eb00182d4","benchmark_version":"HLE official leaderboard","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":63,"at":"2026-08-29T23:52:43Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e5577495eb7297530e08f01c75b0646c9f274ac11cdb1b98ebba42219c92a481","measurement_key":"73132a74846275ec5d8ca8c58897d04999a6d012fde45245cdb21bfcc30f831e","metric":"accuracy","protocol_fingerprint":"85de386bb5b9e508e9153a921e304c475ad7ad4f383514d2db7e317cbe2264ed","run_fingerprint":"ba3d4704474cb1459dbd22916e347f992876ab96c9d117dc9bd8e5edb70dd2f8","score":62.5,"score_display":"62.5","source":{"id":"hle","name":"Humanity's Last Exam","url":"https://huggingface.co/api/datasets/cais/hle/leaderboard?limit=200"},"source_authority_tier":"A","split_or_window":"published-leaderboard","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1e27a40ca87a4086efefafd6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"C","evidence_rank":5,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"self-reported","verified_status":"self-reported"},"unit":"percent","verification_status":"self-reported"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"417e1cc4f5ddcf68d8f57fb975bde04e48448e47f770e3dd5de402326b9df033","measurement_key":"f7d143dd4b3219fe3e503646d61651f9bf6c64f8b0467e7db52fcb89aa1ed010","metric":"accuracy","protocol_fingerprint":"e9754924490d84f96a0dc72824bf9e67b6fe0ab7c8a718f9c17f26bffae726b9","run_fingerprint":"b320325eb1c51918cbc5b2c12b899f415e1c5c4dd622cc818235737cd9623a2a","score":42.261353,"score_display":"42.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"949d703253e07d1fe4a978a0738a64e79723c124bca450bfab9b0d5c77f422c4","measurement_key":"45ddfde43c5f35e6ec36ec97f1f55402b07bfcec026287551464a5b0a722fc1c","metric":"score","protocol_fingerprint":"2447bff548573484163c9372b0aac2b98d92e1c2e82d489b81a0258a1917f4a2","run_fingerprint":"980ba26d14ce4d945a1b2d419ea1dd1c4482a6749a3d3d31143d1bace113ccb3","score":68.444,"score_display":"68.4","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"03e2ccdd24aa45e6b66d3d94b14a7af0d3184695de38ed7669c44f1864513f47","measurement_key":"59bc1e7dc1e1f0125b70c57bcda8dbf0503943db01e48fa1e041f356b09a4bbd","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"124c903d3cc35c73c2c9c497aac27a0d0f90f63f4ce8f7ffb9f6ff7315f4a9fb","score":76.13780952380952,"score_display":"76.14","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_59194fc28b0dddffb241f8c7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"eec8df8475502a5e74ade0cb61fc4be5298d46568c47bc769366855d2077b8b8","measurement_key":"d50151e35a77d99e909070bc414c604f74f03fcd8571cecf48a7be12175bf428","metric":"pass_at_1","protocol_fingerprint":"a01d5af3a2f30cd0722c5fc146d53c6c04aae12d22e883ef67a79c3717e7123e","run_fingerprint":"2078ea9d05da867bd59b794f21b8c671b4e238422433b3702e05ffbf1f265c65","score":80.535,"score_display":"80.5","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":44,"at":"2026-09-17T14:59:54Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c8022d667e9fa2f50cc8f250db7c0f653e011bfb57b9b4be05a203f51c669008","measurement_key":"1ff4358b4df3d2a59d643cd2092ea85ce719720e36774f7e60a136c65183900a","metric":"pass_rate","protocol_fingerprint":"9345bc822ab03d67801e4b450cda2897241bd32ed2bf3fb620a22849a3094dd3","run_fingerprint":"fdeaddf7be1c4c7ce7ad5e2543408d78fd330d5ab126e5ca0f68c2ab0e4b0c50","score":84.2,"score_display":"84.2","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c742d73fd887bd38522e03c0","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b5f93034b53c3d6e6b91f357e22bf612f626fc093ec38c326c3b5063e3afd956","measurement_key":"32801e559fda91f15f9c273b23e64a1f1f20f171427f75e910b508ea0cedfb5e","metric":"accuracy","protocol_fingerprint":"508a7aaccefb4d82390e1a87a00f6816f68df82c84c42b41e7220e9a567c2dd7","run_fingerprint":"28e687892d7531ed132496181e5f6dca96bb44b750285171979ca6827adf8e5c","score":86.77,"score_display":"86.8","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":68,"at":"2026-08-24T19:44:18.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3f0122c99d2458a32998dda62917b857df3129338c3d941a86f467b66bf0d0ef","measurement_key":"8a21d69fb7eb37162e070bd8f57f6a5b9674847d52bb051ef416501dca916c61","metric":"mean_score","protocol_fingerprint":"4e8cb847c4372d821424c8e84d071e4d9eddfa79832e97f96e4beb381d508ce9","run_fingerprint":"33a8a38255bd04cb6ba24d67afcafec3947be9dfc40bbcf607b7c2a3c9e314ee","score":91.11111111111111,"score_display":"91.1","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b66db489774abd287059ad877e94c87fc2c8d68fad473b7d910babddb31f355f","measurement_key":"92b23f9aabfcc314226f9a4637c3a1d9614d7d74f739be8ebf0370c77dcf4409","metric":"fully_resolved_rate","protocol_fingerprint":"e162a0017a7d5c30b94f5cb3ee6bbc8451218852cf10d356b289c7f62137fbe3","run_fingerprint":"9912b750f29c0f766248e153309080c51a10e05f6ed167bdcf8ef27289eae92b","score":1.5,"score_display":"1.5","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c2dabc9866e165521cb71d99f10bcf017f0229515504a56ddb7c6728aa4854aa","measurement_key":"0b9601e1b402f18aa13eea45b91df902a727f697e8296563f8cda72461331f90","metric":"subproblem_accuracy","protocol_fingerprint":"89cd9987488d8fd48dfb9de446aa6009c6f3091d68659152bd782ad40846aacd","run_fingerprint":"7328e4104ce853178cbbd5ba877e138bd663cf8c29df46a156c3c23828a8ee95","score":59.0277777777778,"score_display":"59.0","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":64,"at":"2026-08-28T17:00:06.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bad4f506905b0fbe8f4b42ea1d85767021786c7579e953a4ac95cfdc9efd34b9","measurement_key":"c87d9a7830fc7bd324a388dbff687130ea18e543f6ea08b10e23c6302cf5aef2","metric":"accuracy","protocol_fingerprint":"be976fb14801559fcbcf0a3c3d24dd863d841e7563f53649aa5b2d9b1f5d7f06","run_fingerprint":"f2f47fb20f09672a09e70069e52699faf152c4e1ba36f0dca35294c793c1d88f","score":41.0,"score_display":"41.0","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5bb5a348dbff33d0e8e03798020fc396bee7524ef333db68b12e3a20394bbf2c","measurement_key":"509448d40bc067c7cd3ddc979ba8559df4c39194752e5b0b9cd2543d447376a9","metric":"fully_solved_rate","protocol_fingerprint":"7692577614d8ead3402d7a1ae7afd0bbc29fbbdf8509a2d8b9522dad9168191a","run_fingerprint":"a8f7c908cfef0c15928cbae00cda920a144c55b51e570b7b38eef32aa4a573c6","score":9.16,"score_display":"9.2","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-pro-v2":{"benchmark_release_id":"release_d9b58bd286ce316ccf0ed891","benchmark_version":"Scale SWE-Bench Pro V2 public leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":25,"at":"2026-10-07T01:44:58Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a304ab456f4d968c17bb1526f2e2764dcd5e431cc4c5fb13c98bd1cdb8034b8a","measurement_key":"71cf48a2db4d2fd0d8ee5111df077835812d118293e3ae6c7834ffabafc9ba40","metric":"resolved_rate","protocol_fingerprint":"6e99f9fb4ede3b28e31d85a6c0f09a2d704a25e82990bdf7ceafc3bacf01d312","run_fingerprint":"d835ed884ed7861a0774b1266f5cd5381aca366325cfdb43642082aef8b1d88f","score":95.6,"score_display":"95.6","source":{"id":"scale-swe-bench-pro-v2","name":"Scale AI Labs · SWE-bench Pro V2","url":"https://labs.scale.com/leaderboard/swe_bench_pro_public_v2"},"source_authority_tier":"A+","split_or_window":"public-v2-642","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c31f05ad91ca7e97f4da619d2bb1f4b23cd8e75a7b53aa2cc39a9e7a09bd5997","measurement_key":"33266fff11e8796b337e33c5d682a84684c725eac461581e0fc61da2a955b3e5","metric":"resolved_rate","protocol_fingerprint":"6af5bb58c3385d3d7246e24eafeda47bb66625ea07efdb3363e7e917270f2130","run_fingerprint":"e0f3054018a6db156a80dfae2630b60d7acb28f615cfb57d8c847a39a86e0dce","score":95.4,"score_display":"95.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c31f05ad91ca7e97f4da619d2bb1f4b23cd8e75a7b53aa2cc39a9e7a09bd5997","measurement_key":"33266fff11e8796b337e33c5d682a84684c725eac461581e0fc61da2a955b3e5","metric":"resolved_rate","protocol_fingerprint":"6af5bb58c3385d3d7246e24eafeda47bb66625ea07efdb3363e7e917270f2130","reporting_origin":"organizer","run_fingerprint":"e0f3054018a6db156a80dfae2630b60d7acb28f615cfb57d8c847a39a86e0dce","score":95.4,"score_display":"95.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6925f1aafca0596ee8d47a59130bed9b8a2f7ad57df6b613bf15dc06ad55bc33","measurement_key":"8e9995a794248574d842d887da1d5b8fd14b72328b077598b043432baea7126d","metric":"pass_at_1","protocol_fingerprint":"79804289c5074fc1a679d850742a50336124267abda7f3f0156dc998121ee294","run_fingerprint":"5ff878291820ec03902381d41fbab24da0b887194277fcf3e4e1a13f4b2b7402","score":50.309278,"score_display":"50.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fddf942d9f6830991dae346f0db9fb66f261a4cde7d52526650b2f5e77ee8421","measurement_key":"e6fb0b0713ef880b03fec77e72e6a71da593c9ec1579bde87f62e1f7cd3a679b","metric":"accuracy","protocol_fingerprint":"30e9b8b2223ee26132fabdefae1541d2cca015421958824bcb0a6c5680a032aa","run_fingerprint":"dddd8687bfa8467ad67febc373c29e816cc725107cb7fe3170bfdfb24f86bc0f","score":71.536,"score_display":"71.5","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-3":{"benchmark_release_id":"release_ceb36f25882d8cea2c9d084a","benchmark_version":"3.0 · b936386b-4afd-4ad7-aa7f-6b52bcab9853","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":74,"at":"2026-08-19T03:41:59.486409+00:00","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"937f41faeead6c07f404fe8c0532b34f770fce9974408fd6e8f5ea900c1ad89e","measurement_key":"fb0b272825b16361048f2b646e0a6c221ed8f74e5f610452ead005ce150a5c45","metric":"accuracy","protocol_fingerprint":"53ff18eba7ace83101286cb02f5020ab9cc5293ebd9dda6d00301c775e303b7d","run_fingerprint":"bbad5dac0df5b973c869634b5dfe9cc7bd9a7c39e5a03b4408ca0fea978a19ed","score":32.43,"score_display":"32.43","source":{"id":"terminal-bench-3","name":"Terminal-Bench 3.0","url":"https://ofhuhcpkvzjlejydnvyd.supabase.co/functions/v1/leaderboard-read"},"source_authority_tier":"A+","split_or_window":"official-74-task-leaderboard","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"17bbc4965095b6dc2b207d6d51780f647026ca0d217e9c0d566be1ca5b79e9dd","measurement_key":"a0aef849129afde7d1cd6c85ef2edd367edfea5a5e0736b4e98bbc0b46062f19","metric":"accuracy","protocol_fingerprint":"97de83d802da76ea6223c39ba8381a8716d109adc14386525e270ddf21733c9b","run_fingerprint":"5b368289ee82a1e9a670c6fc9a669e98010b8e6f49222fb4d1febef9b17231ff","score":38.889,"score_display":"38.9","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9bd78720050a688ab3f317250fa1296f3841fb7363f8098f090314a37316f088","measurement_key":"dba29fbcd7f082455c3d27ffdf80f5a333f196c2e42610b45626ec1374478595","metric":"accuracy","protocol_fingerprint":"7cdcabc4244581b79d8be123df4484760fec88ad3680add0dffc3d4e913b5e6d","run_fingerprint":"82fe1099b9358d53845ae53a6ec3d9d6f8c5f7c1275f3e11145a6089d85df308","score":5.714,"score_display":"5.7","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"35dbb601e6b7a87e1e3e9b925e0078e8c20d0b51e2eedfdb6150c9c8ed31f15b","measurement_key":"8644352dbf29cf6bc5ad41dcf68cb603b2cae1e104abe83c5c464074790c77c4","metric":"mean_final_balance_usd","protocol_fingerprint":"460f57bc4832717e13967632b0bcbe5ca1bb1a7e4fe87aca0ed24ae8a70042dd","run_fingerprint":"71bc0f0c84ad34051ce3451aab03aab759f6754eee83ab780d2647a7f58eda1d","score":8163.609999999998,"score_display":"8163.61","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c07ed0ced91381c8fb6c9cb5","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f55545695b1979763f97834059776e7cad7008613cde2338da9c65c3a4244d34","measurement_key":"4d2e3ab411ac62089ce2c7095586d9b1fe28e1761b69377f36a026d6a481b483","metric":"score","protocol_fingerprint":"b6051c8101d2b7cc889b1734d5a4e75ad0b8206a7288c8627e83ede943c651ad","run_fingerprint":"4dde267f9a802865a7e16a706711151cd5ba003671d42ab1085e8932820ceb47","score":78.125,"score_display":"78.1","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6d9ee69164e80f1b6f26fe899ceb18d4b992620067480c35952d3166f000344e","measurement_key":"6a03c08aca3e7e287d620897ddc59ae67c6f5c14063e38d68e7364365b6edc54","metric":"arena_score","protocol_fingerprint":"13abf23810655d5e3cc7b26658994dc532adf26433b34ce6b3c9855fa19f8fb5","run_fingerprint":"59f01106f5520fc11924d747f60bd707833cb6dd53e952864b40d21f35726c48","score":1622.8098625429598,"score_display":"1623","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T21:27:22Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9db3fad1fed400588c3950ae20f8f82d44892ae7331f0659c3c4247279d61104","measurement_key":"9977dea0d23fe9ac4aa44e1a50bebfe95f68244db9a99301cc90edc3fb1b9c14","metric":"accuracy","protocol_fingerprint":"d235c007ddac6805eeaf070ba3e06dcefb7f1a6c7cd41114fa61624a508e20ee","run_fingerprint":"3159044362855ea398e862994e6b4899d7bab74b9479119ad2f72a842f5ca8a9","score":75.4,"score_display":"75.4","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c9ddbc6765550e54adee760a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"zai/glm-5-3","model_name":"GLM 5.3","parameter_count_active":null,"parameter_count_total":null,"provider":"Z.ai","selection_rank":33,"weights_status":"open"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:16Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c0b4c99828fc1e1ee11a735496571e51bc24beee7f89260dea5cd3d949669f82","measurement_key":"0d66bae077d2a2d037e7e3d7eb6be62f74fcb0786d4733696d177b6a29edfca4","metric":"performance_rating","protocol_fingerprint":"72f06cbb6509a75a6886572ca0d438e3c26b92729b2fb1be0ff3c8e5a5e98e30","run_fingerprint":"d3cacc3839e105bca03f2906e30a0f719c858ce16226669c1b07cdd7814a4023","score":1092.35,"score_display":"1092.35","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f5050027bca49136f8c18c5b","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:12Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7fef241518a4c21e9e2f7bf96618e849ca49cf5e9b05ef30c1145f548ac7b3e1","measurement_key":"bb5bd00eb8c40f2b855ca48a2c75faecd9b15b32604455455824cbd0ff51dbed","metric":"pass_at_1","protocol_fingerprint":"d0b7f967aaa0dddb512a04b8a69652f86c5493b28ca74ee7a7863abec3a2be33","run_fingerprint":"63b35594053fc5513b04a6131ced003c54b9f438e2cf05b3bff6b874926f2782","score":39.5,"score_display":"39.5","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_99c4153bd6fcfe58f2654e73","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:14Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"241778aa5e55c9b9985ddf9120fb2e4ca56b35fd893f29ff20f6e0d5fd9a6d48","measurement_key":"fcfcb94f822393325cc61c7fcdd5209da0f661a82e490fde8a83c25b7fd32f8c","metric":"pass_at_2_accuracy","protocol_fingerprint":"a14ee82ca33c631994a647032530181e7f1805c4b03e97ee78f1b7cddb6284d7","run_fingerprint":"b5ede47fcf1ee0b57113ba2901ce7731f8f9914d7b7e237403e2f346a1dbacc3","score":94.5,"score_display":"94.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f5050027bca49136f8c18c5b","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":23,"at":"2026-10-08T22:23:19Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bd9a0ec046188a9827c714ec8fa7ae7b174038f8b66ed72223696df9030dd29f","measurement_key":"d3567c22558cbe32038959b12f611deabee582c270ed4b2aaba322d5e664f40a","metric":"accuracy","protocol_fingerprint":"02f739ab9bfde8e6cff4bb3c7ef004afae17217657b0bed25be6ad047596b341","run_fingerprint":"deb012c19f0574791f64c15dfd60d3ff2d7dcc8f3b7dfed55d44968ec1df68fc","score":72.91666666666666,"score_display":"73","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f5050027bca49136f8c18c5b","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T12:39:44.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fc3a2cd3d5a336faf5c30e4833cbf99ffc251d608cff746efb5d5b2b7453cc2f","measurement_key":"d45be59aa8b46f3a707dbdc04a3f798baf32eccb6c833f2152a987695fff2729","metric":"mean_score","protocol_fingerprint":"693d34b93b9418c46ea84fbca1e42e5b0dbb9205a6f06091bfd93c9e4e081404","run_fingerprint":"234fc9863156493915473bafb2110a104db7b827bc7c28dfa1037b9c6496c80d","score":48.0,"score_display":"48.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f5050027bca49136f8c18c5b","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:15Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e543c958fe8850c3e18c91183fff2b7e98320f0ee5a5434a1cc621f38f66b90a","measurement_key":"d736ec697717fb3d35d6822736c20a68498fc1194f19e60e5599b8f9da45f3fe","metric":"accuracy","protocol_fingerprint":"69d60d2e51b434f80742134cf07c7ccc7c730aa60c1a1a99ee9e359fd286bf39","run_fingerprint":"f4ccb2f5f9f5ee24b2aa3d8712776ef74ea4f9bf8c7f0539cd371459a9fbc67d","score":14.285714285714299,"score_display":"14.3","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f5050027bca49136f8c18c5b","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bd84b6cc344ffb33afe41d74ba03cd03ad5dcbf554ce2000447dc4f2f4090356","measurement_key":"693e4c486840ba5e7284c1e6c66c503b9eea41dd84c9c6f69ada7d253597c774","metric":"eci","protocol_fingerprint":"cae1e130187cd832a913603345d4e2fbc19053508bafea9b0e8f2be12f62ca1f","run_fingerprint":"175eee4a8efd44c1dc799c2bdeb1ff979e4b88e7c95ecb24530fa71b7ca0da43","score":156.11,"score_display":"156.11","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_dd74f317b70c8284099eda37","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:01Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1d1ac47017734aca650838a18b2e79990af4ee20925985e668f1bf12029b4d64","measurement_key":"4838b5d4ebf52338a3cf46575055116dd1c0476875e73f33afe9995f6f6d9813","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"bbf370ef0eece14387c38d3d6769503489888e11cceb06a23d6c8b3d2646f4e8","run_fingerprint":"034e48a8c4370e29a2adb2966acd548d8816373ea2fff84c765b69a40192f900","score":43.87,"score_display":"43.9","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_acbed0464c627a0050ab0f55","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T19:02:32.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4f77f88934bb9d9b8a28aae4c3eb323aca6c67d1b38c90d7b010ea65a1198f19","measurement_key":"c425a653821c1a5f6bdca009d0b4c7da02b8cbf302bc454669545c7758b7df4d","metric":"mean_score","protocol_fingerprint":"e18f09d9e2f96c682a1cfc80f558b03b924e77b939246a910272437eb24d3db3","run_fingerprint":"24957f83f71d0124edd02f47802205f94466e43210e1353000f23717e760d8a5","score":67.36842105263158,"score_display":"67.4","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f5050027bca49136f8c18c5b","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":30,"at":"2026-10-01T09:31:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"574d8e6f02133c61377c997200383b37061212e48feda17ac17b396e8dd7a411","measurement_key":"c05c59c0916f004298ad6f7870440cd5d59edfeab6358ccfca8bf29aeb3a6dfa","metric":"elo","protocol_fingerprint":"6486a9c65218c13ce168036d046284a375175225634d5a18887e72c5bc783175","run_fingerprint":"17667f96630b20383ee0b1e962bf83a7df5ce7324948079604c56163ac719c8a","score":1600.0,"score_display":"1600","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f5050027bca49136f8c18c5b","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":22,"at":"2026-10-09T14:38:01.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"86ff6c6fb8dbdc0a28fe15c2e30b8627db437ba04f35362690523574717bc335","measurement_key":"9c70e6052a9e1824456c3bd1956606055cd1e373c968e1769d4fa9cfa26606ce","metric":"accuracy","protocol_fingerprint":"1adeee9ed6a853cb95a5345df1eb9ce011de80431fb2509bfd2a536453dc1955","run_fingerprint":"6eed33a4c5178e52e9b74cccddf577af4ff1af0a1e13970ca67fa9a473976c84","score":89.83585858585859,"score_display":"89.8","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f5050027bca49136f8c18c5b","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_5f3023448c2ae4632fe1a43b","benchmark_version":"reported-runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":52,"at":"2026-09-10","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b94f49b2a7f17debd460c998ede46067b772c5f476b47c8cdcb4915a2c205ba9","measurement_key":"835846fde43039a2b490a327e48b57e479e3163d79aee97a25ef462c03d38de3","metric":"accuracy","protocol_fingerprint":"6947fd6a3208c0e07be0853cb9fc9857d705337e57801959fd2176d772ec06da","run_fingerprint":"9eef60794805d1e4afad57748ded34bb7f91de9cb61e52085810b47469fc2e50","score":36.8,"score_display":"36.8","source":{"id":"evals-report-hle","name":"evals.report · Humanity's Last Exam","url":"https://evals.report/benchmarks/humanitys-last-exam?tab=scores"},"source_authority_tier":"B","split_or_window":"public-multimodal-mixed-run-configs","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_deca33972debf2b7e8979c5c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"evals-report-verified","verified_status":"evals-report-verified"},"unit":"percent","verification_status":"evals-report-verified"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-10-19T16:37:36Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6651ba3e77be6b0a6a3026d6468f8f085d00ce9e75cea07714312088ecdbcb10","measurement_key":"bf47ebfa9c108abeed1683cfd42061d791e9225a4f4220691e48cff6b51b8540","metric":"accuracy","protocol_fingerprint":"d129e639daac4d14823fbdc31aa765502ca6c7fb4f60ae3f01bc0843aab699ff","run_fingerprint":"37e1108d8972f1f9a2effe8cc0d75563d320a58f831c8d9f4aef2a54b4701290","score":39.249305,"score_display":"39.2","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f5050027bca49136f8c18c5b","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T19:24:33Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6e61f04b5343f5e28fa68340887bf5201a00c585b163eb32b02de9213cf8906e","measurement_key":"84b42fbdfdf8dfae10ca335edf37656a6f9d7f4ed80347248f9b9290bb77b226","metric":"score","protocol_fingerprint":"3612faa886780f7a5b684da0fdd128172c27241633efc8d2ece7654f9e8b64b3","run_fingerprint":"1ed022570f854cf6370b2ab968c868c878d450e59f578012028d897e18855151","score":40.278,"score_display":"40.3","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f5050027bca49136f8c18c5b","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":51,"at":"2026-09-10T16:33:51Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3aef3fb0a6b34ce87f95b83427a254bb1b6b6d83111521a8e027e6dcea7af6f0","measurement_key":"d0d7ab32ef5e498b123b2f735705484323c69d0c197af6e7c7ae34e0df7ca454","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"9d5645fa04e161ab14280912d8ea3097070ab3f71be53c454fb7cd115bf70013","score":81.10970238095238,"score_display":"81.11","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f5050027bca49136f8c18c5b","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-10-19T16:37:36Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"69944fca5bdad882e7b5d72e98114af3ddaaa9c1c6d51dd231eb55018ad6e414","measurement_key":"c7c187e777bcb275dded1ddbc7042aeae3a11a0ab705a8d7677d1d27023bdba4","metric":"accuracy","protocol_fingerprint":"e6762ff11a884531add15b12eb46f33dfc18003b8c7fded2d356ee122ee97875","run_fingerprint":"aefce96f02d411abf2e3bb4071eb63f22756aefac712dbbb5202d640f58ad8ca","score":76.99422,"score_display":"77.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f5050027bca49136f8c18c5b","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T19:02:32.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7cc1d851fa0cc4d82f8b3f1bb149f39ea4fbdf6f87c287237f36f019ed9e678f","measurement_key":"08a9c8531c455237bcd6a38e34015e88a11e40d4fcd4addc98e70b7e1b35e87d","metric":"mean_score","protocol_fingerprint":"e4d403043222b5fcb211f56d28c7fc6fde0c88d3b6c4995890751feb21a95993","run_fingerprint":"1c17cd8db1414d00eca2c0b711214ef7417df4768f3a77490f6d8d1737a3b3e4","score":98.33333333333333,"score_display":"98.3","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f5050027bca49136f8c18c5b","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f7c49200f910c5fa5b3e13a09b0bd4fb6a61d6738bedcd65ca56c5aa7aa94169","measurement_key":"08b4da81a041ad02cdecc1145e14d924019735c3106cc2ca396f8d770445bf19","metric":"fully_resolved_rate","protocol_fingerprint":"b46813122497c19c9ba0dae80d148b5b82cc11678b843b9b7407ed1654c44eec","run_fingerprint":"0f4905632d64d728b95e18b8b99cb43b3336f1a05d833668a0a6d4e8b95cc53b","score":0.5,"score_display":"0.5","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f5050027bca49136f8c18c5b","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:15Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"32441a8a2989faf3097e6ecdfd4757996a3e79d595fbe54daaf5820c0ede35d8","measurement_key":"3462d8d629651ffebcc0c50240325d20203911a292cb184fe24c602cdcbd0198","metric":"subproblem_accuracy","protocol_fingerprint":"fc3067b1b4a2cbe74698f55ae61b0267526b3d6addbe1c9e8a12a15083350e59","run_fingerprint":"84a47e4ed13a75446e3ed9c1757396dab4ecdb22defdc3e540faa0acc6d0836e","score":51.851851851851805,"score_display":"51.9","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f5050027bca49136f8c18c5b","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T12:59:33.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"10dbf662de063906360dd46187540834c04d6c3106d607e4e32303936e58c319","measurement_key":"61fd7899924ec4815b0698a3b9da7a02926f48ecddbde58a2d639d68f6d0b5b8","metric":"accuracy","protocol_fingerprint":"99513d1f10f76d7497af2c7f5b0858de5e9cc8911a52cfe316032976a6262784","run_fingerprint":"e6be99d0474c0c147e4d4390ebab0b8f933fe2f7dd2481ad20e1f8debebbd920","score":42.9,"score_display":"42.9","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f5050027bca49136f8c18c5b","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"041d616818cb9cc834a6c52d9f5d11aec65b026e8cbc3a9ea0e356b1f9a88c6b","measurement_key":"421536f0a4c9e44d930bcee18e04577dda6b473c7bec06f8ee6592e975955be7","metric":"fully_solved_rate","protocol_fingerprint":"0919aa683212c45ad60fa265d765e025164b3b948457272c7b4e843719e2b126","run_fingerprint":"f8921c01d4c1b76db3445ac48c0903ada3ed1c0a3f8532c96b0d97311301e1a3","score":0.763,"score_display":"0.8","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f5050027bca49136f8c18c5b","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-live":{"benchmark_release_id":"release_9d2de9d5be7e9822af19f7b3","benchmark_version":"SWE-bench-Live Lite","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":24,"at":"2026-10-08","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d4d07a5fbe135c2cf7541346d88d7a7ed85b422c9806f4594270b49775490ec8","measurement_key":"608706726ae63d5ff1edaedcae9bc62b05026a1f488ce54da1636fb789c75f99","metric":"resolved_rate","protocol_fingerprint":"d61dc76751ffc5acc0426b88635a8c235020986766903d39e275b088307347ba","run_fingerprint":"349e0d0b9755880c623e3bec3f1f360c830d9b135d9b3de3f5ffd6611eb8a338","score":71.0,"score_display":"71.0","source":{"id":"swe-bench-live","name":"SWE-bench-Live · Lite","url":"https://swe-bench-live.github.io/reports-0605.jsonl"},"source_authority_tier":"A","split_or_window":"lite-300-python","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_58c877d1022e326e6412c759","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":51,"at":"2026-09-10T20:32:05Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"efefb63c016ea894910bbbba459724a1e918f44424524273d5819064e61e9fcc","measurement_key":"0ca96205c292473a17bf0f7fcfa656280cfec5072345d173c89920150d3e6a45","metric":"accuracy","protocol_fingerprint":"17d94bf92e11b19591bb3497ce2fb50b9bccbf5c8c309e60ee34d8b26b7d05a9","run_fingerprint":"4f2914a7f8101c43a15e762f644b3825f0f673f2f3542bdb642c28128ed195dd","score":74.532,"score_display":"74.5","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_acbed0464c627a0050ab0f55","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1429d0674c3971103fba32a7554f4aff502dc596bf9f751a4ed2a29a4c5db9ec","measurement_key":"b66c40d88b7892180e907fd8a0737e3d8ffa90c21b696ac33828f17d8eb386b9","metric":"accuracy","protocol_fingerprint":"8c47f22bc49e6d3d3d773e8423926e2299a6e1b68551422ce89b9e2c4b531f4a","run_fingerprint":"7bc61c07eb68f4e4de010e1c9cb8afb5a262f6bc31805f72ac954c2dbb2c26ca","score":19.697,"score_display":"19.7","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_acbed0464c627a0050ab0f55","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":5,"at":"2026-10-26T22:05:28Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bc2032b691438f6034ce1e578310d49a15c1b60fd877de6df78d98e5141e5ee8","measurement_key":"b37bf5edcbac67de3b9219f53fe56763cd93a22da3df8413472675c03cf92cb3","metric":"accuracy","protocol_fingerprint":"ed35a8b89fc4f0b309ffe34eba31aacaa3fd0f341bb3c6e2ba2359cf53927345","run_fingerprint":"e604eb3299dd9533c7a82034767b69969cedb50e6581151307c7a7b908fd02b1","score":0.0,"score_display":"0.0","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f5050027bca49136f8c18c5b","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":51,"at":"2026-09-10T20:32:05Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"262a640547f54662053b26650ec58412a07cfdc5ddcb40f62f74139b76692785","measurement_key":"2684dbc5afc598140201e3ab8474a5eb6e8759b4479f3637d9a4b305cf9bfcd8","metric":"score","protocol_fingerprint":"2d0fab9a64d382e3a3c1b2bd6bd3f275012b49c6d646ee4c1f8752923e8ea375","run_fingerprint":"28c6231437aac9df58d0e477bae25749053d82912eefa2a72de8d31fd6bd0fee","score":84.739,"score_display":"84.7","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_acbed0464c627a0050ab0f55","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_65fc140e7ffbb7bf62021f84","benchmark_version":"Text Arena Coding current pool","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:15Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c5aecb5ae1759574959e5dce34ccc7594a839310f23ddc7df08242b12f07d495","measurement_key":"53e5a6825ca3c3004868a78c95e5db43db8408e0ca2051020bc56a8f1bd0385b","metric":"bradley_terry_rating","protocol_fingerprint":"e80567596a8a54dc9ee62907c3a08b05306845c1e232cde8949d74c395f3f1bb","run_fingerprint":"ce1fa28bf682b21e0960c92235e1e995b897871bc3f984e99b35c9645a7aa274","score":1613.95,"score_display":"1613.95","source":{"id":"epoch-webdev-arena","name":"Epoch AI mirror · Text Arena (Coding)","url":"https://epoch.ai/benchmarks/webdev-arena"},"source_authority_tier":"B","split_or_window":"text-arena-coding-bradley-terry","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_f5050027bca49136f8c18c5b","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d770cec83a3e5a01cd6c9059301ac4c568bdd682e39eef3eda6e35a7864aeec0","measurement_key":"48faeed65aa7eb0ccfe7cba35a0525ab3cebcd7fde1f3c419144e5e3c9447e13","metric":"token_efficiency_weighted_score","protocol_fingerprint":"b6f1ea3da24ab139118d7c35bbb8abcca9cf0576d14c800f5bda33d0ee5d1431","run_fingerprint":"b23e37889e728a303dcd822b958782f793b4bcab20681625b760da2f52e30b84","score":5.946331818181818,"score_display":"5.9","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_acbed0464c627a0050ab0f55","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"deepseek/deepseek-v4-1-flash","model_name":"DeepSeek V4.1 Flash","parameter_count_active":null,"parameter_count_total":null,"provider":"DeepSeek","selection_rank":34,"weights_status":"open"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"186d8a910440e294aa1efe57e6a199bb92344c3303f2cd1f4cb4e24c55fa3e58","measurement_key":"c18502401251ad1deedf66a4c2beacc6def301a92bb90e75f8bed06097d2b8a1","metric":"index_score","protocol_fingerprint":"737c5486836f0b46e0266462687d4eaa3851cf8d85e9fc717469bbaf7534d901","run_fingerprint":"71fb16f148c4fc7d947d2f908c7c1555694739ba807f179ed55c7edc1fbcbb63","score":23.063298,"score_display":"23.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0619c70fda5fee4e5e40cb85ebe91c75674c2bd1b5dc4e5c0c2c4b9a2a495a8b","measurement_key":"1b48b824e185d38a443ca92c843dbe266d7e9f68a86ab845c0f2a315cc166313","metric":"performance_rating","protocol_fingerprint":"6891d233e4e51d5e32e85f40613aa84ec70db2d12f8707e09e131f6272670e8f","run_fingerprint":"25547f3ec5d8a5a4ecc3551d02fc1fc52aa0ba6f3793a27355de40bf329c4283","score":1403.15,"score_display":"1403.15","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9e80a9baa97441692cd136721521753e0f1e81a3c622028c4a1ba4dba6758cfc","measurement_key":"15106012e40917739217441ac82615a7909b525b8d59a765036ea6102d0d3041","metric":"pass_at_1","protocol_fingerprint":"b65e623417317e3d7f2f62acc87f19ed0bbbce8bdf0102ed0ee1a5ab8161ffe9","run_fingerprint":"a3f38c9cecad9a00eb9095ac0fe5a2147572730c5a13bffc1558330e5fcfc5b4","score":47.3,"score_display":"47.3","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7bbfeeac30a4f4702a8667b3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4b6cb7e8845c02bf694e11ebdd649458f84ca6965f4d0c814b73c02a3a75730c","measurement_key":"902c3a6fbf8745aed1ef9bff23ec343234565dd8b593034381b5a59192550969","metric":"pass_at_2_accuracy","protocol_fingerprint":"20ec2e9d0c96a3ad110511dd3bc6664dc17452fcbd0bf5682947eab4b984831e","run_fingerprint":"e23a1a43c07df7541144a69d686b6fdea9205616a4c592d4157c763a4eaeb9ee","score":90.0,"score_display":"90.0","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5acaf5dedecbabac9e57c1a87b06ca4a31eedcf7c1b9b41ef18195141108828c","measurement_key":"6131a893bc9513de2e4ab01f2f3f1a1a35e22e7110c3733b34e7abd064bab08f","metric":"accuracy","protocol_fingerprint":"f54664a069cd3a263e222b62884cb95777c40556c3db565b8f8b542e48ca7239","run_fingerprint":"c4f2c7f2ca59e4a402f05da988eef15d0f4c876bd68d4c01e21fdba9973cd611","score":61.25000000000001,"score_display":"61","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e3c64f7a183b5fa60a2e2cee6e7f2d7d7bec1a0584bb23a96e7c70f3e692df0c","measurement_key":"bacf12517d5aa97aa3c3d7eb3a8efc6f462b473c78a7a9dc1402baf12828589a","metric":"ips_score","protocol_fingerprint":"2c15a6f4527dea4db1569270c131a5d4bed094cbca7a2714355f863ed0ecf7ca","run_fingerprint":"345410cad5ee160844eaee63b9108694cb04400ccd5404157d309118b001eba5","score":-0.0030051721572174742,"score_display":"-0.0030","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30663e63c085ce7e9e35d6eb","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"544065ac25b698f04b2bb2c4f2a684a82fd084b79b5fc12327211fba18665611","measurement_key":"05a3485a9fdae446f5c19ec7c9ff38c44107b477b1e5172c5962de482674dd5a","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"8d2e164f1685fc88e8ffffc140826c6bde2395baf834dc295af4ece0b044bc01","score":1465.0587343984691,"score_display":"1465","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30663e63c085ce7e9e35d6eb","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:13:34.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d99c44e96715c7d554c3671cb9fea56446fafa84d530d20f1c6c08f2537ec094","measurement_key":"fd71a28a3615b86f2287e21a44266574247e9631262428b1c0e06332bfa92ef1","metric":"mean_score","protocol_fingerprint":"176acecf7dc6a84d63ccea8c01beca6ebd05693417c33427592398e8d7a4f9da","run_fingerprint":"ab46dc19612aab455ce0c7cb209f54e23be904eedf7b3503d1212115c5151606","score":46.0,"score_display":"46.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:03Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b012e13b97c5c297d19b0d6cfb31daad6e30c171dfd808de70cc70e86b6a67ab","measurement_key":"032e725bb8a31030feec550ebd65afc54c052d7bef4c7b63457f65c5f215e70f","metric":"accuracy","protocol_fingerprint":"1abd067406f487e8eb4e47e9a741e294e5071feab4d4584b9ee9d25afb0439be","run_fingerprint":"3d31cc276a5fac45563f03a01df7e32fb0d476e61e9ca26359d87626995ae1d4","score":18.0,"score_display":"18.0","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7fbf45a2ceaec762b823b4d1d6916ff1a76d9efbe161a26bd3605b3d052500c9","measurement_key":"487268abc0aa741c12d8eacbeecc19c065de3785cd2f60f4070389816f4ca9d7","metric":"eci","protocol_fingerprint":"2cea4b5221c2504f9ce4b93d4834e13ec1d94416ebc998a6a3559bc13bd7c162","run_fingerprint":"571f3740c1b6ec641a74a7d81b6f40cafe89b117e2843c83dde55c1f1164e10d","score":155.87,"score_display":"155.87","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c09f67f64bed3296f4de97af","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:01Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d788573b6d127df4c3bbcfd14cd664ae546f7212e000712d50bf8a66f88cebb7","measurement_key":"b85cd74427cb615c0197c1a30b34766234a46f3c321e224acbb540234617d345","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"cdfa9576b0fecd1b9913f0af0b92aaff679bc49f2dfe1fe6daec01ce5745a612","run_fingerprint":"a63ddb8811e3b99aa56581a47bc96fb95ce41e3ef677a7c10a98be74cf76d066","score":28.549999999999997,"score_display":"28.5","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30663e63c085ce7e9e35d6eb","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":73,"at":"2026-08-19T13:35:48.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d6fe6fec63927e8421724d748d545b4d504ff7324300ba7bd45297aee007d8fb","measurement_key":"5ea9528cdc4286d4b7000779d2ba320188f17d46f9b8dcbc962d2fbce3b101bc","metric":"mean_score","protocol_fingerprint":"3a7dbc6bd2b185e89d1634f1e9b098cfb3a5c5a2eb6a502f5c17c352164289e9","run_fingerprint":"3333583bf005f50d16e16a1d2b8b4c367cefd8e63f5461d6918abbd9e3966050","score":64.56140350877193,"score_display":"64.6","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":73,"at":"2026-08-19T13:35:48.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d407ded599c962a96289bc0c809a99bf39192ec87f90802e188cf4514af01113","measurement_key":"becfaa4f656ce2e150d4c7f031c69fae3a96145666d8345176cf9a7a894320be","metric":"mean_score","protocol_fingerprint":"65a81bc4e77c19398496f8304279491bf76b327f284447513082d40883dded3c","run_fingerprint":"a77faf8564216f1fb09f425fe81e628502aa09591950edbb1eceecc7b3dc6b09","score":26.82926829268293,"score_display":"26.8","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8505daed65f03092ed2df5fa52e92775dc362482835c4b1d8aa1832c2dd9e503","measurement_key":"61984885640403bff9bbe3683c8ae3bb820b2996fdc9617371aaefeb17312b2a","metric":"elo","protocol_fingerprint":"b46e0dfcff8c8b9505f0ff101cf3aee62cd533d0de417752c9d19c03a18728c0","run_fingerprint":"d96cabcd69e3995d7a4e1aa2093f38d71ac9799ed0758332a90b9a3db1034d45","score":1457.37,"score_display":"1457","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4a23194b844278df50c9bad9b3b57eb06ebfc51b53abfebb24c2a051b47b0d13","measurement_key":"8b132e34c1dc2701159c80abac6fb66af7789ec5d64ffecab1da4cb1cb1b3b5b","metric":"accuracy","protocol_fingerprint":"38161a15d939b35f8ffd6361497209747f240559523d5748d1ff72396ca69bfd","run_fingerprint":"fd1c653ca14a23f547e2c7c71c957134b4eeeb9eeb0fe74c1dba0fe1a3b6c63a","score":92.424,"score_display":"92.42","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_1f4bfa5486eb4deec4942449","benchmark_version":"HLE original","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":80,"at":"2026-08-13","last_confirmed_at":"2026-11-01T07:28:22Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"76e6fabeb085a834f0e7d3bac34867becf3e12b44dd61b68598b8985a5b9b128","measurement_key":"0b5d24cc89d594193e9043798ead7c56dc6f8f0e7f364b3d3405b72f8282d1e2","metric":"accuracy","protocol_fingerprint":"75c0bf5cc62a5e8a5b5579767a3b94349eb76845210b6368a4b0ed833f857d74","run_fingerprint":"7d9433fb208028a63a95bc36a97f4e7b0326f9b492979994c13e4b00ba7f4aa1","score":42.7,"score_display":"42.7","source":{"id":"deepseek-v4-pro-card","name":"DeepSeek · V4 Pro 0813 Model Card","url":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"},"source_authority_tier":"B","split_or_window":"provider-report-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a6b20b4d1f7b9f4ae3e96950","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bae6152e34bec1027bd585b40a5eaaf8ffbc4588b6089278404a0aa80863b05b","measurement_key":"d0893660b148f609c6a1c9d28cef404d1ebc46cda7d18076b0ea28bddfbd501a","metric":"accuracy","protocol_fingerprint":"6bb682f08bba3be3731329c1420e9222e1c05ecd23476a8a152984bdf45cd149","run_fingerprint":"daaacad00c7a9c0d4442f6b22726c4824df42780ac7fd7ea9c8712f474518216","score":41.010195,"score_display":"41.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":47,"at":"2026-09-14T23:34:42Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"970c70bed6dc79589a5d79838d2815284a1bf63e9f009630909d722492c8e79b","measurement_key":"abe4b20174190a8d262c1098f96a1eaf98286e5ff25d33133a9c5e1c9b79c0e6","metric":"score","protocol_fingerprint":"8c9fd853606ff405b8afab9da85a41ad682f0b0d2c881df799a68b48591de76a","run_fingerprint":"5da6c552b96d5e53df05abe712fd5d8a857287ad4cf16d96d4fb4457c6402a35","score":51.611,"score_display":"51.6","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fd1bc8d80a551159ab1d00ffd59a7ac7d5f2967bd4aef7e2497bf4aff557b533","measurement_key":"bf904c6afa1a966b261ee8194c76f502d02477b794910213b01aacd2b155cd49","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"e4cdca75b0fa369cd54e8b605d97586029d61e0eaec499e4e2605db7e020e32d","score":77.43614285714285,"score_display":"77.44","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2a6ad306680e2f1f01edb742","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2325dc64cafd923b73cba8c82be9691b7b7c54c29b2a35d5403a8353e99df28b","measurement_key":"8a920f197c89a3a3f2b0c790320ad189916b00a4f18afc52a8e01a7dbcc3dc19","metric":"pass_at_1","protocol_fingerprint":"2de02e83a78a2f7ed2387c95d0e5bc5447a0e06484a3dab91875f46758d1bc8b","run_fingerprint":"2204a70458d671c36bf3fd8503ad1f2299c87ff2eca3a44819aacab9fc9dbd7e","score":87.525,"score_display":"87.5","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":11,"at":"2026-10-20T20:32:20.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bedb9b1439198da465c9548b35d708026cf3c0d300919179c267833fba2a5a09","measurement_key":"711dff95d5d5ad06d3cce1e961a0ac8f28102725427b5c4e06c126f5fba492d9","metric":"mean_score","protocol_fingerprint":"38173aaa8e148ac5065daef9cf9c11c853a0cd666b92b00c3e623b75029d1593","run_fingerprint":"17a2ac60fd66c13a1385c45091b31a1f5620214c38b8c643fa7565f11063ab72","score":33.33333333333333,"score_display":"33.3","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"974d62f1598801bec0dd3f7137f43c69979ac867e920c495d7b76c6b5da1ea80","measurement_key":"c2743ff00378970451c82bca906df502692519575305efed0775160beec5f6b0","metric":"accuracy","protocol_fingerprint":"667fd49cfa7b9fae806e1b03bbc1d0fe3aca2ea46596fe3411aa0dc2434b4e6c","run_fingerprint":"15d6194840db2bf76241c4c6780d5ffba503ce63e51bc9e51cbb766823439cb6","score":86.972,"score_display":"87.0","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":74,"at":"2026-08-18T21:03:23.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ed8ac7e68728557cc99efb9b94a6d1ad80c46b1819786483c5a3ee38733e58e2","measurement_key":"a0ca8f75402fe79a80ed0df1105d9438dfee24dcf2aa00f60d7d8578fa0b7f58","metric":"mean_score","protocol_fingerprint":"93edc8b8be7acc7253a111ad5e77411d3b0836ac0cb76c70fedc517ebc5c97cd","run_fingerprint":"0dc66ceab358a798bfc2a6c85c3cecaa0a5e03b085a27d747c167459adb4414e","score":98.61111111111111,"score_display":"98.6","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bb26c2da83b85d692942bac39c38d054e1c551fd5a0e1228130e724eea208317","measurement_key":"1d68f64b8000644c24714f1838bba56cf076a9fe5d4a6a8e33e0f8bed09e22c1","metric":"fully_resolved_rate","protocol_fingerprint":"686d1b2df13b91df77b1f42792ef61142ba1d97d2ffc5364815af261fb173003","run_fingerprint":"e841b993f205c226e2be71ff63ff1594035838c3a1c24385c7e68269b3ae790e","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:02Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ce9d58f3b8daf5b7564891ad5a0c5789d4d30aa1c415320b65ce7d52c0623cb7","measurement_key":"5f1a5cdb72fdba823d07a14e9b00c487a3a989ca6189f555bec3a9c3b7c22965","metric":"subproblem_accuracy","protocol_fingerprint":"b57fc33a04e0622780b6690f5f931d7db1ed22ca076316648d4b93926e08bcec","run_fingerprint":"128638124d99fbd77a832487ef4a19e0ed8d91c21c17addf6d7265aa996f2da0","score":51.0416666666667,"score_display":"51.0","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:30:20.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0c70879a0182d77c9be377defbe1f4d77c98249483d831b45f2caa97df4e7e1b","measurement_key":"988e80e288bc66ebf69f725daf3171af7817115364e3b54e30a202363dce2cad","metric":"accuracy","protocol_fingerprint":"fb389f5e6ce6839d1fb8f0a8eab180a25968c0d0c926ccf278768bcba9be7348","run_fingerprint":"fa3a22de174183bc711d3dcf1951777492729ec9ece957a1f53935baf0844421","score":52.90581162324649,"score_display":"52.9","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"52e3e7e8b4408ad3e68fb08e28f74aead797fea4416b9d004caab3ca14ec3c3c","measurement_key":"fa968e9355b299dc43d5e71df6816c1f5bfdd51b4d49135ccb8f35ce45dc8ada","metric":"fully_solved_rate","protocol_fingerprint":"dcada9b2667ed80333de23270d9b430a382bb0e7b5a5993c3f0ccbb0f3bcc14f","run_fingerprint":"96f043ba94ab55482fff924445059c09edc6ffff0a79a8525c1a2bbe9fd2089d","score":1.908,"score_display":"1.9","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2e5b739d72b06c0a021aaa5b6d109c7d736d017e1ac3b0019798136eb231d598","measurement_key":"bcda363e11cbe26acedb1524347d3106095bc69b9a5316289b8b81912c3a1115","metric":"resolved_rate","protocol_fingerprint":"85959588eff6b49765017779c33994a2669b391ff7c12b230bd90096006b14c2","run_fingerprint":"6bc81882f409dc7e0ead091571bfec07a5f558091f797d9d4c4e892ce5d02ff6","score":96.4,"score_display":"96.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2e5b739d72b06c0a021aaa5b6d109c7d736d017e1ac3b0019798136eb231d598","measurement_key":"bcda363e11cbe26acedb1524347d3106095bc69b9a5316289b8b81912c3a1115","metric":"resolved_rate","protocol_fingerprint":"85959588eff6b49765017779c33994a2669b391ff7c12b230bd90096006b14c2","reporting_origin":"organizer","run_fingerprint":"6bc81882f409dc7e0ead091571bfec07a5f558091f797d9d4c4e892ce5d02ff6","score":96.4,"score_display":"96.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f08219f0723920ab4c1c0d0cbe2309cc508c7fc755083ce41930e4adc34dedcb","measurement_key":"7dd29de414c717272bc349e3eb850b52faecce14500ac38dac0016bf2d2f317b","metric":"pass_at_1","protocol_fingerprint":"b99bb0b1f3613089c782db885bcc112434c645a71c97d64630c00d210360f35a","run_fingerprint":"3e40072924433de7f3e7679956cdba839dd213e8409b836c2bbf118e37f143a0","score":39.587629,"score_display":"39.6","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cb1b82b597079da65f349b1efeb07131f74e0f4bdffcc01f982d29006c122eea","measurement_key":"771cf034f8530af5c531e9c956705b16ed0242ac8f5afc5cfbb311d184176e97","metric":"accuracy","protocol_fingerprint":"a881c122281ac49a833fae875e28b55192135f36775b5330f25137b63ccc61ae","run_fingerprint":"ec607d0c57f259043e8784e42044a4986a1f9cbcf1dc3e2d42059e254c576048","score":54.682,"score_display":"54.7","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d5f6f9d921fec354466ca278037924c6cd3eac65486b1f9f7947e4718b0a2384","measurement_key":"694f2a38631866cb3a9dd875d80a37534a9c06bba1b4989f5b4e38b5b9d4452e","metric":"accuracy","protocol_fingerprint":"3bf60d629e3747ae7c95c4dbd78e331c7bf6b91085409e34268c32ef1118f485","run_fingerprint":"17054dacf3122f236eda11ef9500738fa8c9db37b426b8d0157fd79ab2c7812e","score":14.141,"score_display":"14.1","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a8dadf58ca154cf4806d2f65f3572d0043df768c325949258458a448a01e89f9","measurement_key":"fb01040e77fe1e3802d4214b7daeeb99a9d9ed9d4affee1bf196e776b5878d3e","metric":"accuracy","protocol_fingerprint":"3cc9acd33160fca4968fd5277ec665057d116b030a62d0ba9d546262851bb0ab","run_fingerprint":"fda454b343ac3f0653636ad4a30ba852e1d601a4e5403e94b6a307723c1903e0","score":4.286,"score_display":"4.3","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f367edabdb25ee12fe576d5a71e20c9c00bce88fcede81cccbc14fbbf814d3b7","measurement_key":"baf329acc148e0f75e9e64c43c489a068779f173d800a25681920b34ed27c4f8","metric":"score","protocol_fingerprint":"db1cbf840bb13d5c6ab99abc75b9dd09c3cb9679a3b4072d9e450952478dc5ab","run_fingerprint":"47e6319fa3a363e9cd194b62d0f0a7c6e3df2442c4ad74d671af6cb915ff781f","score":82.297,"score_display":"82.3","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b2261b975869227f8fb4c68014b6472b07103433a5196c318cd8e5341b955497","measurement_key":"1d4a18a7322637e5b65fdc649d582ea94a517d24e70ae94ac7142a73d432e4d7","metric":"arena_score","protocol_fingerprint":"659dbdd801269e5d62a98df7445fe89c67eb9994266484530e0657a7dc14b8e7","run_fingerprint":"06cf7c8bd6cac4342afa9dfe0da12404efcd0dd42b7dd3e08ff11c3ca6f9e114","score":1581.8580682830898,"score_display":"1582","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30663e63c085ce7e9e35d6eb","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6800256c7e1221811e6662916dcb4708c646cfffc4c58a9466bb92a03759485b","measurement_key":"7be57064e8c2c55c617d5b73d4e8e7f5c8482fda3600bf8692968cfab36335e8","metric":"accuracy","protocol_fingerprint":"876d95f59e5e7ca1a61549d0c9418536be0db88d61f34ea6708f45f226b33e68","run_fingerprint":"5e9bcd6032c728b9e7293568cc533e127dedbc7500fb43192cb971856895830e","score":66.22,"score_display":"66.2","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_85d13172a494484884c0ddf3","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"deepseek/deepseek-v4-pro-20260813","model_name":"DeepSeek V4 Pro (2026-08-13)","parameter_count_active":null,"parameter_count_total":null,"provider":"DeepSeek","selection_rank":35,"weights_status":"open"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"46e15d348a1e2e852d312f5e267a65d339a3a1fa3f37cbad2111e10758670b1a","measurement_key":"235713a98ac1a165ec690877b029d311c7377a1d85f0b5b5ff03b6e045b2bae1","metric":"performance_rating","protocol_fingerprint":"bd3d060a508306ef4cc3f8ba4bfb9d72658f96c96a6845870b108e54d6fd01d5","run_fingerprint":"8b0417ee4d06d2e59f37f0ed31312231a1b72af6c31d5c800b88a6e822270492","score":996.5,"score_display":"996.50","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_505fa327bb2ef52374adba4e","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"99d679f2f1468f0d172a31d7db1776821902cc47c55d4b2fa26f691628b7caef","measurement_key":"f3015f802f7a07a5a4d40956f6ac79a1e3d335a3a1fd72de56b8e4cfcf56aedb","metric":"pass_at_1","protocol_fingerprint":"87c7d6d307e6af6aaec53bd62b0bfa5824dae9bd7f22f32a5d6934e4bcc324cb","run_fingerprint":"0c948b40e9e83fe3b4c893fe0fb8747600d10661aa77394627a5154057d1f691","score":46.3,"score_display":"46.3","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_850fc6175572e341e7de5b0a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"appworld":{"benchmark_release_id":"release_3fa145932216c0afcdd9dae6","benchmark_version":"official-c1f56015cf7c","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":223,"at":"2026-03-23","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"1cc1db4199d03d47da0120c97823e9d463f446b46557bf3b7f7ff8ed2929fac5","measurement_key":"2e35b45062aa69767a1c1d68ded429d9343b1be719516e196bc5bc811519bb9b","metric":"task_goal_completion","protocol_fingerprint":"72b8a94a56270e5c3983fc0a16989987c068c2c329242dd70533a415bc929b59","run_fingerprint":"6c665940b7aa160398a5b32af2a17e08b0123d7e0dbddc617029489a17385a15","score":72.4,"score_display":"72.4","source":{"id":"appworld","name":"AppWorld official leaderboard","url":"https://raw.githubusercontent.com/StonyBrookNLP/appworld-leaderboard/c1f56015cf7c3441ff1933f5bfbec879798d7bbe/experiments/outputs/_leaderboard.json"},"source_authority_tier":"A+","split_or_window":"test-challenge-all","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e22277a9c302417e104ce78e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b461a5b3e95ce185cb3217eb325db73b09eb0e39ff7db2e2b7d6242f74891a84","measurement_key":"d8d15f181570d41bbbbd277b6731663f4b4f542f4d6be724fc048c499bde740c","metric":"accuracy","protocol_fingerprint":"064163ac017b920b561ddfc144ba380b6232580bcc756f1dc732224e4f3c6eec","run_fingerprint":"a21081add0f41d64efd61cff8bf2fcfefa52a37ca435e84a2dde82b2a80d9554","score":68.75,"score_display":"69","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_3b724677f8ab5619a6947425","raw_label":"max","reasoning_enabled":true,"strategy":"token_budget","token_budget":120000},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ba55d207005e628c8bf813da7ddf50f61b1b5eb0d1735f127553ddd13782c22d","measurement_key":"79c2b24df310bca2774a6d7f4df7aa3899ceac1adc0de38aeed974f150893244","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"bbe1db75549247e203de3ff4dadf7cda18076d88dbc4006358f06015c0dd17c6","score":1503.162754839902,"score_display":"1503","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_f3a928c2dc4d6711d402db03","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:43:19.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5eca1223819a2fb09ee5f8c2db0cc3f00b489fb8143a8d54e75df6e4765a58f8","measurement_key":"34663e46c6955db70c7442038a820f5e5c19f555c0006323d61de7980deeae79","metric":"mean_score","protocol_fingerprint":"4d2dfab0a746311072c5b8ffbfc0af3a6a326784e207115c4d6757cbcacb759f","run_fingerprint":"020e5f208dca362cfb6c9223730cd2d22cc07bd9a2d0b8836e5f75bf4cb7bc62","score":21.0,"score_display":"21.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_850fc6175572e341e7de5b0a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"66315e4045f49b419548b7cc374c991a95dd4ff8fb3464008c67d9ede1eb14bb","measurement_key":"37995df15001c5ff07803787acffccd12fa51a47a1870a26aa9d0049b733cb49","metric":"eci","protocol_fingerprint":"1f26114cc61f6a9d17a72ada6f47a5f63bd79361f49bacfea508045dc0e3cd86","run_fingerprint":"3b29afd0fecd052703870f871ff7786272b9f77cea9e08df56a9e7100ede971e","score":155.85,"score_display":"155.85","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_152e3a035044e671415749f7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5c6df73441f42f4c70d9af7f03eb58fb0860c15a314f5e247f288f57102210f3","measurement_key":"1f8c0356156fc78a46d386631293829a1a443192a49cd67d552ba1aecee5928e","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"c748fa81cfe10c6144fa6f7d7562489be23172b94784012fabe2a240a05be6f7","run_fingerprint":"3fd204224734556e81e1376d9ac7db4313c95d8a8d84ba8bbb181724b9756171","score":26.640000000000004,"score_display":"26.6","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_f3a928c2dc4d6711d402db03","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":143,"at":"2026-06-11T00:19:44.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"55f484e95424c5953d21537aceb8afc1a7c382fd37d7797e06d6bdfc1f2a1110","measurement_key":"64540a9adcf4f162f57e129055a3d7530b74dee2c47c34c7dd2d54cc8b001d95","metric":"mean_score","protocol_fingerprint":"4cfb756cf4e21c80a11a6c1a5fdd6d61e065e2c01ee1e7178cf2bc90817cd4fb","run_fingerprint":"8a3330741a609c7e0734eda278dde595e464255406e2274535287c8f28fc9dfb","score":65.96491228070175,"score_display":"66.0","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_850fc6175572e341e7de5b0a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":143,"at":"2026-06-11T00:19:44.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"354e9e9e3e5ccbdf0f9f525667e4e6da9df671e8a87dda8e5105a399fbf2bc8d","measurement_key":"d04fa96a5cd65ce28a1359cc0e6ca7082c8bb24eefefd1690b0171d25ce3396f","metric":"mean_score","protocol_fingerprint":"977303192a8bf64f180a1f4395dc194dde5d277227ef9d8d4f9f292afbb127d7","run_fingerprint":"c14a6cfdb2cba541e96ae4da05d4f6269ea07e2fadacd6202d311f1d64694769","score":26.82926829268293,"score_display":"26.8","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_850fc6175572e341e7de5b0a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c84f794ab12e986775ddd665bb6a6140ecbd4c56b2aceeb39c2e9e39e1cf2670","measurement_key":"2977fb601f13f403e5dfb111fdf6793b269fe809ed7ed56814ae946cf9c5e9bb","metric":"accuracy","protocol_fingerprint":"692d3831b8cbb7a644ec31cecda17e81066e6305d608eef2c408c62c850577b5","run_fingerprint":"2fada5ac0388a322efebab9516838b06d34fb5c4169515659046960c66e39236","score":89.646,"score_display":"89.65","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_850fc6175572e341e7de5b0a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gso":{"benchmark_release_id":"release_176f07ea4e9e0b8dfeede990","benchmark_version":"GSO current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":188,"at":"2026-04-27","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"511085970eac586b96be670bbd6c89883f5e3fde9f05c6fbdadb588b94c730df","measurement_key":"8b9c6004d595ad3103af6dcb7cd79ee3f75dca8bd73e1e90509f170cd7ceaab5","metric":"opt_at_1","protocol_fingerprint":"1596cd4ede296ae563e39dff0e68f7793750895e0d1eac5471fb9e59bf002fab","run_fingerprint":"610eeba4e21515274874837fac8f618346b03dca5be4daa186373a0e7ab7ce62","score":41.199999999999996,"score_display":"41.2","source":{"id":"epoch-gso","name":"Epoch AI mirror · GSO","url":"https://epoch.ai/benchmarks/gso"},"source_authority_tier":"B","split_or_window":"official-set-opt-at-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_f3a928c2dc4d6711d402db03","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"hle":{"benchmark_release_id":"release_8817af9d9a0235bce0826e22","benchmark_version":"HLE finalized 2,500 · Scale protocol 2025-04-03","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":256,"at":"2026-02-17T17:04:32Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"713195fca7d2e2537eb16cdabe949df6c3318e4ab6b41fe6de36b3d0918aeb39","measurement_key":"b40f7e0851e0efd9fbff8f50b63d150941436f3345f7e2c873af50b078d05c11","metric":"accuracy","protocol_fingerprint":"8f0a1fba4a76d322559d69680ab47473455fc5f09bf7e1bc4cacd51c4e68eeda","run_fingerprint":"a930b2717cd22fb1c48d04bf27a512a03dd594b8743def08e4ad77892a9e6336","score":34.44,"score_display":"34.44","source":{"id":"scale-hle","name":"Scale AI Labs · Humanity's Last Exam Full","url":"https://labs.scale.com/leaderboard/humanitys_last_exam"},"source_authority_tier":"A+","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_850fc6175572e341e7de5b0a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2e42aa46e2aedb0d33feb9e63f24bd3f7bb3d1a11926d0af97b8152dbda97db9","measurement_key":"b8dafc169a01aa4dadf568a24e99563f126a4a6860fad39b1ad40e1e0b7d9688","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"62e8d2741367f013b032bb76d09e4e8eead22facd06f5934a8764451be2d0492","score":74.51990476190477,"score_display":"74.52","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_f3a928c2dc4d6711d402db03","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2c78c9a8bffe201d250b1756c5706ab29aa7cbda147577dccde0a88dd39b301a","measurement_key":"412689bc6fab122d044d9696cb9a900e14570c6770f5c901b45573c2f241df37","metric":"pass_at_1","protocol_fingerprint":"312178ee84b097dc528d62c68741bc228deb676ae4d0357f763789536981d7c0","run_fingerprint":"82e0ff85a7a69b99775b31448cbc58e2855b41b4ff3e57626728d05f396b1a42","score":84.676,"score_display":"84.7","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_850fc6175572e341e7de5b0a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":317,"at":"2025-12-18T18:01:17Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"7fef3ad5b4071a2e6290a7195c939179591787913dedb696c40a471e9dbe0b1c","measurement_key":"9c1da68b2c9397e5e0c5dcb2c09f1a0eb3bb663ad1f2000426c47891f135f7b4","metric":"pass_rate","protocol_fingerprint":"8c10287800aab508b05e4bc91885490033ffde65e2e25eae2c86a2e93df9c9d3","run_fingerprint":"df9b1688661a4b693fe10898c82af03f31ce3c83220252813d33bbbadb9ddbf4","score":76.8,"score_display":"76.8","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_850fc6175572e341e7de5b0a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T16:48:25.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"615c1652ceb31e31e87bbeef916ba86701edc2c62c1ebb769850eb95ea2f32fe","measurement_key":"6674c28f5e4baa165230c8f8b12e6128bd95331f894bcae3a6ee5cfda059774a","metric":"mean_score","protocol_fingerprint":"6104ec04b8815f57ed721dc6946068bd2e23f650c78eddd6f09b4e3e97f6d68a","run_fingerprint":"1e0fc694e5dd9d70cecb310f81564170782847dfd8a9488493c8405cedd5f28d","score":33.33333333333333,"score_display":"33.3","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_850fc6175572e341e7de5b0a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"112cbe064997117d2ad46121570ded6a85392550ef1b6789ab5c6c2d7f044cf4","measurement_key":"aca266e69a19b57c61102780c5216467b5f11af30032cabd3e16982392ccf126","metric":"accuracy","protocol_fingerprint":"d2af2ea7d7ba56574b2ca9a9aee70a7ce41c605007b2dfa0635495b0a29b65f6","run_fingerprint":"a4e5c54d65fea880f24ac2366d938cc7ef571c957f8dd152da189494c4418e4c","score":89.107,"score_display":"89.1","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_850fc6175572e341e7de5b0a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b05f26e6bf95b4089e90b42c454f527750ee2ec985d23ebce701f523a339f799","measurement_key":"d16fc1101ca00321718654132444f1955a9d951f8d940db77bc30c62396752a9","metric":"accuracy","protocol_fingerprint":"751ee82cb51ee0248b91981c3af5aca737766de94a5a828f99dd47396bb6aad5","run_fingerprint":"e56a6fc6038d840f1de306739064f55ba30b034313c30e9fe32c35b18e31a312","score":83.873,"score_display":"83.9","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_850fc6175572e341e7de5b0a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-06T23:58:17.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"68417e1301fdffe4843e85d812f9572af92c298d2cecf71862864ed0541c65fa","measurement_key":"d70c9cf425dde173dbcd6d88833a7653bf366fef1eb9cb4f31702270d5b7fbd7","metric":"mean_score","protocol_fingerprint":"91f1ee70583fe8a71c9a36a257a8ff7af9a54946c9765146dbd06d21cc083bd5","run_fingerprint":"7e94c925744990e140dbb90996586f902bed14892ed290763d4507f7d4901ad4","score":91.11111111111111,"score_display":"91.1","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_850fc6175572e341e7de5b0a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2f0ab562852c86193e84890c85eb93b862fcc69011cec9a25dd8603a74fd3490","measurement_key":"8ae849630ac4e8e58b9f4c96994580c40bcbd31a0375c2a4bfcdd3540a698835","metric":"accuracy_avg_at_5","protocol_fingerprint":"e4efa10f59195bbd55fde3aa51b8c9db51ed225321e6620142291c31b330a1de","run_fingerprint":"821fe1731435e8bfa0fa6c03baa41144e78e1a2e1026d7ba5417532422c58723","score":67.6,"score_display":"67.6","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_774e289c6cfcaa16db364671","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:27:45.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f4e0f501cd6c05f492c23dbac763bb77ec418ad56b01efe0d8018dec969834a3","measurement_key":"ffbd9d8521bf337ae7b96d5ddef4f08ef709223810c18a6ad526240493b77b76","metric":"accuracy","protocol_fingerprint":"c0cc28b2bc35c4d4af2d8b42dc97810da93d85493654fee2989049a865502419","run_fingerprint":"5ffcf89edc0616fcd6d144f5ef9a4de0497bff501781b19fa95220e34213017a","score":47.0,"score_display":"47.0","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_850fc6175572e341e7de5b0a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-live":{"benchmark_release_id":"release_9d2de9d5be7e9822af19f7b3","benchmark_version":"SWE-bench-Live Lite","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":76,"at":"2026-08-17","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e95322883c11ec76bd0064b1a02660f74f5ac959301a763eef933a3b620002d0","measurement_key":"05776fcb79ad193879311a433dd994aac69a591aee01b91a704487353814faed","metric":"resolved_rate","protocol_fingerprint":"316ad8f92bb102c364f20b335f7b61c5fa87ed7e9712c42d2dc4373709d36dba","run_fingerprint":"05c57601ba4663667c530672f544ab5a09d7a6e9d585f7681e01f6b5f977919a","score":25.0,"score_display":"25.0","source":{"id":"swe-bench-live","name":"SWE-bench-Live · Lite","url":"https://swe-bench-live.github.io/reports-0605.jsonl"},"source_authority_tier":"A","split_or_window":"lite-300-python","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7258dfad95526e807989ecf7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c2e521d67e1b18fab054d408ee368ef7c9841098cb47f68d0c9bf46d489e8d4b","measurement_key":"4425bc9c926e62cdd1b08582f0f2ceb1617e8ea41c887053428465a8ff9c76f0","metric":"resolved_rate","protocol_fingerprint":"0efba33b346c02c6c4c1dab6f884af894585e223cd00e12df247eeca85491f67","run_fingerprint":"913c81b1b1d9ff7f932011d4e76095e282c53f8bb9748ceb4cb7065e7afade4e","score":78.2,"score_display":"78.2","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_850fc6175572e341e7de5b0a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c2e521d67e1b18fab054d408ee368ef7c9841098cb47f68d0c9bf46d489e8d4b","measurement_key":"4425bc9c926e62cdd1b08582f0f2ceb1617e8ea41c887053428465a8ff9c76f0","metric":"resolved_rate","protocol_fingerprint":"0efba33b346c02c6c4c1dab6f884af894585e223cd00e12df247eeca85491f67","reporting_origin":"organizer","run_fingerprint":"913c81b1b1d9ff7f932011d4e76095e282c53f8bb9748ceb4cb7065e7afade4e","score":78.2,"score_display":"78.2","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_850fc6175572e341e7de5b0a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_72d764965dd7baf34f983249","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a3257c378b89451b6ad59b3698f23e7943fd81ba6d7a4fb0ef6da9ac1e9a657d","measurement_key":"6b3cdf89a772f6fafa15527dbf304ecd4f264556cbedc7b7e58b4e7497bdbbca","metric":"resolved_rate","protocol_fingerprint":"ee4e41d217d898acdf8d142ff31ef7c20f7cb11cad469979ca052b4bc43818e1","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-03-01/2026-05-15":{"benchmark_release_id":"release_72d764965dd7baf34f983249","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a3257c378b89451b6ad59b3698f23e7943fd81ba6d7a4fb0ef6da9ac1e9a657d","measurement_key":"6b3cdf89a772f6fafa15527dbf304ecd4f264556cbedc7b7e58b4e7497bdbbca","metric":"resolved_rate","protocol_fingerprint":"ee4e41d217d898acdf8d142ff31ef7c20f7cb11cad469979ca052b4bc43818e1","run_fingerprint":"77bac46b049f106a32671c6dde0f7a1af34d593c009617f9a3b2a4ab9c5211b7","score":47.81818181818182,"score_display":"47.82","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-03-01/2026-05-15","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_f3a928c2dc4d6711d402db03","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"77bac46b049f106a32671c6dde0f7a1af34d593c009617f9a3b2a4ab9c5211b7","score":47.81818181818182,"score_display":"47.82","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-03-01/2026-05-15","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_f3a928c2dc4d6711d402db03","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":179,"at":"2026-05-06","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c03ae079b1ea3586971e1d618d87ecae0a76dcf8c6de94677ed9a4ba8710997e","measurement_key":"7e08bd6d4035e5aabcf1c01db1132f34771a8c596d8bc3c56e43703d69306791","metric":"pass_1","protocol_fingerprint":"5a2403363a0c9feff2c6ac7d53571698b24966266565d4704bcda085179eb000","run_fingerprint":"260d06a9dee49bb1cda333f55abd10aed0b1138f906a2afee8c500498b49fce6","score":27.32,"score_display":"27.3","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_850fc6175572e341e7de5b0a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a4fd702a4daddadbda7b0557978393d5ce348c9beddc3343c4d4d740ed6ba281","measurement_key":"69db89d411c996edcddeec89769319653d4e677b20045910f5c6d7aaa6e3baf2","metric":"mean_final_balance_usd","protocol_fingerprint":"5984834f42e164be2902d2931446c87ab2d68e88835f3ba18c49a083fba222b2","run_fingerprint":"87f2c612d65674f06f2cc946c7e71e95c2769ce2aae37c8c6b641f78c2c7d58b","score":8017.594,"score_display":"8017.59","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1f201fa792617714eed8a8a3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c22b356f78040bbebb58a8c55241420632a5b0f8346a506d8ba8a6908059deb9","measurement_key":"626442899c6e92b5de82dcc34f9a38d282c435de2e90f83c598ab18793942921","metric":"score","protocol_fingerprint":"a4a97dfdf352ec9a16a9036e7aa41ec9893577a2c26bda945a4004262dcd0cc4","run_fingerprint":"3bbc79fef96e2c06c2405b1c972b6a340ffbb162ba11e3aa441759cb8fd3aadd","score":57.573,"score_display":"57.6","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_850fc6175572e341e7de5b0a","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f6a911e05b56f3185c3c69e6a7fe0075217fea5e37d465d7737adaf03a209d21","measurement_key":"2b858ef7833887811be889d509a299515fb76ad6a38d3e52325d2b82ed657416","metric":"arena_score","protocol_fingerprint":"110b4ca75c475241e184c9a2d8d7a99d0b75a64eb6f6cc83304e51d313c0a814","run_fingerprint":"0288dfd38271275a4501f995958711578f44ec13342408b0554241027528cad0","score":1546.235576890829,"score_display":"1546","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_f3a928c2dc4d6711d402db03","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f9fea0954ce2f71ebd697d9e006556ac67b12d4b53ee7189c574ad6fb2815c0c","measurement_key":"ee78dceefb6110fbb41f413072d7452d88832dcbd59e0018a001ff331a480a11","metric":"accuracy","protocol_fingerprint":"e220d5173b7f9c3f85bf1d864cf45f1646f627d8293a8c535d4b9696d26b25d4","run_fingerprint":"3d3a1e1e6ffec140ec9224c823e07d03446e5c57b70da45d60a7a596c1547301","score":77.95,"score_display":"78.0","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_f3a928c2dc4d6711d402db03","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"anthropic/claude-opus-4-6","model_name":"Claude Opus 4.6","parameter_count_active":null,"parameter_count_total":null,"provider":"Anthropic","selection_rank":36,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"eb8c37b674b6160674e3c38dcee6d23382313c0172324a97f0855ecbc2f8850b","measurement_key":"6cf63bdc4292dd3f9c7fc67dee690c008177116a1bfa2e248518167872e88664","metric":"performance_rating","protocol_fingerprint":"bc779e3326d0bf2798439e12ee5b09564e180b02c37dd637e5d73d8d1578620f","run_fingerprint":"0ceb3afeb1a724c9eaf1af61a09744d917c47879f52fa3559be12810ff1a9b45","score":1160.6,"score_display":"1160.60","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":12,"at":"2026-10-19T22:24:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"707804e227dbbac6fece776b3c3e76d75d4ba20b612b89e2590172b82fa980d7","measurement_key":"5c71ec45b346a7e5ed83584d6f131d00eead72a5cd64bdbc8e108abccbabfc9e","metric":"pass_at_1","protocol_fingerprint":"fe4e4e4739bce6a15ce7acd0f662b9c155d0480a074e85d6b6ecf6494498998f","run_fingerprint":"e44ff48b2657a35cb5a46f08140576912d683a64b6791f3be75ab848a622f4b2","score":35.1,"score_display":"35.1","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3ad665509e47df167de108cf","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"59fcb9caba86eb06169d5f4e374f27d6c2867ba5a60499d7108e48329a7ef6ab","measurement_key":"914b1d5abed464dd696b1bc9b39d770834e379420b52680bdff18832a5fc540b","metric":"pass_at_2_accuracy","protocol_fingerprint":"cc2abe7a87614a9ab147026b1341186e1362cd461e7cafc629916f4dc8517201","run_fingerprint":"300ae4d8df78d5ab7193c769903d5713a81eef3680a0cf122ec94a0abab646e7","score":98.0,"score_display":"98.0","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fbb279d340e3a9059784a4f6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a05ff273772ad665615f3f3ecc6115a6fd716ec51391b25a8581520082caabf4","measurement_key":"334396af2b9c38999b7987de815ac149d2d6be27084678243d2ccbda651e4f8d","metric":"accuracy","protocol_fingerprint":"b51bdc08410f3edb3900c1005f74a21aa049ee81af67c033f943bc9ea06023e3","run_fingerprint":"bb4071c7f5d7c5b3658854d5e63d4aa94083ebcb447ab6aae206a9a9a65c53d6","score":77.08,"score_display":"77","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_124badaa245c24f82cccc0ed","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4ee1f9d079117d3e79e59f7059c688f3ef808123b82b1c6c3cd0efe274e4d69c","measurement_key":"6c24f45307a29be962935df4c39df9f62180688063fffd4bd6e60953e57eaadf","metric":"ips_score","protocol_fingerprint":"6f94dfc35f929e177e9f9b1c5b6e04eff77cbbd32e74cced6e05c47a5e5a97ad","run_fingerprint":"5652716c16ca782b6b6cefe47a26774290cd3bf2f3b793ac18c9297645d49fbe","score":-0.044514063835776815,"score_display":"-0.0445","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_71d78988738e81ae5ae5bd43","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6865f561b2469c25c63d3509323dc1493d51534c7ec01b2b25da03561a239e38","measurement_key":"f6fbc0bba4ad3227fe00b566b5265b7bc998906504278d048b537b6cddb4fc75","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"a5812a0fb4c9fa1077779624ac8fc0d13b94f55d673c7e177f547d920c488e4f","score":1486.8999611035829,"score_display":"1487","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fb779cfb20c726fd0ba130d3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:34:13.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e7ba7fb66294642cd726753e9ffcef1b3ff7e8c7a8ef563f760368ca5e529019","measurement_key":"ffc590bf7c6c19faabe9220e3f59ee0d0466efae8f21aa04051c140279ce4577","metric":"mean_score","protocol_fingerprint":"5a0cc8fa1189cb15473e5128726cd2235a11a28372026a0043df6363f456f2bd","run_fingerprint":"ff3c986532d543608788fcba39c1b8421576cbc7670f69ed465dcc673fc40d2b","score":51.0,"score_display":"51.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"00f43ac831113f91c6107180288ca9ddb0a6cf0337f7c719ce2954797cec9460","measurement_key":"acd2e0f0d7fb85a2d3002f4fcec6803202d5eb614179712a2157484318861257","metric":"accuracy","protocol_fingerprint":"e377e43859b258566b6306e15c3deffa6499eee502e08df18f4859efc44d459c","run_fingerprint":"ef0696564ed519765a364150a449ef400611f0825930c26ad116b79ba690c788","score":17.714286,"score_display":"17.7","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8bf7a013a6ba02a14d73d95c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"24531e87c0072f7ff251aad47f74d4c8a8d1d9817f4fa9ec9a809bf051d0107b","measurement_key":"c743f8b6f2659e14b0faafd2963762c099d38eb270286d7140f1649f0da5000e","metric":"pass_at_1","protocol_fingerprint":"2091ed8cc90c49695eccd5e5a9623bb42511a74e8bdc6eda0bbd3d1d5fcb0f69","run_fingerprint":"856701cddec8a0a373d524fdfea4bece9abb2064d37b7c6cef5f69d0b5645322","score":11.725663716814159,"score_display":"11.7","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"322fb65af20b1d26c23a083126c7bbed119a0f9df548fc4f666560c0823f04c1","measurement_key":"259fae698714aeb2e2c6800f9450fcab465081d9016332d37e27059a5e6a54b6","metric":"eci","protocol_fingerprint":"b62aa23688286d42500a61eabe9d164440492fa42b5ab71a5c184744ec6decbd","run_fingerprint":"4961f22970f953549d59270955894cdb4bd5143164ff8495a70e6b5334d5803b","score":155.24,"score_display":"155.24","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_77bb122ce308b85a06f0e2bd","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":142,"at":"2026-06-11T23:35:57.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b67c74d65e41a0617ff657060382a2ab6567db832842d7a978e5fae91889e360","measurement_key":"79db974c4a9a917769fd88176836c95a738937fe218f82e53167374331f83d3e","metric":"mean_score","protocol_fingerprint":"1d7ed5f466056f5a6721a1fbc62165c689ab91d37b31c4cf255aff8f823bcdc4","run_fingerprint":"13e7bf4931eadbf0eb78cc869e4825682ca4505ab096e335e9bebabf8d1656c0","score":59.64912280701754,"score_display":"59.6","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_87c06704555ddcf190611c15","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":142,"at":"2026-06-11T23:35:57.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"be4fd80f5d20f319ec82c7f462bb8c8562c0d8c7e563da28f2fe9c2c97348426","measurement_key":"4179423b9e2cf1627d1ce5bbfea80257950bad226f4db0888f2b0faced71677b","metric":"mean_score","protocol_fingerprint":"b2443e68eed4f08bf6e45e23dd0ebd1e0e724a61ee6a77c71bbc36ffa584d871","run_fingerprint":"6b9cd7b9eee50b02a7a343440113ce3c5c701a39eb0f701d5185d473bb3044bf","score":26.82926829268293,"score_display":"26.8","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_5baafa5d62b0d42201016d96","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"40b5c228d92595657767a8766f46be6e53eff48a42f3638013be7f5eda772096","measurement_key":"2f48024110524964daa7660f85f86e8625cf43c0301f1782403b74fa0a184060","metric":"elo","protocol_fingerprint":"fb609b4a1cecd9a14192ad6c2e961133f3c72b8c9825dfd3c68a77934bbbd90a","run_fingerprint":"dd714c184a8d3a1550ca5c38aee8e5e7aad9c898331faab26150cbae5d836697","score":798.88,"score_display":"799","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8bf7a013a6ba02a14d73d95c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c7de7f95a40f5d4ae7c59a6ec02b176e25af64185d451ff86e7b76ea472cfae4","measurement_key":"1fb068e89427175818eeb7b815494dfacb41191b7fa9cfe3a0ed9f8f69eae179","metric":"accuracy","protocol_fingerprint":"b61d787ce49587fefd9a3b8d192062edcee44f19c95db74b4d064a90f17152e9","run_fingerprint":"ec8a376b44833c24503fe6ff5e0ac258a7263a1b62dcde6ff8509ecdb9f6dbc1","score":95.454,"score_display":"95.45","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gso":{"benchmark_release_id":"release_176f07ea4e9e0b8dfeede990","benchmark_version":"GSO current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":237,"at":"2026-03-09","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"ce1aebccb160f20d620875cf6ce7c7d2aaf50f2d749b143408dc53aa27513a2a","measurement_key":"67b79d27184908c3e09d32008946cf3282ac9574c0b0a64a6182489e4443e5e6","metric":"opt_at_1","protocol_fingerprint":"b135f4b467d586011ba96e921074bd22ba5666ca1223d94e18542068d02118ae","run_fingerprint":"dccf6e263b7a7af27c0f35ed2c2713f9bba1de8232048c1ac2ce1e3d367946a9","score":22.55,"score_display":"22.6","source":{"id":"epoch-gso","name":"Epoch AI mirror · GSO","url":"https://epoch.ai/benchmarks/gso"},"source_authority_tier":"B","split_or_window":"official-set-opt-at-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_73862c6e38001c572af5526a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"hle":{"benchmark_release_id":"release_8817af9d9a0235bce0826e22","benchmark_version":"HLE finalized 2,500 · Scale protocol 2025-04-03","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":204,"at":"2026-04-10T15:51:06Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"253883d2d328a9cdf387228a73feabd75beace3b3e58acd6ba1e1db06a81b900","measurement_key":"d140816110cc03460cceaffb08ce0c0e8418afcc75e8c754961bee337cc91901","metric":"accuracy","protocol_fingerprint":"a31ca2f84947525930e177f3d560f1c550f239837f133d177fa5a42290dd09e2","run_fingerprint":"0b57a226100a827c683d114706544370a71ea5a50643cfe4bbc3f0710b051238","score":46.44,"score_display":"46.44","source":{"id":"scale-hle","name":"Scale AI Labs · Humanity's Last Exam Full","url":"https://labs.scale.com/leaderboard/humanitys_last_exam"},"source_authority_tier":"A+","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2f7d80832cc3c4f491dfb14dc8b778153952ef475da81d5fb4296a0c7f842d8b","measurement_key":"e6af1861a7b2290e72742d3b41effb8053604f0d510dfeb496cd8fd862e35411","metric":"accuracy","protocol_fingerprint":"c2ccdcea67309602be1cf557cd4582a5379241063ff487f6c4acd6a9afe5f745","run_fingerprint":"a0d9e721394552aada91bff32714f5d04f46c68c51b297ee9eba619bd800c767","score":47.034291,"score_display":"47.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8bf7a013a6ba02a14d73d95c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T19:24:33Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"54b1f67f6b9c651a55ee1ee80fa99e361d0dc4e686b793fe5d42518499f8ee30","measurement_key":"c69d418cb2642bb3438b97fccfc8f2112cfd917073e0c785d542cf727c1fb8bc","metric":"score","protocol_fingerprint":"ff4191ac5fe3f4273a1ab1bf7bc5ed19a3b0912bfa63dc9c21c9f1604b16d17d","run_fingerprint":"6eefca776f67bc253e703c84dfa92dc169ab5410f69a0b4337d1e8fe259801fc","score":51.833,"score_display":"51.8","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ef02afb260f08014c0cdd896d1cd6d6af00ff63e878ec2435d18303040be0b96","measurement_key":"2c0c80f739c0368da6370fdc33d6c3aed8ef082cd507c245432e6456c5e56a12","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"bda3a61451750480c756614c6aeb0f5488f02cf7dfb5267c5043a54fc4c7744c","score":76.95184523809523,"score_display":"76.95","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ac927f40690439bb8d8b5b7961b89f21a6bddfda67645568f545530254fe5760","measurement_key":"e14c4dc623e16f9d499a43d2d693a69405557d19d871882aa83c7e535046b488","metric":"pass_at_1","protocol_fingerprint":"6ccf48bb6200d6f017bd2d2ff0f6ce5508368543dc925f86971811b23a95f134","run_fingerprint":"64ea3bf4bcd060d82f94ab733b2fea4c3ee24df38397300f8152966062811fd2","score":88.485,"score_display":"88.5","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":341,"at":"2025-11-24T18:59:59Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"06bcaa75b4a1340519d3a7cc9c363bcea2cdbaf1b36dc82c4de598c8c5f4527a","measurement_key":"9d9536245630a69fe993cf37afee203e8c966d3466e1acb2b5a72605d6850709","metric":"pass_rate","protocol_fingerprint":"be8f2c59e5a7bebcb8c831feada2d1cc11f3a9978fc218c790e316bbde3dbd3c","run_fingerprint":"abad1c7d8996b11c4bfa9c306055056a9a7e9d153966eb753553f3f19a5f5b07","score":78.2,"score_display":"78.2","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":82,"at":"2026-08-10T16:12:46.343Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"418eba716f67e46c17fc0baf37667b96ddcd73e52fd6563ead81220ffa742042","measurement_key":"f511ce1e7944823b7a69ce1c03b63316b16bd6f702cac7d77399994132282c1f","metric":"mean_score","protocol_fingerprint":"4060ee56d737012bf0bdb88584e8d4acdfa2d0d138dc49898229b803c43191ea","run_fingerprint":"476606e7d1c7d22e670da3783dd7028d922780e59ce52f86c800b3da64aba0a1","score":8.888888888888888,"score_display":"8.9","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"71c2d40054297b35aa09639109c71fa78dad29ab773f0848ab85f8d919864c66","measurement_key":"c10984c311e233e50852400e511a520e1ad659e79f0da478d9c778995eabb864","metric":"accuracy","protocol_fingerprint":"f61eb6a345f8238c11dfc6f1d56cdbc323a4376064207a4723ccaecafcc1b8ef","run_fingerprint":"0b66f5f4f99e7badebb1e5f3cabbd1959c93fa7dc2fba067dede1169a5518be3","score":90.987,"score_display":"91.0","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"aa5b74a3f3c13307dd4ba3ce50efb73383a2f8f1955e8c99681550f4250d846f","measurement_key":"12afe819757307975fed82e331edaf214583670c65090439d645c5e7a601e6ce","metric":"accuracy","protocol_fingerprint":"2b0bebc32c45446e79f049e96c754071a130f54318481baf283cb3fff8391b99","run_fingerprint":"8a0b4d8a48b849935fd9c59e4a829dc248888587cb6efd2b62f9208b14faa4ad","score":88.208,"score_display":"88.2","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-06T23:59:11.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a8a78549c58fa3f3531cf28e78919807409f5bc933ff9642fd519bd94097142d","measurement_key":"6405e3c02e5423aa1e53ee870c45fd20d0383983446d3c23d4f82c89c3d8e9a5","metric":"mean_score","protocol_fingerprint":"3829c5d77dce1f2b54d16d58262aa94aa7a4b31971c5e2b75494fe3c424c3f4e","run_fingerprint":"31842463221a1ac1961fc7cb477e8d41d2128fba686203011147dca1a88b256a","score":95.55555555555556,"score_display":"95.6","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"97b1e9e5172321a118c63a752c6f47a5af5d57864f03896ac407c7a602a490a1","measurement_key":"390e99e81f6c6b10c47588f84fef6878b83321808725a40f40243f9ee67c0688","metric":"fully_resolved_rate","protocol_fingerprint":"6c36c13e3d5f67c1ec660554f0f7faaae00eb46d2441ee4e5223b681b89bb60c","run_fingerprint":"0e25fe3bf49e38ece61a92656a169b30bf970db3c80fe7681152edfc973b51fb","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"764eb8587a0612ec471ebe4250efaf5e8bd11df29a57e79da578a9a07a288ddd","measurement_key":"190b2d96fceab0ceb7c7166ee36adb9b1af6e4889234a5713e0a86622622e903","metric":"subproblem_accuracy","protocol_fingerprint":"e19ec468c2a5d484361cdde2c5ae2d160dfd77b7b5b9c540459be845a530fd7a","run_fingerprint":"fb7c0a683c8fe59f79cb4ac183565bc42a8a9e77fcb1f888f348d08ef8c4004c","score":58.6805555555556,"score_display":"58.7","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b7b3ebda2c95fe4a3c175a73","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7c6d36fc5dee8f9b3b033be17cd95b3ecacd783ac5050dc28985e812c3ca6821","measurement_key":"f04b3e4708916ad655cfbc6d0530525c479382d2e7523836cd01568e8893e8cc","metric":"accuracy_avg_at_5","protocol_fingerprint":"df2016c95911d075da9dcb44503a38e4051fe0cd9bfc78ecb819c4b5c28303cf","run_fingerprint":"13e48fb89b5acde4332a32d5a56e9b45b5d75281a3d2766f4e0c7b2a2948f27c","score":79.6,"score_display":"79.6","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ff8f9f6ebdbd510dd6741832","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":82,"at":"2026-08-10T21:35:39.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dfac9feb4d38caa47936a08f1190b23baa02652c83f780bacebcb7b52b9f0554","measurement_key":"f18d1ab7364f09bc4891462b6c115b7b09863578ba184432e52767fcc59f7c46","metric":"accuracy","protocol_fingerprint":"6ec618647aae19d98a2e6a010349940ff6e286be1c872a82002ffffe0cac6a6b","run_fingerprint":"93dd795d91b3d633faab06b4aaf2ae201fb20f98f050482a8190b34524bc945f","score":73.5,"score_display":"73.5","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"skillsbench":{"benchmark_release_id":"release_093b45b8b752b3f08534f6ee","benchmark_version":"v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":138,"at":"2026-06-16","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b8796af64635661398b904d63b66723dc1024b861c50a18b65ac29e8056a40a5","measurement_key":"c0a06d3c3bdc859c1040bba5bb317b7bf10deff62b978d572c633a9c8f440d76","metric":"pass_rate","protocol_fingerprint":"b364c19f09c3235a2849dcf46f5f7497a801c57e4a3db1ecf5efd428de0c8418","run_fingerprint":"cd788dad355a4a048591bb5e84b111298c20de68aefde7d8dae02cb0ae260e9c","score":60.8,"score_display":"60.8","source":{"id":"skillsbench","name":"SkillsBench v1.1","url":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json"},"source_authority_tier":"A","split_or_window":"official-87-tasks-with-skills","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_522565efd30b538ee4ac5d42","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6ddafbc392a2ff2291d0b73ec9aac13471ad50a23566dd8dee6c1524fd63adc4","measurement_key":"98ddf886a712388944148f8a14a64f298337a50fb2cfbe9538959036bb04d072","metric":"fully_solved_rate","protocol_fingerprint":"6682a12127eaca1f8518b02f5a574ca9b00531ccadf708490f448d4c9560155e","run_fingerprint":"cb048da02183c6d8f0044b39235b07616f97ea4aa91c0f5b427daf0c8d4f586b","score":0.0,"score_display":"0.0","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4e427e30b1a9b19cb854a137f9e0acedb80fb4c6907c1f40a3fc3a91b15e1503","measurement_key":"69f1de1e5e274e402730e6cb9cb78f68db1f7efb7fedd716157b7fa4a7120687","metric":"resolved_rate","protocol_fingerprint":"2a4f62aa36b6f99771eb16c33e2fd52bdf47ba7b3da8c214ff868379d2fbe719","run_fingerprint":"7ba58ea4d68df8e3e1f21cff5f1cff57c41d8ee2dc22ec84f84784a5a9af3f50","score":78.8,"score_display":"78.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4e427e30b1a9b19cb854a137f9e0acedb80fb4c6907c1f40a3fc3a91b15e1503","measurement_key":"69f1de1e5e274e402730e6cb9cb78f68db1f7efb7fedd716157b7fa4a7120687","metric":"resolved_rate","protocol_fingerprint":"2a4f62aa36b6f99771eb16c33e2fd52bdf47ba7b3da8c214ff868379d2fbe719","reporting_origin":"organizer","run_fingerprint":"7ba58ea4d68df8e3e1f21cff5f1cff57c41d8ee2dc22ec84f84784a5a9af3f50","score":78.8,"score_display":"78.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_72d764965dd7baf34f983249","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f09c57a8a0af2f2cc0bbd086c5d7f44b8cf80d83d1d76613b8b6364cb86926a2","measurement_key":"08b6eb22dc5407a31ebf0f0b61c76813dbebea76410cd653249a762522034889","metric":"resolved_rate","protocol_fingerprint":"264a1b30ff55d0e372595d202bedae349375f44074f5a61627eca3e3dd7d29e6","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-03-01/2026-05-15":{"benchmark_release_id":"release_72d764965dd7baf34f983249","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f09c57a8a0af2f2cc0bbd086c5d7f44b8cf80d83d1d76613b8b6364cb86926a2","measurement_key":"08b6eb22dc5407a31ebf0f0b61c76813dbebea76410cd653249a762522034889","metric":"resolved_rate","protocol_fingerprint":"264a1b30ff55d0e372595d202bedae349375f44074f5a61627eca3e3dd7d29e6","run_fingerprint":"564af9ae9f84ba108ecbfca44c385f8016673f5283ddd1a26a20acf87b010202","score":51.0909090909091,"score_display":"51.09","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-03-01/2026-05-15","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2f6483fa19b9e55f4f65fa80","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"564af9ae9f84ba108ecbfca44c385f8016673f5283ddd1a26a20acf87b010202","score":51.0909090909091,"score_display":"51.09","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-03-01/2026-05-15","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2f6483fa19b9e55f4f65fa80","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":180,"at":"2026-05-05","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"070142ff00f7d669c7037fcd12d788543c794206ecfbdee96c63ea7b068fd90c","measurement_key":"76189134419f983a61e8a2d1cbd308b25dd1f11dc88228f12329162a734223ef","metric":"pass_1","protocol_fingerprint":"cc2b5f2e843b4d0088ddb39baa3601946a893dd4972691552d040c8ddbfcbdb9","run_fingerprint":"5705135e7e214fb580ffab2117b7d06653bb4b7384095c135e414adc6bcc559d","score":26.03,"score_display":"26.0","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3d0e6b79a64e3df6f0fe4abf0db1496e8f51a473a61f190812f580df2219d7c4","measurement_key":"c3020557de70eb4a904eb8ecbdce608e108db02bfd8036452485bbcb1336aca6","metric":"pass_at_1","protocol_fingerprint":"81168e94ccc34b0338a17620240d815652317bdde42f8682ad45a7b9e35df5da","run_fingerprint":"46b4869dc80b84fbb8c0430435a8fc8767700d501f8887ed4aff5fb0b004697d","score":21.443299,"score_display":"21.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8bf7a013a6ba02a14d73d95c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3a18a26e4632cc606b646dd510e64b4ece6ead7ce2345dcdc0488a4c1bd9022a","measurement_key":"0a71a9204289fbde085fb033eddf80e540db922dc73cb41476250bd3fdb1fe57","metric":"accuracy","protocol_fingerprint":"59a46fae927a8ba671ab40cf6539bbf614163ed4b81f17aad271f78627b0b1bb","run_fingerprint":"9bd5f17f8f943b05eb0dc3b21d2187edfd58e3bf2c908d81d09a7ee9f8336a77","score":70.787,"score_display":"70.8","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d2a817fbed4e5c86591ef775a2a4ad02a10dfd07c5e4aacd3a39b6a7ac172187","measurement_key":"3b43a37f36fc3bde08a0f53ece8b245ac6912cfd8d7d0843070f3b209a565c9b","metric":"accuracy","protocol_fingerprint":"73c80a52b587e24957ad656ca4b84c5fde628b74f5dca87a57e00177f9d5ae4f","run_fingerprint":"0fdefe70891cb29e05783072e513fcd0a9bcddf2ec57a16421bc79da8a468c5d","score":2.525,"score_display":"2.5","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":5,"at":"2026-10-26T22:05:28Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9debe32a3face03ccb1e208278f66e81dd16864770828525ba0c5c14ed9f11b7","measurement_key":"a971a2d7bf24baec39ff7f0ac692635eb36df039b06c2bff66084ea12033d27c","metric":"accuracy","protocol_fingerprint":"0c9950239c54bc8946cf37a8431907d28f566bdae18d7b250476128e7b838fdc","run_fingerprint":"5f5cbc0486144d76d1864d11946e34af8a3ba69ddf6677d51b7ee3cb5e25921b","score":1.429,"score_display":"1.4","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"17a77adbf1b24556ecd1d78eafd3d6b095e32cde4fae49ca25c8c05adc1f6f9e","measurement_key":"a4850f2b48408c3c7a3fc19d7159f388d731ec154b3cd37b8742c52f31ca09b2","metric":"mean_final_balance_usd","protocol_fingerprint":"8259756d9448652adb9c8e2ee1fe06f67271648e2f5f364b0f1709d484d02ab4","run_fingerprint":"54cb3c06127e67b09523262c124d6cd130271ed4dd06553cb1668697e10fd161","score":911.2139999999997,"score_display":"911.21","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e91ccba2908d54447036bd3b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4fb3fb10439b02bce962d8ec6042dac0cfc933296f93d149caf9c6c022ad7043","measurement_key":"aa3f07ec5e340f96a589a6d15af90bc29f36cb6fc55cece181602b90c0d09cd8","metric":"score","protocol_fingerprint":"6033a7a00359ed4e825c4bcb86393e9401348b1cf80efccc3e31b93cb181d8c3","run_fingerprint":"0beb942e32fc92aa254f27490702c1edfcfbd1e1c65ab54f932b3edc01b960bf","score":32.034,"score_display":"32.0","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_dd3be8508497fcbd983b0185","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4ecdc3a94a5b81ff0015dd6389aca1f988bc0aadaeb3da38fd59a224be14c053","measurement_key":"5d0ddd2dedd0e96671ed76887fb0fc4b0c2be5c76ea56fc565a96eaeefcad532","metric":"arena_score","protocol_fingerprint":"19a1dc6556160885f4ec8dc4ee56394cf69f60b22134da74591a47349587a662","run_fingerprint":"34cdb2a5610eb7e097837561c5229c3f0f35a3e2e6e7c58487ab680244f8f873","score":1446.6498483953492,"score_display":"1447","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f3c287b85bdf2bddbf2899eb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7fb7aac72716d54c205f47de179ff98395bb89b038a9d9999b4679dcba30946c","measurement_key":"2d385c6cbfb4ff2de9f7145accda0a2f443b3930df10d8ba56ba395b86001921","metric":"accuracy","protocol_fingerprint":"2d55e99abd048ba98d8233abd81925bb13dcd26af11a5c45a211addf5d7e63d1","run_fingerprint":"591741da0aa50b36cff5d925a4458c59efed5e22f424664b01236d81d71a9e57","score":72.07,"score_display":"72.1","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_32dba87df2012b02f4613fb6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"google/gemini-3-1-pro","model_name":"Gemini 3.1 Pro","parameter_count_active":null,"parameter_count_total":null,"provider":"Google","selection_rank":37,"weights_status":"closed"},{"cells":{"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":12,"at":"2026-10-19T22:24:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"93810fb5e60b31f8b64419db95a5854ecfac7670495e6171104a039df73a7b38","measurement_key":"f7588774f35e5c535c424f9f479f4b272ddf300e8eaed6d56e25ce5ad5757e15","metric":"pass_at_1","protocol_fingerprint":"b07d59e3860875786cdcce441391a5f01684b899578f4e5e3abe5ce59f889e02","run_fingerprint":"20d195a45757e4e4eb4fb4c6a4816a76943af125432947f16dc04a659ab9e278","score":45.4,"score_display":"45.4","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6949cf33fc5bd1ec3a3284a7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"15bee127ea2fffc10a2502cf9ba23caf541a0a7f583a5ea21e96c0bdef73323d","measurement_key":"bf6a712a58f443dce844fa83b866502b17274f3277d331891d195904aacf9121","metric":"ips_score","protocol_fingerprint":"66f20e294edf67f19528ae22d5ee44e90cdf0a74c8e17cb02bbebe5939271f73","run_fingerprint":"1b792183515ab5a456f3d109c9d79984fef8bf965f91760c81521695c4d7533a","score":-0.07538020659982388,"score_display":"-0.0754","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5b05861534997157de975f487d06794b181a3a4308eb12999c0d18a7dde62435","measurement_key":"dd9bfd1a1365aac8badacf8d9696abd428c8917c19be6a9053772214cd76542f","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"1bd3f35fbf6c34d8c0d7bad5abf52816cf8046e38bd40dfd12494c7beec4e2b5","score":1492.188040510066,"score_display":"1492","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:05:03.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3e6b4690647bf9f5fff9dd6097504f0b8a216dbce3d3ebd332ca2b9e58cb7dbb","measurement_key":"12942d6d9b5333cb5417bffd7a6c82a563ce61e4ab2bade3203848ad6cdc95af","metric":"mean_score","protocol_fingerprint":"34bd3c2a792cb1d370ccff4e8e6e03902c73685013d0a23a18d99e26214606b8","run_fingerprint":"407a02f6115c0c46d58ec28cccfe80919cc1bbcf4313b3f58c971395014c332c","score":27.0,"score_display":"27.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a418a974072c93df0aa9928f6ae402f4b4dc494c21a09149de79706ad426ad98","measurement_key":"4bdeeee8286024dc28a661c462ba259a989dea656094a65ac7441633c4180a05","metric":"accuracy","protocol_fingerprint":"f1be2f82d6b34791f82dd4f67f3085e36bd1526bd543a0931c438f9fa63a3c5f","run_fingerprint":"0caaa8b181c8f3685dd47ef28e1356db69aed700747aeda739e94cb997b14d1e","score":17.714285714285698,"score_display":"17.7","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e3d8e74aad1585cf832823e02c0f2cbd6e414cda49c90a5544288226891aef24","measurement_key":"c078dd1da5b900f7359a99aa8e7774865e17e0a16efbe56e6a3f15d2edc0ffd1","metric":"pass_at_1","protocol_fingerprint":"28282cf783bafcecd7f7d9d45b49a4ca5f96b889be7c9be1937e83965b47aca2","run_fingerprint":"6f36446b918ecd4442e0c62dccc20ec6009e5cb2005585e6294c340871628c66","score":54.86725663716814,"score_display":"54.9","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"61c347a2790a8a447c95b3031875e9274622e562d7579d390d5abea19d72b5c2","measurement_key":"e84b4f001b18ba37426d0101b97980dc0e71500ffa7516c0e284de197c718425","metric":"eci","protocol_fingerprint":"897ba1cd014dcd819dd68489041b9f035f5cce425258e9ef0e38e65ece4fd970","run_fingerprint":"2e619eff873fc6dc5ade8c5612d40dfc29edfbbe7410ca6031afe94e9598ee18","score":155.2,"score_display":"155.20","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_07d1816d63900bef656c0e24","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"928cb834c592733f51a4a390ac2fd58ec836aff6b33dda038d3e498f703bc66e","measurement_key":"173689e4e7980582588da562d178007cff3b16e66119e3287f40f982d2f93096","metric":"elo","protocol_fingerprint":"370129e05a5ccfbe9a4d83e2cc78db918a46628871d8a9f6ef50b427589db98b","run_fingerprint":"23b91385e6a6c333cac4582fb386731afbed16700bd125683d74f0a79160cd4e","score":1480.04,"score_display":"1480","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_f83cfc2a9e19b8d654d7b58e","benchmark_version":"GPQA Diamond (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bba14c83f57afd2dec0c4e9f72cada6f4aa0cf6bb6487c81182bb4ecb6ed8a25","measurement_key":"b56e828adc009dae4874cbb7f31424a821d00f5c1b37d51c6dc00c44dda19114","metric":"accuracy","protocol_fingerprint":"87f968a546c9523fe5682c528ae62c619eecf75dda377913fd1ef5d1055eeba0","run_fingerprint":"fa240e3bfe3d08d0494982d85de1d7f742ea7b7a4518d5ea86b8cda5c37be6a1","score":90.40404,"score_display":"90.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"diamond-198-zero-shot-5-repeats","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a0ddf2016bc7ab005a5c432bb0d78926457c2711cf944b4b0b4d2a7ae28c9ebf","measurement_key":"f1bedccba0565e57fb166057bb62aca08fbf75fa1da5332490d8f554280ae4c5","metric":"accuracy","protocol_fingerprint":"b9554e2032c7be8036d239d362912f1ce3541c0223e284819304e8efaae5e25a","run_fingerprint":"554e935bd6f3b4fa060b4263f50fecc07f64f16dee7eacda35ac3772edacc6cd","score":45.458758,"score_display":"45.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3eaebadfec04a6437b61d64e3d54aeb4e672973afc1cefef5e23bdd41a6acd95","measurement_key":"a54ce027779087443a0c8ad23612d8b298d93b2ce8ea065a08f74e7a08c9d894","metric":"score","protocol_fingerprint":"bd6f744bd3c5e33dab303062e574b07c9a19d9591f9ec619ca3a7bb0c7cd049e","run_fingerprint":"8449ecd9dce4e2c1b0ec5bd2719f2ad05d183f739d24f9aa261963475f0365c7","score":21.778,"score_display":"21.8","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0aa93282e1af17cddcff8520264c7c79de6271bc70ef28c1a33a4ade657c8a50","measurement_key":"2e9814d416405720638efc2f86435e23a234cd72600c5c13dbde289ce40a4635","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"022137b4eb7ac10ee27397a97b1c44af4f8a81a5be6bddf6d84a62fc861fbba2","score":77.9547738095238,"score_display":"77.95","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1b4186d450816ff4d658ef6d59ea3f38885db8d68eae4d3f77d32ad2fd9f9c62","measurement_key":"f53c9e9c4d2eee46d7d053acaca9e5e18db3e624136d64307abe92c715587bea","metric":"accuracy","protocol_fingerprint":"29fcfe5a022d697f016363a005652aba0cfb4c9cedef845707258e2657b850de","run_fingerprint":"b38e45c85d3e4add28d8ef84b76d48356aeacc355a73767874355308b1036368","score":88.275,"score_display":"88.3","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"48b266ad07f757bf2cff3eeba59baccfc5b08bffacf10e55a661e48c47785ba8","measurement_key":"7a821b8a90014ce2e2f648e7d12d83029baa9dc111166d2202f08116b0968f4a","metric":"accuracy","protocol_fingerprint":"108f7c7932ab215ebec5bd11827b1bda1a54703db7eb9b1ca54d66dba28f97fd","run_fingerprint":"cff51443d433ddc78bb63164c02d0127d81fba05a4ac0e2d0e723b10dd884522","score":86.127,"score_display":"86.1","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"90bdde53e0da7edbee24046dbc3fb007c86c07b750bef0aaf7fd4f10c6d83e02","measurement_key":"edc8da45fdbdaa50c3df8d9083b230799cde0f3a622f0c9b5e60a1530732ebe6","metric":"fully_resolved_rate","protocol_fingerprint":"567326fe8a298690587f810783b49500f521a8f33809ac31d1198a98dfaa6690","run_fingerprint":"57a69771b6d12badbcf334ba56d6374b638299b268f8e9f446c9a9a63af83f0c","score":0.5,"score_display":"0.5","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ac3e14a72e53eeb2470e56db37f5c56f71bb1a6e08bcf3ce3df53a857b5e725e","measurement_key":"c785521d20a062dee3e88440e87eb041aafac0c38778ec84f7ab3b7a7dcb1332","metric":"subproblem_accuracy","protocol_fingerprint":"969fc0db003b7c4854887ab612f2d7c2560c84785d1535ec2b08f7c8bb3da7fd","run_fingerprint":"3d86fd25f7b894489ceab3edff05f505277704e05323259475e0ce4bb0e942ce","score":57.4074074074074,"score_display":"57.4","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"104c2f26af251abd3677f648b7c9cec6bc434ff9b8a6a8cd8fd792e1a9d91f58","measurement_key":"08b5d7f06bb530694798113f2b27b7217b9103d15b4372aa704c0f881712fd1b","metric":"accuracy_avg_at_5","protocol_fingerprint":"84da92f7c5c07b1b3e560be218e49d78ebd66a5ca25cdcb81951f69bbdb448f2","run_fingerprint":"82c0b3e69c46fc148ec9291ee316740a53f7beeba2277aa92407958d3049b2a8","score":74.5,"score_display":"74.5","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_01969cbf5dae3b1269d94614","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:36:49.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f0851812d1d42546731e31e6a0d97940d196dec2592905584db900de801cca19","measurement_key":"8f0575bf4a75bf4e08df7405648b66e48228a5ed1db3bdc3dc118bd57d260153","metric":"accuracy","protocol_fingerprint":"cf5cdcc4c3a70b7351aabe6cbba24f9eca000dac537b1ffcdeb66a58b7031afe","run_fingerprint":"0c2f1e0739e98bae3a2a1ddcbd9cccf6975f56b01a6124dcbe45b837627173b6","score":60.30150753768844,"score_display":"60.3","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"65aca63e7eb0a00a52a0ff19c2d18bc294bf722f569ed2cd230bb9e2bbb32728","measurement_key":"c3904511e2962fc22175f78092410384ad9f6e5c7045c237b0ade1c943b6db43","metric":"fully_solved_rate","protocol_fingerprint":"d70054ca3eefd85179d02ea87d444bef70efc3afc35359f41b937a5fcf69938e","run_fingerprint":"2977bd730a2c1f1a6a53118546eea0fc8c38f8734176a7af07ff68f7f3c5723d","score":0.0,"score_display":"0.0","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"961b85f92c9f7e2f85b7ab757b8d581398c32fbbc7d78fdd2fa99cd6249b6395","measurement_key":"c3030ecd088ea7366ab6ef427afbdfd061230578d648877df3d71b10e15ff732","metric":"resolved_rate","protocol_fingerprint":"a05b09281606b4ab4972d51b72d9530d02afb4017a66cfa2b417cb933abe8878","run_fingerprint":"2b13dee71ed10880fba26a53493de1c7d0419be5a72c128a05f7870d4c99429d","score":86.6,"score_display":"86.6","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"961b85f92c9f7e2f85b7ab757b8d581398c32fbbc7d78fdd2fa99cd6249b6395","measurement_key":"c3030ecd088ea7366ab6ef427afbdfd061230578d648877df3d71b10e15ff732","metric":"resolved_rate","protocol_fingerprint":"a05b09281606b4ab4972d51b72d9530d02afb4017a66cfa2b417cb933abe8878","reporting_origin":"organizer","run_fingerprint":"2b13dee71ed10880fba26a53493de1c7d0419be5a72c128a05f7870d4c99429d","score":86.6,"score_display":"86.6","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7f262b9819e9112dfc0b61121effd17fa9e4ad64a4787d45a784a2cc5cb76c87","measurement_key":"9e935d803e4489b644ec47418690ed80e287ed4d424f43ad4c8d70de24bc9ad0","metric":"pass_at_1","protocol_fingerprint":"60a5c6f1fbabc90023fd5a9c18df1c000d431d1e29a2930a21405eeda84e113f","run_fingerprint":"48b525abb074718ab62c6b1902ed78800280815b08d0ee5028886f67ba4add02","score":34.845361,"score_display":"34.8","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"65cfba9a9f0e55e957b3fc8c1fd145304240ec461d93455b926e8feab197ba50","measurement_key":"e8bcffcfd6779492c70625751b79cc99a227b368a3266427e4b6afdb87af11b5","metric":"accuracy","protocol_fingerprint":"710a0843ce8d4d01d7e65f58c3ebdcab4c378674ce49fcf99cfba53ad4bf89db","run_fingerprint":"d09a08ea556690f157e07eb6f2614881c1bce10bed7d21b1d7ea76daef217139","score":69.663,"score_display":"69.7","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d41bc6ff863adbb5425c82089fb58b03bf432e81bd8d239219f120921eaa42c0","measurement_key":"ed6db109ac30e8eefd7a44a70a22f0ab213681fb5198793c69778575c1e67e04","metric":"accuracy","protocol_fingerprint":"92883ef74af8abf93fdc22edd8361bc0ed1fdc5d5e003f1d09fccdf02ceee695","run_fingerprint":"5bbed6897abb94628222732fe99dbac31f853e9f0d3a26373367029e3e1b706d","score":6.061,"score_display":"6.1","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c16ac1945db665463ebac5e3d3766b28b7d9a265f61032cad8dccde44df0f31c","measurement_key":"cf6a8fefa85e0c8bb17620db540a641307126fe03a07e8ae15e13c64f3dcbb9f","metric":"score","protocol_fingerprint":"067caee6503667936eaaef788d6dc1e1bd09f23e7a74d02c9ec79dd17d1d84f5","run_fingerprint":"d6b37fa31ce2d740db201b8fd0cecc3da9e1f0861d9f753c1a725dbc0be39359","score":79.1,"score_display":"79.1","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"985e598ae83150f6779bec51e2bca1f54790a3f3411bd55a7f7ff9d044fadc53","measurement_key":"23029bf4456a91a5b77ecf57996280fb5af64d8b626f026e6851798f372349a8","metric":"arena_score","protocol_fingerprint":"bfddb5d36dacac6f5c175a6a5a714a48922d75d3caf6d966d8c825edda7352e2","run_fingerprint":"8b7f0331cb926e593003bae6df4606c8992c6b1a53ef831f6d65ed3e879585ab","score":1533.6689783572438,"score_display":"1534","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cb5235d4127530b7322aa96a7823873b9c3e0c8382b0a7cc130d513d900a6897","measurement_key":"84ea376e746d45868d4ede9f67d4a8ce2cdfc064461aa772f530919953e01baa","metric":"accuracy","protocol_fingerprint":"40925098be8d19a7ea155e1d80d593ef09345a8b8ceec661dc3c16dd00655b43","run_fingerprint":"e95b9b0cbca4e68a6fcc162391bdf5ecd9f197f57c31727f667332ebf211d9c3","score":60.3,"score_display":"60.3","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_502229b22892e7bba82f7d86","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"meta/muse-spark-1-2","model_name":"Muse Spark 1.2","parameter_count_active":null,"parameter_count_total":null,"provider":"Meta","selection_rank":38,"weights_status":"closed"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b9fbd3fe77b021891d4eec2b4f629d8a8f4b6abdfa6126d31064b80b56331051","measurement_key":"4d3111375c836961501bef13ff093cdfee8ecba97f06c7b0b9fdcdeb36a806de","metric":"index_score","protocol_fingerprint":"2d9d2214c3d6f813be698696200aa143e893347e9c02ab7fc79b26278a16fe62","run_fingerprint":"2d61a00c4e1041e76ee7ade9627ed829213b2f5239339a41d6763b80ab498add","score":24.681587,"score_display":"24.7","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_ae2b0889cadd601ae1049f93","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":10,"at":"2026-10-21T22:23:16Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3376ba48e508af44878ec9a45ddf8a961385e0ae7c1f92b948512f64b1cce29f","measurement_key":"28006cf023aa0a9fe28e58b73fff8ef955b928429c8fc2387c4db884a1fa439a","metric":"accuracy","protocol_fingerprint":"2dc7d3cd93c2288c1e025b143d853046083ac506f18d333af907400bb534d896","run_fingerprint":"2430566af4b3bc27706339c8071b027b4a2c0823eac198f3e140506cb2ac8a29","score":57.49999999999999,"score_display":"57","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_ae2b0889cadd601ae1049f93","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":16,"at":"2026-10-15T22:20:56Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"549706da91d516ac8e0cc119451f2c3a8b6761115a3d7add91f00d5633e39801","measurement_key":"e148f8d403c2624251d3a8f1a9fb6edfb1ca896fbf76ae12e9481dcd94eabcd6","metric":"accuracy","protocol_fingerprint":"a470794991406c565e1aee3510a0242e5dcdcb7aa7c2c3630fd6fa353504908f","run_fingerprint":"fd7147f6a7783384f27b7bbd89af2187ca2e687fb9ab73938d4f0d6e45d9dca7","score":14.857143,"score_display":"14.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_ae2b0889cadd601ae1049f93","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cfbcb2f1e080c1ec4b05a138f16aee2e05bfe8c085cbda16b19f96e62ee10b3b","measurement_key":"00a51f5fe547fb051ecc27fb63261cb82ba201b38383ad665290f1f32c0cdb72","metric":"eci","protocol_fingerprint":"5badc9ecd93bd2ac2560d010034e9de572b9eec872420d4878ceb2be59d7b35f","run_fingerprint":"51ce3f4672be70cabecbb94f92ae0ae485304dcb4c1c494d83e9bf8cf0423673","score":155.05,"score_display":"155.05","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9178b0a2d0e284b4c757f3e1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":16,"at":"2026-10-15T22:20:56Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c8081ddd4ffdde6a6f95ce1249d506ef6495a1075616c20dbc4fda9917416b41","measurement_key":"2b4292181e580b4ecc4364a6f71e555b1349b04bf242de591c38b68d903c14cf","metric":"elo","protocol_fingerprint":"ea180ff663f5ccf2268ccf0375d2e297501595050a9c5bf3a2e4054aa9aa34d6","run_fingerprint":"2fd20ce0ea2054a5e56716fc42398ec7921b1ac2a8f9cc01b52727eaee4df795","score":1401.12,"score_display":"1401","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_ae2b0889cadd601ae1049f93","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_f83cfc2a9e19b8d654d7b58e","benchmark_version":"GPQA Diamond (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":16,"at":"2026-10-15T22:20:56Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7d6d620af504f71fe589a413fa7c8df838b4be34e97315f0ba89df02a2ffe921","measurement_key":"86883945b5f3dcac8d6726b816cf58446504dc071c0439dac356b1f96b70da2b","metric":"accuracy","protocol_fingerprint":"02945c406adec6e1444f7b02c388dbbe69ed29a02bdd52ddcdf480b63a43f5c3","run_fingerprint":"e954f4c3438a009b34918e9413ff24f6fc22e9e2b8fceb4cdde4fdf814039873","score":88.989899,"score_display":"89.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"diamond-198-zero-shot-5-repeats","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_ae2b0889cadd601ae1049f93","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":16,"at":"2026-10-15T22:20:56Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1aaafae53b446574530c0ad9989072441a049f079754414f0fc00ab181e1d898","measurement_key":"a94e4efe63805b77c2006af543cd98372de4f573a397dcba3e2b97f016c6c44e","metric":"accuracy","protocol_fingerprint":"8e78c908cdfe6241a6af1211b300c2684969f5ab8db4e3024a351fe70c7e69d8","run_fingerprint":"ea6fdd5e934986c960ca595c4f7880e798321e9681841b2b1044b47b850e9d79","score":43.883225,"score_display":"43.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_ae2b0889cadd601ae1049f93","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":16,"at":"2026-10-15T22:20:56Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"75d5d412c5864c1876dd07b476a319dbadb0d3c73b11d80cd68d3a13d9062725","measurement_key":"6f280932f19369927e9090917b380887467e54d06dd8ad949303e9690844dbd4","metric":"accuracy","protocol_fingerprint":"904bf5b0dd6c8ba039f5ed7f92a770f585817f587d0143ba195f70006316a4b1","run_fingerprint":"4ff82e59f0a4efb4684261f27d2e46401f288f6bf17e3aaa2a57a6b4f9986f4d","score":80.924855,"score_display":"80.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_ae2b0889cadd601ae1049f93","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_de40c66bd40a7b5483b40f9a","benchmark_version":"SciCode v1.0.1 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":16,"at":"2026-10-15T22:20:56Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ec258ed81fa6995852519b76d26f6aa15e714daf6507d46ad6ac97c44e4fc3e2","measurement_key":"b1926435e26dbccd35254dad8891571bb2b78167ba9b745f3431ce8b35aaaad4","metric":"subproblem_accuracy","protocol_fingerprint":"c8da256b9b53f1d1a24afcb996406071609da22730ac8cb061c9f886c06a2a73","run_fingerprint":"81bda2856fcc90761ecd6c3e05a405e0f5427ccd168dd8f38e52a9b65ea83d81","score":58.449074,"score_display":"58.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_ae2b0889cadd601ae1049f93","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-pro-v2":{"benchmark_release_id":"release_d9b58bd286ce316ccf0ed891","benchmark_version":"Scale SWE-Bench Pro V2 public leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":15,"at":"2026-10-16T19:17:34Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fa275ebad5e53d5f160301bbe946a2b6e6b0ff7b9ac922ea3fafbe39b96e6b5b","measurement_key":"7f884c0910d06851515b4aa58d559cb254cc67f4308ac1cbdf8af8e7660467a5","metric":"resolved_rate","protocol_fingerprint":"4a2add125f344082322bddc1575e56d3d9e6b86eed4aa01307a902c52f17370a","run_fingerprint":"fdba10e1d0c5f1656784a75242522f1bef9454a712e1028f84794e0834759565","score":95.02,"score_display":"95.0","source":{"id":"scale-swe-bench-pro-v2","name":"Scale AI Labs · SWE-bench Pro V2","url":"https://labs.scale.com/leaderboard/swe_bench_pro_public_v2"},"source_authority_tier":"A+","split_or_window":"public-v2-642","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_ae2b0889cadd601ae1049f93","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_c53c830678318dc1763793c8","benchmark_version":"Terminal-Bench 2.1 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:17Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9af7042cf7973d5692bf8ecb6b93957925aa9a442c3e0a949a18f9f7b6a6f71b","measurement_key":"723149382137fe4edab2d6a9d38b5fc27bf19003d6e313f9708c904de9c67e2c","metric":"pass_at_1","protocol_fingerprint":"28b9626d77409af07f48a97bda59053fc96928ac1133a83464d1e96863fb7ca8","run_fingerprint":"820522ae6eef6bd7e97954e5a0a23c4b432da4af781fe08b8c27af2150d86943","score":76.404494,"score_display":"76.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"terminus-2-89-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_ae2b0889cadd601ae1049f93","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"90fc7e536f90ef1d799b3bfaaeef13d18a0007d7c9bc2672383134266c27073e","measurement_key":"34cc25c22ab95b010746738ec5979a2eb09aa23a105ed3cbfd43c898b2ddd348","metric":"accuracy","protocol_fingerprint":"2b464bd20d79c0d0a2f19f2cef2f0b3b2ea518802fbff3c9e8bb485a6340ed56","run_fingerprint":"ca335c6282ef2598fd276db5fc9ed2b11895e66609559006df8396e24cb2892e","score":6.566,"score_display":"6.6","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_ae2b0889cadd601ae1049f93","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":15,"at":"2026-10-16T22:25:04Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c223fd7d2f09dbebd6d3fbd50dbf483c4ea73e244be385eac8a8fd763215842e","measurement_key":"2bbe593b17d66418b60c78c473d86ee38354761a85452403dcac6b3437d74d78","metric":"score","protocol_fingerprint":"b485a060cfee9de412985e7facaafce4f190c2e4b4a248ba16acc26ef5472f13","run_fingerprint":"9caf2221f1b021f9c31a199a4c71f17fe3a9763f8ec933e4a692737d15b3d497","score":76.187,"score_display":"76.2","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_ae2b0889cadd601ae1049f93","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"76c2002e70f8af30527510138d38d9ffc8a2cd345abc7f302cbaab90e726d8e8","measurement_key":"5a81071e7d6898e020a1c66499bb4191a4e306b074dc04e3068537e6ed885bb8","metric":"arena_score","protocol_fingerprint":"10722bd31ad4a3fff0e41aec9037abe13451c8cfcb9dc04feddd0439d29e0259","run_fingerprint":"25d1a1b91535e325bd3f41af1c2e64c0c8cceec493a3415e4912f383076d6344","score":1526.2373165722156,"score_display":"1526","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_08650aebe41ef808d3d674e8","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"meta/muse-spark-open","model_name":"Muse Spark open","parameter_count_active":null,"parameter_count_total":null,"provider":"Meta","selection_rank":39,"weights_status":"unknown"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"64258336583c0e15d6f0766488b5a1cc54defde59e2ffdbf5d1ddf2250276734","measurement_key":"5f9860b58ba400e39abfd7f9ddc87106f069b2bc3cf0620f7cbc73627418bf55","metric":"performance_rating","protocol_fingerprint":"ff7c4e8d844244d6df0ad98ead4952ab0d5bf0cd9dd1e645c58dab28adfee8d8","run_fingerprint":"7d6a3e3dc94a256f5d3ad7546c2970637f7a651ef7d1a0ad839b5cb097571a94","score":911.02,"score_display":"911.02","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c95d355c6880d9e12ceb443a8f77347500c8d0244f94965eddc0131c5f325a49","measurement_key":"6f934ff222109366aee0a6b2a5cd4d68ea47ec1efdbb920ae724d963352a934e","metric":"pass_at_1","protocol_fingerprint":"4476fc4b13aef3a80e395fd04a9a309eaf20f4322b18ff7acbe86126714a050a","run_fingerprint":"900dcf5a435675c7ac49286898781d650c33db0872cbd5d421937bef595cc20a","score":27.500000000000004,"score_display":"27.5","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_97f8426db315c9e742f4bc9d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e53c40e679296217d4b462976a8ab03d700e14f958d12db534d4a9fae666c5ba","measurement_key":"cc44d8d9a761ca83c0589156a58faa7cabda3524b7458218f3cbc8601397573a","metric":"pass_at_2_accuracy","protocol_fingerprint":"3194eb015bdbed7128bfaecdd95ce7a9afe9ccb8aada513b5e6774c14e91a543","run_fingerprint":"5b807803ec428066c222040ae61b3bc1576e4e0d15f2423d47eab044c64c6b6b","score":92.5,"score_display":"92.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0dd4461d31eedfc95e677b60cbba1111f07e770498a04b849e458f30c9b178c7","measurement_key":"e19fde0f543f03adcafe13714ea40271a413cb32b9cb112a59e78862f0e25a62","metric":"accuracy","protocol_fingerprint":"dbe38c082ebd2c37cdc880c1706306279374fbeff0205fdba64e0d763061a9c1","run_fingerprint":"986e07d8e3f525c63994847c40858db2472b4a43024065b5676e0774a70e540a","score":72.08,"score_display":"72","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9d6cf1d0710548e16a13eac07212d2ff95fd040a5352501d310a05b417b8af35","measurement_key":"5dba89c11b4d0c6e8c5d4717d3d0ccda5ef2eeb09b3822b87b448be66659f613","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"cb3888e059bdaa4ae60bb47ac333fedb2f3f23b10f18e7a00c834ccd300308a0","score":1477.6273768777826,"score_display":"1478","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:33:53.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e91ea39c2b330ef314e0d4ff3ff9633b88a7fdfef0e5ad2f84eb878f34a96323","measurement_key":"f22d4df4cea189ead3bc15628e1d2a9ad1a7abb37c0236898c192939e8617fa5","metric":"mean_score","protocol_fingerprint":"d3d9f1de2322e388d7485ed2cca2fb490bda7323295cef7b5f1de2ccd57821b7","run_fingerprint":"9fdd0d389f9c264c2a613a2b33fdee7a5923c65cda035c49e737a0b5ff0ce47a","score":45.0,"score_display":"45.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7697da0109ce2fe06607ece192ceede7e6a35d7c513eeb2122a2e1548b346fc3","measurement_key":"715f6f88d62fbd67387f1525ad70d93f668a0e107feac7eda6bd4bf89216bac0","metric":"accuracy","protocol_fingerprint":"766c1b2908381ba0fb0250e4b074ff1189922b8db55cc8dc5471587266323044","run_fingerprint":"988c5973533a99a0123ef54bc81be6dc340d2c38c61e93c60ef01e6b48a7041f","score":13.1428571428571,"score_display":"13.1","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1b64508ae33f3005a1dfcc82f19a4a06edcd10cd5aad07c7a75af2b592b07ee1","measurement_key":"a418068d37569598b3f8dee90083f2e9f4b1de225df298bffbfe3d62cd34ee5e","metric":"pass_at_1","protocol_fingerprint":"e47ead2f51c572dbfc57ebe743690c269e3b2a60004b56d6c13a0123d91e6db9","run_fingerprint":"35ff8572ac1eeb0e063ed04b1ee19ed55c00e59a9a51fca597972eee7b8986c1","score":36.06194690265487,"score_display":"36.1","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1617d92e9f1377b976075a05e42c098907bef02c919fc6dc8e1514842402e753","measurement_key":"cf9d7515dcfa2e551a119b5f2aa59955ce5523e0faa5bea8d7e00d6f0988121e","metric":"eci","protocol_fingerprint":"8b6b6e08dcbcb2d0e73673fb8d80971b11af2cd9300ecf366870494c77a14a7c","run_fingerprint":"85ba47df5533727e06591750194aa4710862140a663b12b3a1f60c34b3aee3cd","score":155.03,"score_display":"155.03","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d3b2abb9ad25b246a9b715e1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":143,"at":"2026-06-10T17:32:38.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2b2658e74e793576ac7e809c9524683e466eded96b25a7c0c7ba9cc0ee5f4919","measurement_key":"09f52a309cee25d7e705c18aff89460fb341257a86635ef08aec3d55d55bf265","metric":"mean_score","protocol_fingerprint":"daa218ae0b434ce51d940177b4aeb7f1dde4b11fe1e481fe1df08e75d4d6e5b7","run_fingerprint":"1ef1a6ea05794420def5d7e2da39c5953159e8fc20d802ef837817e7ce8efff4","score":62.807017543859644,"score_display":"62.8","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":143,"at":"2026-06-10T17:32:38.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a7c1cadcee572b49b121cb141e325509adcdc9879cb3b3ec3a3e3093f9450564","measurement_key":"3aac684d066f5775d0cf39cfaaec7183075edba758ca6a0d1baaf9eaddaa0960","metric":"mean_score","protocol_fingerprint":"61b9e7719f4d628014c835305095e2f34f2afa822735c4212159bb6315897cbc","run_fingerprint":"b694cfd043a6c8b4585b08fdabee36f46867346dc0f19c361b6bed4d7772ca0f","score":26.82926829268293,"score_display":"26.8","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d9565715e1026bf2de367808a6559e0f463bb2055c550bf01e7be98425849c43","measurement_key":"72a7bab6dededb4907d972b97c64738558a2de328f73423f5d2f6ae57fd2c142","metric":"elo","protocol_fingerprint":"3782b4ff4913ffae588e1473c4fb03ab58a239599887b4d8c34c43b28aaa1bb8","run_fingerprint":"4bbde2a867f5b49ebb7ae62237e9ab094286ac85bee6838bf8b33db109e7f9be","score":1211.55,"score_display":"1212","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6fc4d9737a663634ae2d0a0612e91e720c076499a210b5dfcc0cc273127749a0","measurement_key":"b32413df1c5148eb85822ca0d2c07868b71a1c89944624c7b751bc55f16d90cc","metric":"accuracy","protocol_fingerprint":"304c1cee578e771901d2db02a68e8709b0786b9de8311b3726c1a0d9377bc126","run_fingerprint":"c9a84746b84ee524e51afceb13b0449cf63a06fcf510c65dc26a9f5b76c78e6b","score":92.676,"score_display":"92.68","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_5f3023448c2ae4632fe1a43b","benchmark_version":"reported-runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":166,"at":"2026-05-19","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"797fc2e0417b47624835cb25f38009e532d955528b95007dd153ca50a8b0007a","measurement_key":"baa778c7a78c8563cfcf08682f14a6699c55fba7f06fee46452352f9d8d64b28","metric":"accuracy","protocol_fingerprint":"f1c14751cb135ea7742188a867c1ba4dd19b3da37521600b924d9d938272dc0a","run_fingerprint":"a8b4ed847af0e912a3f44e915ab3525871c03bfee7594d7dd8b12ce74f152abc","score":42.5,"score_display":"42.5","source":{"id":"evals-report-hle","name":"evals.report · Humanity's Last Exam","url":"https://evals.report/benchmarks/humanitys-last-exam?tab=scores"},"source_authority_tier":"B","split_or_window":"public-multimodal-mixed-run-configs","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_04a576d1beb0fd7c718f6932","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"evals-report-official","verified_status":"evals-report-official"},"unit":"percent","verification_status":"evals-report-official"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fb2ce8bd76e9f4f7890c9157c15fa92b340f78db9786fa49caca1773b7b9fdd5","measurement_key":"f806b4253cc1de1b5b8469b55b206b88efdbe8ed0bed5ce27777405b6cd5e7c0","metric":"accuracy","protocol_fingerprint":"ab03824db671c6d94897a344c9a9308acfa6123fc7a3526b1403f986d011dc68","run_fingerprint":"963f4bfa82beb3aae899062359d6ccf45ff8cf09234f8a4e42547b2c1741eab0","score":41.334569,"score_display":"41.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_667b754faded84c3180149c6","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6b7c5944affe78ff9d68051b94db0eff2dfbf7cd989949109f48da738dfbfd79","measurement_key":"0ec5bbb56f25e812250ff07a44856eb1aebac0abddb6fcb299060c198e8fb908","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"708ed4ae8d352d0055ca44aa7719a2c8139ee77bb1f55b8248ca0b3c3c869cfa","score":74.6377619047619,"score_display":"74.64","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5ab762cefd0315edc036879a3048bc1b262ca99504f1a24894f97967b730a46c","measurement_key":"f8bf5a322d410fd40c72c1fca65028d7a5562730e027561dc779203b678502b8","metric":"pass_at_1","protocol_fingerprint":"75f4a201a33e83fcc7374d51a81fcf686107533e207e87f40a95800f0c1d555f","run_fingerprint":"fa06f85e345deeb9f84fd5e5a4f4480ec908e1753445eb8dc6146746499246b5","score":87.604,"score_display":"87.6","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":165,"at":"2026-05-19T18:56:30Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c3324b9893fa2155de7427393cbed7fc49c08a895699395b11c9ca263b518767","measurement_key":"d24802a787518da4d8a7d0b2e2e2badf3c0b238f0bd250fec03a8bc93ffabebe","metric":"pass_rate","protocol_fingerprint":"a70710b84629cbea5d23cc130cab469cae477f848702116abf8184e9273013b3","run_fingerprint":"6e17332d3b734bbe2325d8d37a441c9f944282562ddda94dc31f3f71e8a96970","score":83.6,"score_display":"83.6","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4c6dd49dcee6ec97591fd4261791ad4d7eb04711b528f4a4a379505941d2172f","measurement_key":"a799b184efe7ae4b63375ee3e42247f3f1f181f68a1fe9f147bf12888316c15e","metric":"accuracy","protocol_fingerprint":"c99c68e86d5603c9191cbecf32c36729901f529ecc04ed77c0f9c22dcb08473a","run_fingerprint":"795a9fa75592607418a47e300a4dd545ed9e72dbf95aa0637ebb3a0c6b2fd0b3","score":89.515,"score_display":"89.5","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7a9b044a48e37df0fbf1d320aa122dd8289ff39e10d5b081ce61bf1d9d1beafc","measurement_key":"5a8e7e0d30f7fb1cbe994af7439546d9df0815660ba7fc5c9816d2f2b509ec67","metric":"accuracy","protocol_fingerprint":"d75a988a9863e64765f093d2198ebd74f41c3337b75c4e9b2d5587232c690d84","run_fingerprint":"409a07a754f129dd45772147fb6e5323c835a3f8965c1318ce3c35246e79c188","score":88.266,"score_display":"88.3","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":159,"at":"2026-05-25T13:10:18.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c4401c6bfe9849bac82782b692e77dfc59427ba60dcaa972e71d3d135b2e31e6","measurement_key":"db7de0fe589afa28da02557e2121391ae3cf1dd1e3a0abec705777d935107d4a","metric":"mean_score","protocol_fingerprint":"f5fdf83eb3d4f1fc9c2086fc3f859867e4070da47236d1a1788e969ac7c2d436","run_fingerprint":"d7aefe1534c1c17f4b4a17fb117c903731e37c96dfa26a127bd1f9e6cbfc6e88","score":95.55555555555556,"score_display":"95.6","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"781dd298a107acfab64645dcbfa8f45028903baa85a5c53395e7e4c8232c2944","measurement_key":"d46bdd3528cfdc3902e09f4a7cac6ae54e2a08ff1100338d07834c82962667d0","metric":"fully_resolved_rate","protocol_fingerprint":"33d92bd143476db9eb9854c145519019cd84cd865ab701c9b8fdc4dc81ce85f0","run_fingerprint":"fb4c7952c71b7ff55a4d43990f92b63ad97eb0b20fd0d2a4d67c5305a4659852","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6f5ead39d832886a6da6c4fe9a5f30a3fb00a3b3c91600eb6546aabcaa04e8d4","measurement_key":"e235bf4b44f4a8b92a95889d661d9076ac66429dbed5aa94b9f124ed963b7d6b","metric":"subproblem_accuracy","protocol_fingerprint":"d8653dae3ef9b6db54408e89e286a24bf9e163cab4e5dae462577f628dcfdd5a","run_fingerprint":"63b08be79fa6b1215eb97869436accdcb902962658ca16a7de330f9b25625bc0","score":53.9351851851852,"score_display":"53.9","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6e8532cb8111c25943ffd62587cfd9e01b73ee5539c6b91ecc57736c13fc3bfb","measurement_key":"58d075f0eee92f3978e819e1aa7f312d992bfde3f98fd593ef3435038acfe493","metric":"accuracy_avg_at_5","protocol_fingerprint":"34c405ecef08f9fa68202ed884d799037870c7441b23f79acba78c81c9c5ff3b","run_fingerprint":"cf3325512eb74ed46463d94ae554035f962e467b43c92fd8ef458b536477a32c","score":76.7,"score_display":"76.7","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_712ce459e409b423c301b510","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:30:35.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"eab486438c0bd1641cff4595132c722797647446283b6aafd36c8d801d5a9651","measurement_key":"9feb38c26804201facb04d0b3081e70ad154ea09badcdd2c581f1b9d4a562c33","metric":"accuracy","protocol_fingerprint":"e862642b958218745c8c4c30f3ef5e81069ee89a2112ae7eeb5a3627c1e7c8a1","run_fingerprint":"39a4d982b5bb9b0d31f6f1e541525de71866abbd2a7986b43fde60f4cdc9fb6a","score":66.2,"score_display":"66.2","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"skillsbench":{"benchmark_release_id":"release_093b45b8b752b3f08534f6ee","benchmark_version":"v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":138,"at":"2026-06-16","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8bceecd92221db77944ffda42e2ab85e21337caf3d2e23a688cb5a09e26a2599","measurement_key":"147d5180814643208886d7a2a4f5d533487922d4bcb5659193119a91dc264cd9","metric":"pass_rate","protocol_fingerprint":"c2ed2025e534826e5e627446f4493a128269710491b35eb2122abbaf19d56304","run_fingerprint":"8d8c29bcb5bf7f7aa3dc0d1cf8a5006f636be15f031cb5c09f584289e32a5962","score":48.2,"score_display":"48.2","source":{"id":"skillsbench","name":"SkillsBench v1.1","url":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json"},"source_authority_tier":"A","split_or_window":"official-87-tasks-with-skills","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c2aed1feafbd96f260e04542","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"70a8c70aaeebe42bd19d5f7f3f911f0346a4e195b47e61c822f624235b191609","measurement_key":"03925d597279cc4b27205ebbbbd6f2b60c17e782a52a85b6a57e1e26b9bd81e0","metric":"resolved_rate","protocol_fingerprint":"0cf1f0f1968fb021997b12c434a3e3f55eaba1b4024d6a2956d2143c7dfcf378","run_fingerprint":"e787a6288f44471e3257433918aadca25cb7d0e4d60680434527a24f2b7b47cf","score":78.8,"score_display":"78.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"70a8c70aaeebe42bd19d5f7f3f911f0346a4e195b47e61c822f624235b191609","measurement_key":"03925d597279cc4b27205ebbbbd6f2b60c17e782a52a85b6a57e1e26b9bd81e0","metric":"resolved_rate","protocol_fingerprint":"0cf1f0f1968fb021997b12c434a3e3f55eaba1b4024d6a2956d2143c7dfcf378","reporting_origin":"organizer","run_fingerprint":"e787a6288f44471e3257433918aadca25cb7d0e4d60680434527a24f2b7b47cf","score":78.8,"score_display":"78.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_72d764965dd7baf34f983249","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":62,"at":"2026-08-30T11:02:42Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c2d9fbd00900a879634dead4ec872148747718dc01090f62b1e14637ad6879ca","measurement_key":"38ecb8ef33c8455226380048ad2dea23aa9fb6261fe13cc076c6258a328723d6","metric":"resolved_rate","protocol_fingerprint":"87cae4fc720c39d5f79492dbc012e5444b315f8a6cb11bd00d5822d440b577ef","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-03-01/2026-05-15":{"benchmark_release_id":"release_72d764965dd7baf34f983249","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":62,"at":"2026-08-30T11:02:42Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c2d9fbd00900a879634dead4ec872148747718dc01090f62b1e14637ad6879ca","measurement_key":"38ecb8ef33c8455226380048ad2dea23aa9fb6261fe13cc076c6258a328723d6","metric":"resolved_rate","protocol_fingerprint":"87cae4fc720c39d5f79492dbc012e5444b315f8a6cb11bd00d5822d440b577ef","run_fingerprint":"aa675fde7b44f1357ce0d43de8b18ac3ed435f64c51df88a50a561f55ca43927","score":49.45454545454545,"score_display":"49.45","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-03-01/2026-05-15","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_336dda2b1636ac9292005a45","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"}}},"run_fingerprint":"aa675fde7b44f1357ce0d43de8b18ac3ed435f64c51df88a50a561f55ca43927","score":49.45454545454545,"score_display":"49.45","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-03-01/2026-05-15","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_336dda2b1636ac9292005a45","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bc40b059527f4a237415a587f6973d241ba71fbfd858fd5a5e66ad9067c69a80","measurement_key":"ce72cbd12c63543da007215cf286b977b9fe50f32a37150a84ff221468ca846e","metric":"accuracy","protocol_fingerprint":"a014b01503734ff9164368c4f97d154c3388ce94c5bfb6f29d74eb3d75f6cbd8","run_fingerprint":"5cb948c77f0de72b4e98a0eafdd3a3d50b28163c24abf51327967b7a6a67d69f","score":74.157,"score_display":"74.2","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e0bdd95341a4e6da7c95e3f98735df935184f39ff9f7d3706ea3772ec4e58b63","measurement_key":"af5ea2d3428e3169e9ea914e8e4556c9bc165f195c425a5e7f44a36c3af29564","metric":"accuracy","protocol_fingerprint":"9e273746af5615484192acb98c52aba78998a73c5173cfa6270acf34e0069bcc","run_fingerprint":"6622d6bc2d8c7f3884cc52401e07967d6a61645b0eaea1bbd20df02b7f71ae29","score":6.061,"score_display":"6.1","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":5,"at":"2026-10-26T22:05:28Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"539841032994970020f506c87353431112fc0829279c43b905f257a037c20143","measurement_key":"9f6ac941a01536d30cac33199753850f330502d8f012bf79f0256a5c49a6dea3","metric":"accuracy","protocol_fingerprint":"60de94512bc8d3ae20116fe763c1114e524f568ae626d53682eb1ba09013895a","run_fingerprint":"8840c270f50ad87e8bc7c30f73bc2ccded842961f8acc0b1fa9f65a4ba54bf64","score":5.714,"score_display":"5.7","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c01beb7291e936b8dbae7a7f405f2015031fbf541a64bbd938a2cc26d351c7a6","measurement_key":"2df805fb2bfeeeb11215659f72a53b9c75dce3bc0abcc4274eee460aab387d9f","metric":"mean_final_balance_usd","protocol_fingerprint":"aa8132967196758e9cafa32477dd5915441e1de5b9abbf10bab0fc900987ef2e","run_fingerprint":"201657be2e500acaf220fec775fde1af87601ac7b096888511ed94a669aeaa1f","score":5396.418333333334,"score_display":"5396.42","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_81b485f877e695032b0db2d4","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1a55688850e5d0779682855b841fcba6b71ff0c599e84bd06c3d38d9904a8676","measurement_key":"208ac0bd0a9b232a9a43940b05565dfa1806af754a91aea91320929d61f92666","metric":"score","protocol_fingerprint":"29b627d5308e800ec60ee7cbb05e2e32ebaa9b69cc59a052fd62298d5d7878af","run_fingerprint":"43c363da0b1c4cb89dc96225f534836b4ccdf712496f8579c17ebf01f94561b5","score":48.683,"score_display":"48.7","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5395e723b3cd52f198ab738650eb2d2b17a6c4ec78ac1a1b8dddd56fb069d3e2","measurement_key":"dd013fc679278afd1df0900116533d4ed58a6b83a6a19420243abf60b71d6dda","metric":"arena_score","protocol_fingerprint":"13b8f5367dbd56386a64d986c5b951bd9ffdbb656ecc58dcd600a42d18b3037f","run_fingerprint":"c7837440e1280dbe086f0ae2ee2cfcd0c6a412135fe4f93a8c7783fc08ad00e2","score":1499.2741854109668,"score_display":"1499","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ee714246d67430b6401dd16aeedbac5946d9368cda8b7a8a3e0154f8fec31d98","measurement_key":"667a3fe3545286faf5d3a013397081119a3cc81b3d9d5720070b5333bb21a216","metric":"accuracy","protocol_fingerprint":"6314b3888394b0ce27cf106727cd174d83c0e0776ca36ea799a0535697dd4c89","run_fingerprint":"c779f9877210d4b36460518eb7b226770e9d907947d8b564af74578403b2c340","score":62.64000000000001,"score_display":"62.6","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eccca673c5e71c05cc78a977","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"google/gemini-3-5-flash","model_name":"Gemini 3.5 Flash","parameter_count_active":null,"parameter_count_total":null,"provider":"Google","selection_rank":40,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a495c326385cf0f59a02cf387b3c4255ef989c6d46a17d5ab00825785ae2ee53","measurement_key":"c0bc5746b4c318204a811edab67b17fdf33ccdde450cd02f532cc352a66518c1","metric":"performance_rating","protocol_fingerprint":"a6ed17a92b410aab877736161aa7f4ef805d5fca3b89423114f840c6c590c7fd","run_fingerprint":"c8573542bb48f370111f84859594cca43827dd3b81849bfdfe3bc8316bd3ee8b","score":1306.08,"score_display":"1306.08","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_58929078b91d4914279ad26e","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"542b43a6fc992fca0aa185d559baffb6c405eb07cd1a5d5db4262d364c3ad446","measurement_key":"8742f407143a967f18f5fd3561739d92a20d4b4a5eca549c0fe1a4e0956d42d5","metric":"pass_at_2_accuracy","protocol_fingerprint":"b4875e94d18b050b87239fa17e624b0ae70852c2826cbe5d3cc85ecb71209dcb","run_fingerprint":"1fb24d524188d5570b02719ab1fbc8bbd7cc23fb04e03fa34caed54aa51c187d","score":89.0,"score_display":"89.0","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_58929078b91d4914279ad26e","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0c8685db78ca3dd1d3cfffaf5ce8c0ec355303c49d132ed9133cba7cb6cdb952","measurement_key":"ac82c3afc2d9f155d1fdf34a7dd8f6d5846eca2e167802895c1014c179dd0243","metric":"accuracy","protocol_fingerprint":"ed6c05b974d18e2d530771f8572131d611f108e3703feaf748158ccf388ca042","run_fingerprint":"74debfb575427a3eaa688f93224e07b159b4d6bc96e0dffd0e7cf7be32ff6781","score":61.38888888888888,"score_display":"61","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_58929078b91d4914279ad26e","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:32:51.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fc03eeab91a73237aa901e3c73ed6bd913d311d8ab9cef4d69c4c873ce960344","measurement_key":"aa76eb99262ae00d28e72fb71a8cf53f1feb5e0ae77d6c873d8f53a8ee496327","metric":"mean_score","protocol_fingerprint":"2f9516114072525c21b6dfdaa314f40c5cd10e98e8316cc20e516721c79868cc","run_fingerprint":"4e82d51872e65fbc2c5daaf3416bc8ad72fbc8912d2e31f5415623c410c164b8","score":32.0,"score_display":"32.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_58929078b91d4914279ad26e","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2ddc102ae5b95836098f5a770828f43142bdea7ec50cd1f2c67dcbdc2cb4304b","measurement_key":"cfed54b31f43da88a1383cc94964a9344b8d6956ad20b6dbf2ae020581ad0cdb","metric":"accuracy","protocol_fingerprint":"71c1ef517fae994939ed6031a7be314280d251cf3237e2d39146cf104a88969a","run_fingerprint":"df7bd7ec1d910c0278d434bd48d907eac32bd852087f6b1a77e0cc0312307cc0","score":16.571429,"score_display":"16.6","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_58929078b91d4914279ad26e","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8c07c3d516e67952b886174dacfd2219beb38b2dd172134dac2e517569186ba3","measurement_key":"c023a6231b6c7ef1b4866cf59131cc049631f881352ae7e3be5a3ad6a845d173","metric":"eci","protocol_fingerprint":"be3eca2869814a07109082268b5d094d1a1f909f86c6c90949ba8eea6f958b18","run_fingerprint":"c0f0856ccd51cde7699a553aeffafc932f5fecb4bd0dbbea6c1d3da6bd8e0e67","score":154.94,"score_display":"154.94","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_21b864923f5257b0d3f99f91","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:01Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"36472679e6e1cc48c1c662ef5eb42f71c717de51e2feaf41ff2ceddc543aff70","measurement_key":"88ed4b6b44a6a2ebea9a76cf704b5e941ac73037f5647638799f64b4bdaf5a0e","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"62c5b8fe50324737434098580766a1a669322fdeda2b5bd427690c7dda11acfd","run_fingerprint":"e10c1e33011dfb1fb725330e6bfb908992888d74638cf7e65c94c1bb8a456d23","score":18.8,"score_display":"18.8","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_e2fefa2f41df7df75dc708d0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":91,"at":"2026-08-02T02:15:37.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6147967342e06f6efc18642b380246f7c64b17db719b7252aa3ad3f096117127","measurement_key":"12e4a47c7d9392c632391b31e1212fba5248bccb599479f3d3649bff262ad68e","metric":"mean_score","protocol_fingerprint":"f2ceab1ba37fc2104982d325b74da10d78a9ead35ee022f27dc7cc583476e02f","run_fingerprint":"bbba82ef692b117e4a9f19d5030c3e3ea0e638fd8f466e6bc433c6851ac81832","score":57.54385964912281,"score_display":"57.5","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_58929078b91d4914279ad26e","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":91,"at":"2026-08-02T02:15:37.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7fb43cbfa887d1bb0272e16ed11c9dd2e14c4f641743f354b75d100bf369b8b8","measurement_key":"57768677d66d2e5bdd58adc97c4bdfd96484694abfcd32d80dc190b794f33210","metric":"mean_score","protocol_fingerprint":"b6075d68f0e8d230cdba359167d52f612e596f30c0039c7dab990949d63c86e8","run_fingerprint":"99d736ec99deed87f7e56a6089a6b209dea1d1ce4b889c26eef385eb288dcb95","score":24.390243902439025,"score_display":"24.4","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_58929078b91d4914279ad26e","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6464faa4e2fbebca3e5182f7093fd0c6945e13748183bfc307fd861f43ff98eb","measurement_key":"803452f9a0282ec419ee01e78ffb4ba84563a7386ce77fa57f909a603ab79f6f","metric":"elo","protocol_fingerprint":"592e7900639074ed6bcfbc2081e47b1a4a5b3542ed0f3fd1ad18d6aae531bb97","run_fingerprint":"4d6ece8edb99ec063a9e6f05548d6cb07bd48cfb9fe2d6eea1f123b1a1436a0d","score":1440.57,"score_display":"1441","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_58929078b91d4914279ad26e","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6e52a8659e46b93a7e1bbb3006dc36fbc5214e9b79ab2452fb92964449dfc026","measurement_key":"b9da5233e0074e1c0ed1a23bbe6d93b85dfcd243195afd970c3746469e456d4c","metric":"accuracy","protocol_fingerprint":"a493bf3e107ef04ea235ac47fd6425df7effa7e0fcca8088c1464d5bfb7ccc0b","run_fingerprint":"f247ff16a54f242fd02367b8130a0a7f10590d8a211a32372106278e752f036f","score":89.899,"score_display":"89.90","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_e2fefa2f41df7df75dc708d0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_1f4bfa5486eb4deec4942449","benchmark_version":"HLE original","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":93,"at":"2026-07-31","last_confirmed_at":"2026-11-01T07:28:22Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ad5a5f2007ee39c3de3855146704d005e804b1cd8a340ae8af18b48ea7e082d2","measurement_key":"7e9efb7fe318a18b76f4488a68740d02d39f87f3150dfc75b94dff3bcc1488c9","metric":"accuracy","protocol_fingerprint":"4589a852099f2d691fcd122c2a19219befde1963631538e6595ceb9eab750ee9","run_fingerprint":"b35e205fb2026d0fe75b0db6e96838ec878dbadaecd2711a24b816baae632fce","score":37.8,"score_display":"37.8","source":{"id":"deepseek-v4-pro-card","name":"DeepSeek · V4 Pro 0813 Model Card","url":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"},"source_authority_tier":"B","split_or_window":"provider-report-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_bf407507bedf02addf42d3d4","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"501a90c355e52048e1be450b4520ede9f40722f3fcbc946c62f24593fee84419","measurement_key":"eb710345e08e65cfa600c078890f64a74925dd0534f3fdaa62aa155172c7331c","metric":"accuracy","protocol_fingerprint":"db5b4c9bc368ca3269fc65cd7577a445e70e6dca8d81c2798448ac5be6d6d1a3","run_fingerprint":"d0024344ce46cac3c345b8e2c5d95f2754da8a6028258cc1ca400b32dd6e1b7e","score":38.554217,"score_display":"38.6","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_58929078b91d4914279ad26e","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":47,"at":"2026-09-14T23:34:42Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"47dd90691b404dda755512ed1e52ecaf72a467705eda854647854fce6536c021","measurement_key":"dd8d112dabf4be3f8952a78564badd92391400f922dc6a6903ff476374d83602","metric":"score","protocol_fingerprint":"e95e16071e41f3f6ff236aa328f0bff0fc293f21b402d4d26fc3744a6ddde8a8","run_fingerprint":"45ef8f9eb9e51dc8bd633bf1542600b73ba695b5be76821e52fe34b76a5a92dc","score":32.722,"score_display":"32.7","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_e2fefa2f41df7df75dc708d0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"16040d54bdc0aa99749366be940871b8d55a4e3bcc2e5f08ee2d3ff1b22f0ddb","measurement_key":"035306ae41cf556d24702de55b72bc182974764fcc52ff2687134f393418356b","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"cd79a0695612cf2973e2f40d49fcb7c5d19563d2fb720ef69cb9aeddbf5bdc6a","score":74.17078571428571,"score_display":"74.17","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_27322121cfe7d870e70b359b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0e099231e07a376fe7f54551b4f584595b396edc9e36174de182f4ef98149ba9","measurement_key":"3b95156422f7be216b12b690c6cf7ad9d1d2e61403751b8db13f23947ff83c40","metric":"pass_at_1","protocol_fingerprint":"d08950f44f333805ad987964e015f27b137f72ef2adeed192bb9cef4aee4c519","run_fingerprint":"3f8bbd9c65d4dbdc105b39174b811be7bcb22cf0c118f133f76a22606129f8c7","score":87.264,"score_display":"87.3","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_e2fefa2f41df7df75dc708d0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4f72742f5273877f13daa672745c1a08172f20486e6748028f27728af2f56365","measurement_key":"285bdbd83f245a3aa166579a36a15b25611a2c33e051261d0041f40460bc0110","metric":"accuracy","protocol_fingerprint":"e3688f6717b481e55df0b8d913033ad3a42d966e1043cc47d44f24db1f27b9ce","run_fingerprint":"a3b8d54037a93d87cf50c3d753ca1169d4490d60b3da5ce40afce26c8cb5ce28","score":86.206,"score_display":"86.2","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_e2fefa2f41df7df75dc708d0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":91,"at":"2026-08-02T00:22:31.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8ef87096a5eadafa6e0c6796826b219794f9acce4112ace9afe588c31cb41db5","measurement_key":"4f4fcdb1ba53fb847705db3be48d7a1b3852436c96b4c66ea9da1b5df6c9913a","metric":"mean_score","protocol_fingerprint":"48339610facb782b0d911290d11ed2dbf3217eae2adf9f0f02530b418cdbab4f","run_fingerprint":"5c26b3216153b5b80ef1eede0889cacfa872d338f1e3b08e0980ca308963586d","score":94.44444444444444,"score_display":"94.4","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_58929078b91d4914279ad26e","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d8082f046ba3ce8b7f6a06a2013fec65cd5e01843452e6bb4342206dd651cbb6","measurement_key":"1399f443b163f1afdc30af657ebc4173d5a57878a396227296ded1f286c2f13f","metric":"fully_resolved_rate","protocol_fingerprint":"11c716a896d79fbae3a802bb0201497d29704bb1466e74a8e715a17357dfef99","run_fingerprint":"91cf71108cde370876542c7dccd45bc8623b20adaa9b446a3012c75e4a8adb52","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_e2fefa2f41df7df75dc708d0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:47:54Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"91e053a8e9c888684e9f04d65df85cafa2f977af813f17fc54be04004d9bdbd6","measurement_key":"17ad567a7271e8eb8c81fa1dc593049f7c1816c5465f252d12fcd88529d4a0d0","metric":"subproblem_accuracy","protocol_fingerprint":"13c6184b21680ba605fc94a5455bcdeb451e82d3a9e2691e8a8aa4708d51f2ba","run_fingerprint":"a48e4e012a6bd5a08471dd80f295282eb530e9cb4e5bd283f59a0264e5fa7d60","score":49.88425925925931,"score_display":"49.9","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_58929078b91d4914279ad26e","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"56578a8a66c7d249d1980a2521c5276157479732f3cf37342e9b0d8623dcddf4","measurement_key":"b9bc5c768e4eb51f76708a54af692967ef97cdbe27d29ba1026e2bf5126d126a","metric":"accuracy_avg_at_5","protocol_fingerprint":"cf7f78b05898922292516882047806d7f9daa066f7ec01a61f921883183837e4","run_fingerprint":"4a8d973bdf5968954d76efd76b9e1527720c2f686dc191eee46268189548fcaa","score":61.1,"score_display":"61.1","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e2ef717a623eeb73e7398005","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:30:16.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9fd59210f4d72af3529fdd88b4e6775ba6858be12c97d96f9ab43e2de921b310","measurement_key":"d709219a1f7f4b8d1cb5a9b4be0814d2e9a5eb05617b11e0972a10ab094d3045","metric":"accuracy","protocol_fingerprint":"c508a328505e9ef3dc1b69c8bfd1933ded821747cd869563855260a91233d886","run_fingerprint":"8b5fe27f27da7d15243e3917e33e94c7db0f2b1b31b5043b3c18544aa86e9445","score":33.633633633633636,"score_display":"33.6","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_58929078b91d4914279ad26e","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c5dda6ace1e0d6c0cd985e3d7f0e0c1bc35711692370dab042608c20c147401e","measurement_key":"d672cbbd4d0b628606d16169edee40900197bc7662934b682bc0962f7be04fd2","metric":"resolved_rate","protocol_fingerprint":"7e2388441b97b254d55da72440e4cbb7f9f784aff791ffef0c69af721401d1ae","run_fingerprint":"ea7c2c9317f93576459bdf7dc7e4835716489a3107b92b980cb3c2ef751e851a","score":88.8,"score_display":"88.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_e2fefa2f41df7df75dc708d0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c5dda6ace1e0d6c0cd985e3d7f0e0c1bc35711692370dab042608c20c147401e","measurement_key":"d672cbbd4d0b628606d16169edee40900197bc7662934b682bc0962f7be04fd2","metric":"resolved_rate","protocol_fingerprint":"7e2388441b97b254d55da72440e4cbb7f9f784aff791ffef0c69af721401d1ae","reporting_origin":"organizer","run_fingerprint":"ea7c2c9317f93576459bdf7dc7e4835716489a3107b92b980cb3c2ef751e851a","score":88.8,"score_display":"88.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_e2fefa2f41df7df75dc708d0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a8a04afaffe800894c59e2b59de356b893e5cc75f28b10d28e724289ada22626","measurement_key":"0f2ba553876b0a44bed9fbbd6df4ec8a5cf692fb1691cfed325cbdaca0d4ba7c","metric":"pass_at_1","protocol_fingerprint":"fa30a46d3c4e2647076ffb19dfd97ddfbc7fbf8e0338826a7b14058b3ca2cdca","run_fingerprint":"124a3ce37f95f81e602245ea38783425171cab20e1c67242d6966eb668974357","score":39.381443,"score_display":"39.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_58929078b91d4914279ad26e","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9ba6727dfbe84818e8175601705078c3bec47d6e2d04a5fec32c0de725e86b77","measurement_key":"49079e1c2297ad523b2718de93abeb55ee374765603e5747bb65e72383c64e01","metric":"accuracy","protocol_fingerprint":"350e65a26f9521aeab9a9f711fe352e059578ccf18a17854574c54c586e637f6","run_fingerprint":"4e935a4e1e740cdf39fff0d487c5bf0f10d8cdff36583309b86f236132d91de8","score":67.041,"score_display":"67.0","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7379d89dcae12f3817cbf811","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b0e5da1d8ede094a20f0d9815cbcd945817a77a569b7596314bae7f26c637723","measurement_key":"917c29c8d5cea69bd9f8bf0bc2c56690f1d786b7a06a9b75b8823def984b0314","metric":"accuracy","protocol_fingerprint":"3ec3dacfe32d92f6c5c22ce1ebfa3aab44f1b3892d0efa4cd510970e2aa31e6f","run_fingerprint":"821ed1ddc4559a9fa614432cfe5b6f2735fa1468f7f55c44ab6df20de13b59c5","score":18.687,"score_display":"18.7","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_e2fefa2f41df7df75dc708d0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f70947e52f6167541396653c88ba451cee9be0411c84615c8d13f01f12d991ec","measurement_key":"ccb70b1e3a68da39cedc54ee67ccca695e26ae650256a694a216b4129e42ab34","metric":"accuracy","protocol_fingerprint":"7e7b7e936a217676774cd60e29e30e7c07749c22aa26b8a2a3e7d145a59d27a1","run_fingerprint":"c27dedd92a2080121dbf345ca8e37e665ec90be9cb28d5d7507a0c816412db5a","score":4.286,"score_display":"4.3","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_e2fefa2f41df7df75dc708d0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8df01860ca991546102385163c2a94ffb6a95fdaff72a03fbdb0180dcba25e43","measurement_key":"545dff596c7eb3105b04337e29474787ad5b79dd0b0d2643c76322a03f4406b1","metric":"score","protocol_fingerprint":"c2933e9fd40db6e389dc34059f2bed96f4c6dce396d59f3fca4658cb0ea014f5","run_fingerprint":"839dbdeec15daf2bbb1dbf24b37fc5d43a3b110607b38e4f47d68ea23fe4b1dc","score":74.736,"score_display":"74.7","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_e2fefa2f41df7df75dc708d0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_65fc140e7ffbb7bf62021f84","benchmark_version":"Text Arena Coding current pool","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:15Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"47ea0ee120aaceb273484ecb3d2fa48714dc5770c0ba2299a38eea0c74db744b","measurement_key":"d6e82ec86a242c9ae87a9d091bea9139a632a23d75a5ea9e59b2340ad4d7b04c","metric":"bradley_terry_rating","protocol_fingerprint":"fe5398199e5b4ae0f55fab2a4bccdec2bf4197cd7613709660eebe0894a7cc51","run_fingerprint":"e24adb6f96bcec18c8839c0d79c260cebeea1fc688f24391b1890e017d7d09b3","score":1580.2,"score_display":"1580.20","source":{"id":"epoch-webdev-arena","name":"Epoch AI mirror · Text Arena (Coding)","url":"https://epoch.ai/benchmarks/webdev-arena"},"source_authority_tier":"B","split_or_window":"text-arena-coding-bradley-terry","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_e2fefa2f41df7df75dc708d0","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0e35aea58b9299e908907659d4566cfd050a4f38d875b17cee8922658d7c1705","measurement_key":"3f89855a792281495402194f770512122c7d438dbef67975665ae931b13c406e","metric":"accuracy","protocol_fingerprint":"b28eccd1504c39139f2e046ff9f2e5210909468615c499a8547165b56f927d6d","run_fingerprint":"94864af600a493830bc78a5c6264917766c2ff59040709dd4328902b58333ef0","score":62.96000000000001,"score_display":"63.0","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_58929078b91d4914279ad26e","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"deepseek/deepseek-v4-flash-0731","model_name":"DeepSeek V4 Flash (2026-07-31)","parameter_count_active":null,"parameter_count_total":null,"provider":"DeepSeek","selection_rank":41,"weights_status":"open"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8958c13d4cdcba65026a4f9b3ecb4c56af165190b8309c5eb761e4c69c545b60","measurement_key":"4f3693f3249428975d543c783e86e35dcc5fc8ac337368d6d2600cff1b5158ee","metric":"performance_rating","protocol_fingerprint":"7cd0014ca862437fbdce8d22a81e5a4e5e55089d061b1b3238417a012545d34d","run_fingerprint":"bf3c900f96f84fd763cfa5758df7774c772853475fce58b155ae43aa9664dbf6","score":715.52,"score_display":"715.52","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1b05312ab043561c02314b545f8fb963c8912d88d4790b1025878f1558d227c9","measurement_key":"e1b0afb0c089dd9c8d72a5e2b02540f4378762f95bff3f96319e5817ffd15c12","metric":"pass_at_1","protocol_fingerprint":"4fd14524089ba16d3f3fb9ca6d6097a22820734676e76806a473ab8424621689","run_fingerprint":"f7735921b21f326e22a55bac145fb07fca7f44e18cf42a1775e723ed6f27c919","score":46.9,"score_display":"46.9","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8c08c2576548098891e1714e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5cd2f302288080a63a3185c8fac88409fda121f474f49bc32d01465ec2c62f1d","measurement_key":"b3958052d8b963086dcb366a7cbadc776fe020ee864dfa12234458939d560695","metric":"pass_at_2_accuracy","protocol_fingerprint":"0ff0cecd15fa0dc7c17389bbe906b92d29f43f4496ab963d0a22a57c92b920bd","run_fingerprint":"8d277eaa40631697c6ed812825149854476347c08613bc56f226390eaf31991e","score":91.16666666666666,"score_display":"91.2","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dcc3c22f9abca9796a3b910d6fa0af3a461b63a2d5209abea6f09767834f306d","measurement_key":"e2e767b1563e21cdba01dbb9b2b0331d28af1efc6b122892734c8d7c3da90bae","metric":"accuracy","protocol_fingerprint":"554223a6af1805cd60039a3dbf8b91eca97034772aae1bb886053a411bb9daf0","run_fingerprint":"b88a77307fe60987d62c9e9653aec287bceaa2898e472196e65faaea951f91db","score":60.416666666666664,"score_display":"60","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"18c1f92dc657fdbb58a01cfce3a77a68ece4ffad37f9a5d33d9b38926ee2cf50","measurement_key":"1a2ea07af35c61eb87da9a5d32beb206a2ac8bf16038826bc46af92073f2a2fa","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"b3a6561993ae97c9cf3cfd4262f3da51108e3749fbbd4228b14a128faf6f75a1","score":1483.155122800798,"score_display":"1483","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:14:52.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d134d5270a1803734a5fd8bc82f6e24eb9ad0cea01da492fd51afbb52350a910","measurement_key":"7e85d85fd4f32fc915457f8f6054d83fe4d631cf6882474ed1801a74c2019ac2","metric":"mean_score","protocol_fingerprint":"eb47023cda6163348f078a26f601763f40dae842b304a97005b33ee5388ac261","run_fingerprint":"174d2e452266833eea6765a07cfaa33da9b91b751b287fcb3d214b65255c98de","score":40.0,"score_display":"40.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7a556887a45287d04b2c4e338c583daa7f59a1b1f8120a3b22ed96814505f182","measurement_key":"b7fc9d7f59a839d989f83c3560acd1336697ff24db641376428b38356dd59465","metric":"accuracy","protocol_fingerprint":"4c871a6888ba4d35f9162884c2d8489dda58047701c7d3bac7440123d696c17a","run_fingerprint":"fcca66981b3def7c7877701bad8fb46fc198dd8c9ebd1e05eba97bad7606c9bc","score":10.5714285714286,"score_display":"10.6","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5bbf6f0bb61d9ec86f5d65c6e22d3a4e43edbb202c5be6ca50bca6ccd65262bd","measurement_key":"8115ef6d0440ffed6d0a85b97f4961a356e616b311e707dfef0ea472a6907592","metric":"pass_at_1","protocol_fingerprint":"808897a2ada0f4bd1c0907516eeb1e63004ffe30d1bd8bbfb33ef7e9bf5968c2","run_fingerprint":"3c5c812d091e53f9b1392a08c0d38d56b4b55516ef8be2abafd11ff6c82052ae","score":46.68141592920354,"score_display":"46.7","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0f833d247c41fc359575465911300501380ae58ad61c27fcb0a0cbc0c35d897e","measurement_key":"b5a3ef0ed7cc9e7c4b95fa61d051814837d005dbdab3c8806f8f46b8352a5a06","metric":"eci","protocol_fingerprint":"4b56be829d24b33a8a4e6529f03f2326a6fb53dc965554b5984b604e1017bb73","run_fingerprint":"3fa5847d8116e3624d64b73ce430038c5f029dcc9310b948c4902f81e9bf3319","score":154.69,"score_display":"154.69","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_873f73507674253f1bc4bf8b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:01Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"263b670fff3eff0d63dc5636a3908326f964bfef123f6aee0c924127f140ba33","measurement_key":"dce9a24fc8b766f2c879404954fcd54ac899921d5a2836b24fff313ae9615b51","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"04560db7b711e12dca40285fbda63eddf2e4cef9dd4c3f7b4dc6841b47aa2bb3","run_fingerprint":"eadcb0685ebcb389a3f80f5c0bcda69b917e3d1054b78ae96844b69a16184cf7","score":34.37,"score_display":"34.4","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_d6f7288969ac5442efd6b4b1","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":91,"at":"2026-08-02T00:36:45.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3f7df3de999b798a6761bea811826438d8037d25054875aa8f22bc29a0ab6b74","measurement_key":"42944f706db2d0546e7a5a7206725600ec5a724ba42595e42e98e8d5634ced1b","metric":"mean_score","protocol_fingerprint":"7009711d176684ec2286b418347a8c55d59be076e6ce742303dbfab48fa05624","run_fingerprint":"4e3a5916b3615e3556e77773b1dc66451824c7a93d3730492e66f7bcdc8aa8d7","score":58.94736842105262,"score_display":"58.9","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":91,"at":"2026-08-02T00:36:45.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e6f821659da220ec55cba3f836133ea6ebef8c4c8d43596a29a654c188220a35","measurement_key":"3d0687d23e6009f458282a1939371d151daba7c7cee399b24b36428da1c7bf40","metric":"mean_score","protocol_fingerprint":"7157a5167fbcc14c246da0a6790e6feb872cf05de840639b974c69b75ce336f0","run_fingerprint":"e1f8d9edb3f6376dbb9d924cb56ba2bdb43a6cc3f912fd1ed51003793a3cacc6","score":21.951219512195124,"score_display":"22.0","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2b8fc35112da238a4cff83e22f32ef64a0fee4a6ae3741d9499576177c1e11b7","measurement_key":"80771d42b82aefb74c775e15d960083ab1f273757e9f0c38691164fcc14d431c","metric":"elo","protocol_fingerprint":"329045579771cb2f4f33fd76ab1dc151844151e977b5c771055765ba824c8527","run_fingerprint":"f947b27de3395686ff705961908f1326e7905f69a51a63b156749d275ec2c7da","score":1294.63,"score_display":"1295","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e15a4c232e728b0187c51a895c1e8d865495f179410a75aacfbad79bd1cda926","measurement_key":"15a3537454408f1617a5b5bdbfa25013da3b29cd65ec056fb59e7d1faed2a8b8","metric":"accuracy","protocol_fingerprint":"036d248110c1387eb142bde1055c6c986220c4d124dc62dd20e0c536c5e56cdf","run_fingerprint":"8fd5b86f9aaee7f343ff4df1817627ae1847006d12ee57d94e9ae76d2eac93f3","score":93.434,"score_display":"93.43","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8dd9b7970fc7489846ef466be154c1d269711d7bb7f28abece126de7fcc61c5d","measurement_key":"76e687836845f115426dea5e572101a237028ee261fa63ae105e7f0c18fa5080","metric":"accuracy","protocol_fingerprint":"d3ce1e90a3ea85678481bfab2cdb77c323a79c154bc3d4580427b79aededbf6a","run_fingerprint":"ee5de3c7354b1d9f8132e037f61f29b0e3ab40ebe7efec31f6c0068cf9867c7d","score":40.824838,"score_display":"40.8","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T19:24:33Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fe646b488bbb5255a3df4d00cb4b17bf24d0f8a7241812f70220dcb91e58c576","measurement_key":"b874880fa70437c6d11fb1633e5405c6ee546add970333971756295bbb074943","metric":"score","protocol_fingerprint":"521f86923c1b5498e797d1ada569c87d4c6d33b68676e4d9da9bf67adf682356","run_fingerprint":"cfdaacb95a62cc307d00d3f686463b8a44aa23af58493e7c9304686292e1b6d6","score":35.056,"score_display":"35.1","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5bd0dc44a1f02cad43c6370ea812a00250ddabea1f41f411ee1dfb439c6b93f7","measurement_key":"75b00a342f698b1425188c71567036f9ca68cf9eba4cb7c4ecdb15b2004b2137","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"dccca5bf6a407e42fa846c36abd0fd6901ebccced285ccc1fb331c65ad863f36","score":73.5875119047619,"score_display":"73.59","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"801dac345091934fe2f8abcfd5dfec22589c095e19b284c170573a226365d578","measurement_key":"c4e80557c18b44a9c5d674ed3395f780c75140d546f8310d8d4b25c1f3563ad2","metric":"pass_at_1","protocol_fingerprint":"ca3253b1789b642d754b915e20a1fbd84b6fedbe1ea9e9034faa9f873f8febd0","run_fingerprint":"15385c5f4d2d43f1e7df7d57cbcc4dfc44ebeabec31467b0ea59e339a4297162","score":88.08,"score_display":"88.1","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"543e40cde08078508afd64b49ec9b0f3368e5057c24fce9908612856b2fe5d78","measurement_key":"23c0fb16335e20b4fb14347b3cf0b557a98f9460e234c6a16d319166b4b84e33","metric":"accuracy","protocol_fingerprint":"275a021c7c1f6a5743dd1c0e531db1725777e55f7ac5eb359c2479240f867131","run_fingerprint":"d272f7cd0596e489e4ccf5f648e28292deda8ab16323f0672960c61a3577d77d","score":89.276,"score_display":"89.3","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"aec7c78d88488c2d8a43a8a02869b285ba005bfec3a10a79449774856e5530b1","measurement_key":"d8e06dc3c7399be1385b0e15b376f4d06b2c2ab16752e24663425d6f36927136","metric":"accuracy","protocol_fingerprint":"cd10394f6643ac9d38ed8ae0bd6e88b3a2dabd69ad8644b6eabf05c35b2530f9","run_fingerprint":"3bee005638e10f80df59b17622a00dd0dd475eef51b66d3b772f63067f415cac","score":88.382,"score_display":"88.4","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":91,"at":"2026-08-02T00:21:27.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"19722ab6b659ac05e97cafd18cc2a093f68d09d60e1945f87ff50aa15c6f66d4","measurement_key":"46f243eaed75f6332515dea33e3248456e267a98df9b77b256b619333b6d0019","metric":"mean_score","protocol_fingerprint":"4f13d3d4ab35bb573e108a1e14ddd9d6029fdc2f9388cfd160170901439a0866","run_fingerprint":"44c7568bca5460823d77ebe9d88bf63405364486db9bae9287f242dd695972af","score":94.16666666666667,"score_display":"94.2","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"39fd7ac8a960813659c1bd3523aa3a4ee04f2520e589d25ca151146df852e4c7","measurement_key":"d374e218d23984cd93eebcf3ccdd497703d4787ae24583108326e522864e1dc8","metric":"fully_resolved_rate","protocol_fingerprint":"575465df6e3319d9b9a0b4cd3562b0145a7e88ff202a93e1bfac9835326c0ea0","run_fingerprint":"e5294fc8471b84efb61832f139c10b812e4ea9674ef07020d04fcb528b91dcc5","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"22c5d4cc8beeb379d43923d4fe035e7ca2c555ed4b7e7e92050632e88aeb6235","measurement_key":"d1f1fa9869f687259c75488b39971bac81be7f823ceb081ec6f5f6d2ca3e9921","metric":"subproblem_accuracy","protocol_fingerprint":"1afcc49b7d3e3593a273e5b654c5b1406c66e611a6d441ae31280b76d079b24f","run_fingerprint":"dd92627b60a10cfa605855072dbe44cf922e11eb1da860e6b8eee30310ba0b9f","score":53.3564814814815,"score_display":"53.4","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:30:09.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fe2c28fbd1d96a7cb472595cb4daae897749d206df8a14a862bbdbb2cea27eb3","measurement_key":"61c838e04137760b1d1fa8b6b9c21317b8e18d495fd8f21c87e29955529bd655","metric":"accuracy","protocol_fingerprint":"0d6ad28d9fc396e46a42355e03f980b920d813e637e068660351d9f66798b9c6","run_fingerprint":"c46de95e158ecab2b75ae8ed17e1c9c645cd8ea7a19e5fe2b9a5e7826aa3f110","score":66.2,"score_display":"66.2","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2bdf07bc35a1678b96b376b422c421ccaaedc0552353cf16142ae887e0086031","measurement_key":"3a246ec7cfb8e473e0b3dfe9c21675961653bfb613c782a7a726369cb69f2cb0","metric":"resolved_rate","protocol_fingerprint":"b343a65e31729dc33a50a6f3429b8b2cc86fd1358b12fb935ed8e738b4d8b3eb","run_fingerprint":"a1642b35949ca01c9cf0b723a4b50f6c5db706dadd153b2644c7430dfaa499a5","score":79.6,"score_display":"79.6","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2bdf07bc35a1678b96b376b422c421ccaaedc0552353cf16142ae887e0086031","measurement_key":"3a246ec7cfb8e473e0b3dfe9c21675961653bfb613c782a7a726369cb69f2cb0","metric":"resolved_rate","protocol_fingerprint":"b343a65e31729dc33a50a6f3429b8b2cc86fd1358b12fb935ed8e738b4d8b3eb","reporting_origin":"organizer","run_fingerprint":"a1642b35949ca01c9cf0b723a4b50f6c5db706dadd153b2644c7430dfaa499a5","score":79.6,"score_display":"79.6","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f2b5ba5ea0f82322ef1823f904dab93a735c1b1f0b7a5d666ebeddae3575ea71","measurement_key":"040404b4ca83908d2483fd495ac389255e4fb8e29158e4a4d316ea4287036625","metric":"pass_at_1","protocol_fingerprint":"512734a6a28523bf4572c6c83b3ed7007e69ec3a01528bf06a4fc4daa040feef","run_fingerprint":"5fcb31d401a9479d755bdace4f2c6770ea2bdac2faedb91bbe54400ce376ec64","score":29.896907,"score_display":"29.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"95d17feef5e944a2a21461c871dd0f3a591f9f6da19780be1a7a518b088f29c2","measurement_key":"bc5441080d5555f0c0d3bfadaeb4ce01249b591c846d58a71c3f719640f8dc15","metric":"accuracy","protocol_fingerprint":"6d9f534def2a440d1dbd6fb87b11b6a2d4d7b30bb4a9894c3fe2353d7518186f","run_fingerprint":"a1bbe20cac011e1160ef4dd1f7e916ef0fbeb493ddc8f455f5ee7564ee66f54e","score":73.783,"score_display":"73.8","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":5,"at":"2026-10-26T22:05:28Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5c53392b93820d29727925bec2c59a9c6fa1341a3044cc41181f7c400593d8c4","measurement_key":"d4b4bc733375ca00c38b065f2608ff870f24c9aea67aaf36dfdc14518f1f3cfe","metric":"accuracy","protocol_fingerprint":"18ec0db34175ebbe4736138c30f4399c24503d43420c8ef925e43ef33e6b2fe3","run_fingerprint":"eb431d120e0e8e93ff69bebb8c9fa8adcec090e5fb087534552e2dd9f3cefd2a","score":4.286,"score_display":"4.3","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d15dd73638c79e8e205e04a74037c5f300288712fbff5e3d39f00bff8a1027bc","measurement_key":"cb2153e502dda857c4554007381982bb444fd5994402986209ef7200681ab6b8","metric":"score","protocol_fingerprint":"bb352c62009cec5eb45a26c704bdc44b0f278ff94621451998d7bc628397a6e9","run_fingerprint":"746afbc1fb5226f1e2f4a8b1cbe49b236714d5f914edb14917768640fc070e60","score":64.005,"score_display":"64.0","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8273e59652e0e64ab929b6d2ee0f9d21d56f9cef02a4e5f678c2853fabf27680","measurement_key":"d4c4d8c61b045598dce67abbb7f7b3afae4221292bfbcea7445b67af8491b3e3","metric":"arena_score","protocol_fingerprint":"969a4db70abbe06850e6b2d8d7122987525372ff4d84e100761a7e6e07c01ccd","run_fingerprint":"71980432db50c41cd891fe810ed34433472e304fb151cc4ae50f44045a2d7cb9","score":1537.5456409227427,"score_display":"1538","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"103de9a2b89c02a59e077199060a7d67750e912156b5f81ce6e82a61fd2a8876","measurement_key":"c81eb656ae79a692baa72ca2875f4d3f7bc439f599f16550a9a88bd74aa16ff8","metric":"accuracy","protocol_fingerprint":"fed35aefbb9ecf5bdac93fe42a07a1389116668de3e39f8adb4adf526dfbe273","run_fingerprint":"c9ac21ac3075ebee6ce28d564c03dfaad8b40dd47869f1e0bdba32b487184548","score":56.10000000000001,"score_display":"56.1","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b910cf792225dccb483afa4f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"google/gemini-3-6-flash","model_name":"Gemini 3.6 Flash","parameter_count_active":null,"parameter_count_total":null,"provider":"Google","selection_rank":42,"weights_status":"closed"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"44c9bdee63e731eccf4c4f0d02f72923ce0b1bd9e8213a5b10a2a0df8684df55","measurement_key":"f1d88d835a6216bdc07d0f0a0a4fe84b0555f58b62d915d4096719b3e7e1019a","metric":"index_score","protocol_fingerprint":"0a2531931526defad170f29b6712fcbaeb592dab72ba66e013c91f9d49eeaef0","run_fingerprint":"a05e83a4de4c0818c0d2ef2ef953593d0c8e90533744a4bbf713aa907a0b2cd8","score":34.335012,"score_display":"34.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:12Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6b1e769eddfda919ef337c69b45235593fe0e4e6ddc4b7ca0d12e059c138abeb","measurement_key":"0ca98e9a3829f06edfdd29c09dc8fcc2e88caf488c6a6e954c3b202f11d12683","metric":"pass_at_1","protocol_fingerprint":"bbbc5bb3cc34d866861fe43d73a30e9e4d58ed7aa8888326d2f0331a8f919e51","run_fingerprint":"72140053929002d789b6f5fe0443241afcf7a9bedca50f5748a1fd977381ac03","score":54.6,"score_display":"54.6","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_89a7d6172adc99c954f9182c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:14Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ff2413ccbbdd7db2d1ecba7018c9b4572064a69193bb67eab9eeaaafad67dd13","measurement_key":"54132b672972138353bfad560da5494f3138b7ac5a8e88c779743414e9f7e712","metric":"pass_at_2_accuracy","protocol_fingerprint":"1d72fd0e84f6ede463fc5584d2b4ce1561454cc537705fe0db3057e075521547","run_fingerprint":"9d18bf94f2565bc15111190bd8b86c86fcfed9dbc57035d984ff54941368b172","score":89.5,"score_display":"89.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":23,"at":"2026-10-08T22:23:19Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"988c91df41c2bfa727dbc783e6f1846007b2963352e78c09f0ae570e912b8e5c","measurement_key":"e82178c27e366a074f41befbff646bfc3bd38c3062a95bd56349a80328c81cec","metric":"accuracy","protocol_fingerprint":"ed4a2a4a139d50926900b1501b97cb17353f657136e72bcfc3ea78973dfad2c3","run_fingerprint":"4e6fd632725586911fe11948ca1ccc21085d4058b9a58efde5378a673aacc7c0","score":61.38888888888888,"score_display":"61","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2a82adf52350e4603d9b588942ece65d520fb0db01f895de19abaa5ee85b34dd","measurement_key":"f3fdbf9b5fb29cf2aeef74616d6955b77dfc7ada7ae8a13ea8f64976c148b40b","metric":"ips_score","protocol_fingerprint":"c997f4ebd042cfcda34d7cc76ab45791850e4c0d4c9e22314656ebc8dec06778","run_fingerprint":"c2c4d00116a2a9ee60e3216ba0cd675edcf923d25ed93d933bd58a9ae15f43da","score":0.023946701791754732,"score_display":"0.0239","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4a6e2f0c00344631d517c5d0956e193feedb18643f4bf564d4e5d7f01acb84c5","measurement_key":"d4882132ca205ceeb93b2cb5313ec5dd56ae0b23ffc8509a50897823cd7a8421","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"dcfb7374f3fd9e1e2ee4049198564915b5ef3ccc326611aa9b023ba07f5a5ee0","score":1441.2270542052997,"score_display":"1441","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T12:39:21.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a689870f354dbc5debcb77142fdbc4fe03c84a380cca7021e1b290b875772d4e","measurement_key":"3414c6afe022a3eee58e5a9d7fa152b1e222b749a7a7d8e2050ba6a5057b587a","metric":"mean_score","protocol_fingerprint":"e1c987a055d9b0783be516d94254efb2f1e5500bef6d7849285983a5d1ee00ea","run_fingerprint":"2f1fbe706cab72b00363d584ad001656203a3ed372734a2631003597d14fa62c","score":41.0,"score_display":"41.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7dc9cc043ad29fbdadc87ad4991091312cbbf2ac8758663f9559a41e9e38ca01","measurement_key":"35eb2fff0d2fd56ba80da0b3d589d4e13515f2cf3acc805f166729d5e460d9d5","metric":"accuracy","protocol_fingerprint":"dd8f41a4d230a885e45d7e16de85b502999fd96f95a7c0032d8ef6cbd69e1df1","run_fingerprint":"40412432f45a51f7157eb75b6f71133541d4ca9e85e912310522f0a3af884908","score":17.714285714285698,"score_display":"17.7","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"cursorbench":{"benchmark_release_id":"release_9acebd5b002e9c3f18a30606","benchmark_version":"CursorBench 4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e8acd65262ddfb582cce5c930a55c717ba2371fb5452c8341e8ce87ce0bf411e","measurement_key":"7182067c731600cd214a1a79e4215d1fa461d929e6e528754988631b5fcb7a4a","metric":"score","protocol_fingerprint":"6cbb1948644b8ad8e8bb7940086710098d626a0b5447950e21313d42b08b488c","run_fingerprint":"31f4caac56926ec9de6e973df2b25cc2cbdd6db0d0caab14b8ae43a1b5d7c7b0","score":46.3,"score_display":"46.3","source":{"id":"epoch-cursorbench","name":"Epoch AI mirror · CursorBench","url":"https://epoch.ai/benchmarks/cursorbench"},"source_authority_tier":"B","split_or_window":"official-current-suite","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"70ed8f09433d33968bdc844ef98df9057e7124508d969418f9f5818cd16d3739","measurement_key":"dac895c1172e6b15789f31eaf1ad0056fb40c269fc5184ed934dbd1dc07c0d84","metric":"eci","protocol_fingerprint":"2cc6410bec453b49e8e33a4abf0b045c103dba0883f0653799c5f170e42ce805","run_fingerprint":"45729c4b16a26c7ca384627f1219d567fca5426e41e2b3fd469f01f3f0db453e","score":154.55,"score_display":"154.55","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_41d3dbb96d2673ac6d6ba6bb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:12Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f41be5b34e4fbfe8ce067d48f09a6c8369f574bd676e4e0eef4bab27d3f0b614","measurement_key":"e457574bc55396ff0547fb0d37ca157f7b8538937bbf13d50f258b1e9450d61e","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"99e4b51319b947166a810995ac4bc70f908c5af0f32398ff03a4b015b7d49cf7","run_fingerprint":"afa141174a989803f6f895c920d403bfc71f371c77f47e06e497be1b9732cdf0","score":47.589999999999996,"score_display":"47.6","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b1f23152c5d73c89b843de81","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T21:49:22.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cefd0f96500d72ee527bddea73b67f2415f75602e17d24cd5aea1e53a1adbc14","measurement_key":"ad4b21d5a534644fd06131ce5f0bab12a65f4e7fd15d92a89c07203b7236f5ea","metric":"mean_score","protocol_fingerprint":"ad64bf406a59155c8c66d3acacd28cb226ec54a10ee69ae99d3b1a4369969769","run_fingerprint":"05c767def89b7c1b083f49060c09e6fd8dcd89b881caf80b6eacb94f19612294","score":52.98245614035088,"score_display":"53.0","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T21:49:22.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1fc80fe347264ed65d0daa28957bafe9f1458686b160af8ee53ada2e024ca98b","measurement_key":"acf84b40531abb2413aa6e2c8597d71d0297c1b587edfa86ff2bc8ff6df28dbd","metric":"mean_score","protocol_fingerprint":"8f425196ee2bffb2b6982024f14ea775092e191848a81f4c192683d2b8aeee52","run_fingerprint":"96c872fb288b9628f0cac265fb62d25721393a699fe41d265ce5853ec2f54e93","score":17.073170731707318,"score_display":"17.1","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b2ccbd512953a6b94f1e013556df66f3114fb981725c4711a7eb04494e3720e4","measurement_key":"0bacb46f8ff42e625d54ad4f43e2395905cbf0a7c4300d1c52205e5f615b0edf","metric":"elo","protocol_fingerprint":"95fabd5d8840686f1fe5a5bca8d8fd618bb4372400b50f5a1fcfad3a18a39c58","run_fingerprint":"10c3b2e5c0524628e7c338d4634df755363f2bd81860d74997f1cc1fa42c1c85","score":1718.42,"score_display":"1718","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T21:49:22.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b090e548cf1b6c6225b69dab169bf0cdc202f545e72590d7848591835860eddb","measurement_key":"03d807ad945d6c3f9100522f432412ede0565e1d2b6f987a36e3e3570fdbfb84","metric":"accuracy","protocol_fingerprint":"c7166913d39cf25ff6883b56b97c6c4e2c2069c08eb39b06111cc2a769676565","run_fingerprint":"e216f0deea3261041ed83097fa8bc3f5515d6a1758b959b33b37f60420773ba5","score":92.73989898989899,"score_display":"92.7","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"24be2aaf9baf309481c1318d8297536c3fafee42dfa5c19e946f68abb72265d8","measurement_key":"673c1da29e1cb39a9e91ac69e8c20364b3418bf536945d1b224888f222a19f36","metric":"accuracy","protocol_fingerprint":"09baaf16588d7f5bc1e8de8012f98dab5ae18981e2a53a7c6e4436443eb3a964","run_fingerprint":"7aecd7a7f8517f518150c7d9cb38ee8c4dd079f3e63fd3ea3280b725a436ee17","score":43.141798,"score_display":"43.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":41,"at":"2026-09-21","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6aba23d8edd08e46344f9582df9ab0391de2a090bd97fed0a83f8f666ad6f9b4","measurement_key":"4c1bbcbcf182f6e38c9a828b49cc95a2ff829f07fe8d9f6038364276e3b909db","metric":"score","protocol_fingerprint":"e91eb17b8aabb913412d0a64c97a778c7d5f39fc41357f709c9d3521d046e2a5","run_fingerprint":"a81e4cf6a02455bafe2c8801b1b11f1aa79666dd02133aa16cecb1c6945f2b5a","score":57.722,"score_display":"57.7","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-09-30T18:53:19Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"77c6fe57f4ca3e4d1da1870e6a97ac26753aef3dc3fab5d915f2f2ddfcf55736","measurement_key":"62a8480fb3c73016ff76f5e52c58fde654236919647d2d252897e41a0d2930cb","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"e36b7edf5132d478ef50ec8da3be1fafc8910550c4a018f9ab48504baf38e0b8","score":77.39673809523809,"score_display":"77.40","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":30,"at":"2026-10-01T22:31:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f41329b8edf8d075e5038479d62c4f93c0b40c37ab9bc7dc3e77bd2596cd070e","measurement_key":"6309cc7f3b1e5859d86dd9c8c98892da3b8b917fa4175fb9447ffa4431905ddd","metric":"accuracy","protocol_fingerprint":"d7231f31960e21887048beffb2f74e66289b104736222c734247cea636b1a19d","run_fingerprint":"abe4bd6c4d2ac286f1b20a7517ff050ac47b3421700422d8a306e63a0ddbd221","score":78.150289,"score_display":"78.2","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"low","profile_id":"profile_cc4e54642b60580b7257387a","raw_label":"low","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T21:49:22.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1448e36cc7faabe0d0b509b012f4d753ccb657cfe7b49f96ddd447b5d617ad79","measurement_key":"8ddb3004764310aefa77ff847de7a3f3cb26ad55237d74219e1e1c259c48284f","metric":"mean_score","protocol_fingerprint":"3b87eef345d7e339a4cf86dd308fb014be73564b5beafbb401d4930cd7ab9441","run_fingerprint":"41aba1ff096d74786d55134b1164790cb1069a372e52b938a42d00a799d384db","score":98.05555555555556,"score_display":"98.1","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2456ef9c7a7c6d932c83fe384f21c607e0c28d20348514e364e1ee1a148d670e","measurement_key":"197b547e64d6d2152855e4330cab0c5d57bbe3e994628e28b9502735c76b2a75","metric":"fully_resolved_rate","protocol_fingerprint":"fefd96bf3cc9d55c2d71409e0324e0af7ddacc60a19bdabf8a5b78817cdbad31","run_fingerprint":"8deaebecd8a549e2dc2d0cea56ad7c68b68c50ea015b9ac1d324ac425c02e46b","score":0.5,"score_display":"0.5","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"47d560278655e6452d2002905118eb3da8134c3648f294d0c9f727ae6c209489","measurement_key":"b381ffeb26db51225975cde9a5a0bc51221378634ae711e4f19501c2b419a974","metric":"subproblem_accuracy","protocol_fingerprint":"a076f02a0a1cabf30ff29d1de05cfc8638bcfb219418daffee8ea3ca5f8ee1ea","run_fingerprint":"5068f0a09de5cfbc0fc1fc2dc4c80388e8e20ec64d3c91d781dd74c9e7009b3f","score":57.4074074074074,"score_display":"57.4","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":39,"at":"2026-09-22T21:49:22.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"aac34a5d4373f0d7414478d1012f33a6baccd126c99a95533bfb9cbfd3814154","measurement_key":"a8fb998ae3c9b3142f6d8ffbf0cbdca8aed0700f276fd0194e268b930d8b66f4","metric":"accuracy","protocol_fingerprint":"43c130d8c464e692585f692717ab455f3f31e03573c611e2a24208f0bded20af","run_fingerprint":"07ba013d843a0fa5cf903364bbbc925601a36d4a560cfe61c97759bcd18ba6a8","score":56.00000000000001,"score_display":"56.0","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f10f0d85821a7506bc608059fb4c13932d57f1199f6a627a384b9d82b8197467","measurement_key":"a3d9509591bbfb6b4177770126420355c92772b9d6ef56bf5dfed2d8138a7ebe","metric":"fully_solved_rate","protocol_fingerprint":"6a6d24508a05f708213a21c176a001b4d49f3022b5c32984791443de5dcf295f","run_fingerprint":"d4cdb78dc92f0cc6b34a50f1b796cc9d5c70d749794d2e9f4f4121a5e70801ec","score":3.817,"score_display":"3.8","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-09-30T18:53:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1ecfd7d0148a97f138a4e76effc13e43955384dd34fa304c1f66b15900750656","measurement_key":"852c41f7ef41fab294a27e06e5289e82a3aabfb06403eb045e5a2fa4a4742362","metric":"accuracy","protocol_fingerprint":"b9748d5e3cd8dd853b51324ec685115602dbb87a372d953b1696b8b5791c6ca5","run_fingerprint":"cc143346cedcda08e67192268ecb7da2becd2e1a938d550d1d3ab26e141d6a8f","score":73.408,"score_display":"73.4","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"283d2a85dbf853ac34a4b3ce7b0500d4518bda55c264400cddd21390023a1841","measurement_key":"9059b3dc2b842b15988e0a4ebe08d1436f2e6ef254fa5c8536c2fe8b3a1a05cb","metric":"accuracy","protocol_fingerprint":"398e926d9443cd1abf77adae8779775a763cb722d025bcced02d39a5c3863a35","run_fingerprint":"69f8bdd530e28edec395753453534f0e708273a2cf23afa5e9c752a146f1e47d","score":28.788,"score_display":"28.8","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8a82a587a93bccbec2db67cd17e5068e898927b833b9eb6f3f4506ce5151c9ea","measurement_key":"6353b9de16b7b9b11a51f4327c6840f05175d433ac1ffc2d1ba7e057806e35e4","metric":"accuracy","protocol_fingerprint":"ffc7535fa6bcb9010312382c5ecf9b4af78aefc293056d5484eaebd56c88a9f6","run_fingerprint":"c12e3eb06c3ff056eab28d1fd30ebbc6d2de7ee06120f318a6300a1503f0d98f","score":10.0,"score_display":"10.0","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:14Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"61e0c7bb2e51ce788900a66c660b014ec667cca553d9b039487ee2eefc28b1ce","measurement_key":"a95a4af194e858b09ef740f289a20a2821d283f28db1d9c44e9ecd4e6edfda56","metric":"mean_final_balance_usd","protocol_fingerprint":"36f069c55af8c61cea81e24a730a10a585696877835b2f60a92ae7d9ea314372","run_fingerprint":"5e1f59ec090f2cc839c2d7c4d17c4af2b37c0a33015e9c1ade7339a9b6d80308","score":10536.831666666667,"score_display":"10536.83","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4b6b7e85727e66180cb268e6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-09-30T18:53:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fe271c4c856592da2451fab5d1188fa69683b395cbf28e81c9db0759d687ca12","measurement_key":"b4aed726429e48683d0387c4ab4372afb7e2926cdc8e31ceaef5fedb52d0808c","metric":"score","protocol_fingerprint":"da3ab17f506dcb1435a5be4fc1dfdc76860308e58a0887ec74a1983cda8e6c6d","run_fingerprint":"5889713918388e329e60a4b2948c65c014732c771b1c786a1420088e12668f56","score":86.175,"score_display":"86.2","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c30cbb090dd69473c8b39f0ca2a9b809213f5974bbd4eec0e0aa5ed05d1b1b9b","measurement_key":"0f0a4ae928f620d610570cb3690514550e1a8011889980413d5fc82dca2b6b00","metric":"arena_score","protocol_fingerprint":"d0eef5b3aca0d99e446b293ff5ed4773674609492f3106653f147842e994e5bd","run_fingerprint":"f180c8d09d884e6850d54eb9a9ec2ee88c5f73aa309ed9849e03bcee713204dd","score":1637.4572057581888,"score_display":"1637","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a8d0de3e87d58dec3553f0d1b7b2a008eece8b068d357f916eda9dc97ba1fc08","measurement_key":"1a0b85f42c0ae46d52fb41552617b78ef66809f7b249e62a2ba90535f0965fdc","metric":"token_efficiency_weighted_score","protocol_fingerprint":"9e4f94b8c03d7f64b491f2338d82f7228bcf29e154c1a6d90f2ef45087000b39","run_fingerprint":"70c762d78bc471b71799de1c8b6f90a9f3729f6b27164fa51b00505972c9d2b8","score":8.452663636363637,"score_display":"8.5","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_1105264d4579e04e2c6a4c9c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"xai/grok-4-7","model_name":"Grok 4.7","parameter_count_active":null,"parameter_count_total":null,"provider":"xAI","selection_rank":43,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6a3d44e47a6f739815284cde192c470f64dc53fe7abc492e9743a3f3d17996df","measurement_key":"3c267f0518ed2cbc75732746b48f3102aab8ea9a08ebc7355b19c7efdd74d42b","metric":"performance_rating","protocol_fingerprint":"5e43d648a673b4fb850af65f22c490376fc0f5a52012a0a59dd674757e7382f8","run_fingerprint":"4aa25c7c0bcdfc72fbde73196f1cdd59e4e12b753ea3bc89299f6ba7747027fb","score":1309.28,"score_display":"1309.28","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3ff9ea23bd234d06b3bb0ee3307bcdf5dd1bb3a5c955a7216fbd56dda8979fe1","measurement_key":"45e70feea84fafd926937cad46afdab285b31bc91c2e78d4289d044d8d55fd0e","metric":"pass_at_1","protocol_fingerprint":"6c3b64469d43afb0bb8a2917614bc92a8560dbf8c565fb26ac9de05af91ce1ae","run_fingerprint":"b5ba9bcc823041ddeeb351200d54fc9f224b119c76d5a1b670df6f0c8a4f6bd2","score":56.2,"score_display":"56.2","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7b5a51c768e676f4fd84a86a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"75116117690af31d02f75bb1429c7a4cc94b1495a8b4050890f41a3b5e0ba2a0","measurement_key":"ea210bd91e326b2ce8de493618ac2d356e6986823fb5366976a33eafe53f852f","metric":"pass_at_2_accuracy","protocol_fingerprint":"0be15b5fd304eb56ca0f44856d57eb910ed57bfeb05acceaa66240d6bd25a138","run_fingerprint":"0640d6a3c7b39f42786a91cd8abc13b15bbece4ec738e7d8efd953bb7e611dff","score":85.67,"score_display":"85.7","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a3cec82218ad710b7638b97c2e3ff64f5e88b0449544736d1e7a59e6b4feee1b","measurement_key":"f3fa81c1895bca3b3841ebac9a3465fc4850e6ba443e301d937913009d6d319f","metric":"accuracy","protocol_fingerprint":"71362c525a715c2754a7cff2c2545649c1c0aff25800e6118476191022c6b207","run_fingerprint":"b30b1ddb9425bc4dc2f753fb7f88d326aaaa25f12cd213d8d4bd4f98773bfd65","score":52.64,"score_display":"53","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8380fb710a7cac0a118eaefecb751048f8cb8cc12ccf4d715e60f6b89454ef9a","measurement_key":"336773577fe6558768415158f343347b806db0aa08023a37e29076f79adcd2ce","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"fd5e527e7bae79bd21fd1a188931825f6bcad9de23cf371270316d1ce24d6add","score":1465.4464199324245,"score_display":"1465","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7c1e5a04c3bf319f34e54098","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:14:23.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"12a828dff44f211c9cfdc1f056016e156fdab15ab71ccc6409f53989993d4077","measurement_key":"598539929d94abfb42c75fcba31e648bac5b3777b296e5eab078e89a72fb7265","metric":"mean_score","protocol_fingerprint":"9cc88178e492b7de42f9fdd7b84ef537c11e8a58c110bdbd5c980649721be921","run_fingerprint":"bf3bb9e0512b767400620e684c253b33796c519fda3c786a127ce019d1779742","score":35.0,"score_display":"35.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5c96bc17ec6151470f73b3fab55b84763920fdd56327fb8cb70f720addc0b5b6","measurement_key":"637f2448705267279120f742ac5228af2267da3252578363d1e9eff0f2f1f1e4","metric":"accuracy","protocol_fingerprint":"01724d8acddab79cd8a6dc45e06906c7804ae19aa3f98d297f91bd3fa39c645e","run_fingerprint":"e816e19d961b770db1d8d9588b56d2664be9c2a2ec7266493d08a27b22b5c14e","score":15.4285714285714,"score_display":"15.4","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"03fdb0b16f77c8d43b91f1c1f844c1e2645c3f0d14f22efd0084630ddfa61b76","measurement_key":"7c3e0b54427a1fcdc402a93670850efa2abfa5615ea46ddf1be75de259aa5c6c","metric":"pass_at_1","protocol_fingerprint":"92509b6905548ce6b2e9db8427bb6bde696ae1d9d7d8b138aa5e5c11b885c7f7","run_fingerprint":"98c6076e0851e228353e6ec4bbb40052ddca9b08593f86502d28236cef4cfc63","score":53.76106194690266,"score_display":"53.8","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6e141c3aa218cfda873d73154196e5e691491ba8b6c34e758e7cdaa8b947931c","measurement_key":"ec947dbb029dfd49eb1b2eda7b8fc645f252a594f67b5d9b67ee9ce07900844a","metric":"eci","protocol_fingerprint":"3356d89e877509f21c7113b9241d784d738cf58adb249c1d5943aa569f22dfa6","run_fingerprint":"33b3511c468ae9cd146365d756ba3894eff388f29f1188fc7a3ab288f7be4698","score":154.36,"score_display":"154.36","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_cb44654bc85aaf39fe593479","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bb45dff861b188b806bd95b76ba3439d9c39cdfbf0a10d4959906bc4bdbd0477","measurement_key":"09578674e78d303bb0b56dd787b2d2ad77aeb361d58a7b78b98d04b8d3fbd37d","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"40f16d3459455495eb47f3033dd5b0fd57b39ce300086fbc9e2ced61045e5710","run_fingerprint":"3bc12b94bd1354cbdf79f1e3c8e8be9ccb52e8207abedd2b88f51c34b8c90cef","score":42.44,"score_display":"42.4","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":115,"at":"2026-07-09T01:53:42.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cecc05e319492c41f5b5cc784471f244dcb023783eb7a5d8a8105e0467442d3d","measurement_key":"ef235db64e49e8ce815a41477d28c5f84b24538e115b8c6c0104414095bb7e1e","metric":"mean_score","protocol_fingerprint":"b6614fa95b24c1d92a5abd67890f0e700c4381fe4735c9c1acc943007f927de0","run_fingerprint":"9e2c46ddba31a61086ad167338677381bcf3981f298c1842ae7305e0aeeca29d","score":57.19298245614035,"score_display":"57.2","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":115,"at":"2026-07-09T01:53:42.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"69b9b160c4882329d88a688d7a8d2e3f8365445c4eaf32ac5c39145c167363e6","measurement_key":"f45b8adc5032985f3ba37288d456a0f22a054631678c426b9dd40817af73ad28","metric":"mean_score","protocol_fingerprint":"0cd213659d79ae2397b7ff1939e91844219063f5993ae240a46e4183d90e0845","run_fingerprint":"bea3edf9d0610afa29b0bf649411d364f2a648c8a16e89f73c420cae9785e63a","score":24.390243902439025,"score_display":"24.4","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5536839a619e4a5927a49ec7f058001b2118f396326e8bd6c3beca202fef78ff","measurement_key":"fa13238765cd9883f445b3b93f7db0a3a4428316b12e1df193af4d3ab4c5db88","metric":"elo","protocol_fingerprint":"df466eda8afa1d45232539b4d8e1df2cc8fa4fdcb291394148c92305e8d6fb1e","run_fingerprint":"913e3fdde55f77307a6ad75fbba7895316457cb4a7135a7add0744c34085353b","score":1389.32,"score_display":"1389","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ef9e17ed59fa4409a51f4f2404018288c2356305ba315e6fbbf57c12dac3d754","measurement_key":"f885b614efc08bd6a042f5a04bec281b22a8b4515f18c4a8503de063f25dfcad","metric":"accuracy","protocol_fingerprint":"2a8aaee35acf7ffcc1c4b7f3c771197affac6a9935489acd67fa9d5e46824496","run_fingerprint":"83159f4b1bd283f2d2b8c603b455d887524c1a14ab790488c9cb8da852145adc","score":92.929,"score_display":"92.93","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d1378b7f32cdc6ed7782377e167c98a22a301e2306f7738f8e6d1962a272f2c5","measurement_key":"09d645273e039b0c2e0b3e555fc9d050678b520e17381dc3fc19fd30ad6ae5d4","metric":"accuracy","protocol_fingerprint":"9ed249e49ef2d928fe3f70ad57eb328a3ff34b2b25fe8281440621d9c32f4087","run_fingerprint":"34b88495ef8a7de06426180d152c4330363080c5b1888153f57d362e06ddb686","score":42.678406,"score_display":"42.7","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":47,"at":"2026-09-14T23:34:42Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4f11795d6fa349bcfcac5889b44d4cbf2d20ce438d32b508ccb4be0b73aa018b","measurement_key":"0ad5823390038867ea19ee0ac2822f97117393bc03f5fe1b65c22797d86d50e4","metric":"score","protocol_fingerprint":"8e196fab58e435ad88cd489105eb1c155bb2cf36433105ceb6a6671fea5c817a","run_fingerprint":"985c633390ef35d20ca3981c6e1812b8cfac14b717e4392dc574bd82f472fc38","score":40.556,"score_display":"40.6","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2a736bd66e96a719635e8aec4f56f35c5d638ce557df18acde6e67989ab7c4d4","measurement_key":"a2e70a9e30fa976273a08ed3e7dbe7347fe59d505ac732edb5a6202383b8e2b7","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"996fff90b4da941f85081c855ba5684938c9975a9674b24fe743f900c86485b8","score":75.77284523809524,"score_display":"75.77","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4a583e289c2d0896454de86f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"487cce8dfebe52995291057d10c071675618d00877e89229ddf0924a33c63a28","measurement_key":"161566e0f2a03f7c6555c9c221f1c3aa4908063acb36043d6cea5f3234180ec1","metric":"pass_at_1","protocol_fingerprint":"3a0567c444fb0b281c0f3337ee2dc3ebdf76cfe4a87783ae18d30ce6c98c01d9","run_fingerprint":"82cd7a725233cd77e7a6373d819cc0e554ca39e3ebbe1917ccc4b4cf178b39ef","score":87.351,"score_display":"87.4","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T16:49:00.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"96ad08880242ddbac427537de739cdd61c5c4ca8cfaa8a1979aed10e09de4cd0","measurement_key":"559a9ebd51d0f65757d202ba22a5c7b62ca86a5c467985df8569179ae163da45","metric":"mean_score","protocol_fingerprint":"290a92db8b9ecf0be0c87a2a891515e339b83acd8be75b9a325dc61e52556dd9","run_fingerprint":"45c9f31f1841126854104b0be42c5f29627803fae8e38291a4eb2d45f00a3d5b","score":32.22222222222222,"score_display":"32.2","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"82d9e5855b57ee585e0bcdfa0095056c95629115fcee9e097dabc47e535a84e1","measurement_key":"b0aec8040ae41a4a98a0c5810b66bb979c325f95711f6d8de59e6eae5acf546f","metric":"accuracy","protocol_fingerprint":"30783e9e3e504467b7393749b69de46b5ab86c389a05e1c12e5ed4c6204aef96","run_fingerprint":"f61c65a2db448df13a57d0533e6b8fab4097a41c56e5345cd70e987dfc5f3570","score":89.216,"score_display":"89.2","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:41Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a6df5ffcc009a231d58c987e0a65fb3db928c1eae737d0742e90b7112026374c","measurement_key":"777b5f4bd50b97ac5f2f3b339f4d2c0f091c33922acd518a2c05f5d4f19ce93c","metric":"accuracy","protocol_fingerprint":"9cd973b156f4b2c6098b25ee60bd123eaf7b9b0ec7ab107f6adad140085ef369","run_fingerprint":"f32f6562fd47d849cc62dddf11ced8e795fab5ac882129eec9bb736d91044011","score":61.792,"score_display":"61.8","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":115,"at":"2026-07-08T23:54:22.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"09865fb30b11876232e160140966492084bd57f18c50486bae0ca2a2407bb6fb","measurement_key":"6c20fa905b6dbd082dd0cc7095912c2d44dcb69ee7a68dc55ac6a93baf8ab8f1","metric":"mean_score","protocol_fingerprint":"7cbf38020bd69bd48d8e8fe29843f017d6e1e5a9a361c88d9b00f8b0f310957f","run_fingerprint":"fc7dbbc9874b78d984db2db3a8889bccbdf004d03d103d2bf3c3667f4ea094e0","score":97.77777777777777,"score_display":"97.8","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3e634d9b4a00a218d313873262457e33b3ba484989cb95f40ab5ae5dad7913f6","measurement_key":"4173029a3cd19720ac4f9817233c218de55b250e5458211065b4f4068b7fb2f6","metric":"fully_resolved_rate","protocol_fingerprint":"46edb43243e433304d7bc1caff80231e6c2094235cece27d53a400398ce45f7e","run_fingerprint":"6b0a117f300dbdd4a58fff62e23e84be9dde5443cfa37369e1e8f856008e96c2","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"937ce4456e034b5935dd1c8df5d4fc70ea7c5c969aa56be7687c907ec19467a9","measurement_key":"7a8f23bb4967b96469f958e30458764af9d79227662d315285560caa008e7240","metric":"subproblem_accuracy","protocol_fingerprint":"1ced07f516399abf66fa226f9eef7b480a06804ce384c488f55b773e6dbb857a","run_fingerprint":"bb1753266f698de6a9bb44bec517ec797a1b8bd739d1aa3190e31a7ad0ab8388","score":54.976851851851805,"score_display":"55.0","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0d056695c37263ff0039af3287c084fc64a1f35dbf8c3c7589108f0fa7397218","measurement_key":"a5b2e04e1583f2bcd5ecc70cf5653895d2aaa6a737aa168d481b1c8bb8e0c303","metric":"accuracy_avg_at_5","protocol_fingerprint":"7eb48decea3ecaa512c14af260f93c5830a0a514400310caae0df1b4f8cb7406","run_fingerprint":"8b59d9c1732320c15478e97067263669f6c1dc4edacbd795808a68a3752e477c","score":70.0,"score_display":"70.0","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e2a20830119d2bc9ecee925c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:29:30.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"31f9197b29055842baf3b68ae89d6ab91a34440a596181540da52960b3385fdc","measurement_key":"fe94a34caea70a088d293c1428c8e52c7b9777631013ef71e967b6c1f52fdd3d","metric":"accuracy","protocol_fingerprint":"708704be34be87713cdc078eb35d334a987d1955cb120dd9aa7ecf74278c21a9","run_fingerprint":"6505dbe0444b4dc33b9696e49a581e4e3fda81961d30825d3a97f6a2d2dc950e","score":48.3,"score_display":"48.3","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fe70686e9daec8d352d76562d957d124ee528823e332328fe9954d424bb35eae","measurement_key":"fed23d94c57db973b48b3d764da5c955b1f4492c2335542670db86e2d0174117","metric":"fully_solved_rate","protocol_fingerprint":"db79727d67c5d372e5ec385843d53c8e2a86e4534323296a600d8a5c115f4f56","run_fingerprint":"311140a186bf2d7398e87e51b514daad2a09ad620b8dbd6113b09579e95a3098","score":0.763,"score_display":"0.8","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"644c3601bc5f5236d2d498666ff496e2e0f8f68b4d74b97eec604ca3afad5f23","measurement_key":"eff9f964dcd10f41db5833ea6ef064ba2ed9ab871eb029cb5889730debbf260d","metric":"resolved_rate","protocol_fingerprint":"91004525e8a60922427166921e1c489608e94441bdad6fd99d92565b6cfdedf8","run_fingerprint":"7f246c4dcd71c90b483279b4d3f6bab453146659f03621ded6e1e1511b9e88bc","score":86.6,"score_display":"86.6","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"644c3601bc5f5236d2d498666ff496e2e0f8f68b4d74b97eec604ca3afad5f23","measurement_key":"eff9f964dcd10f41db5833ea6ef064ba2ed9ab871eb029cb5889730debbf260d","metric":"resolved_rate","protocol_fingerprint":"91004525e8a60922427166921e1c489608e94441bdad6fd99d92565b6cfdedf8","reporting_origin":"organizer","run_fingerprint":"7f246c4dcd71c90b483279b4d3f6bab453146659f03621ded6e1e1511b9e88bc","score":86.6,"score_display":"86.6","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":62,"at":"2026-08-30T11:02:42Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e5b55272bc0c8263a108183c1c1c1c8e50c1fde3d297af19350011aceb9a4b89","measurement_key":"b5efc1b95f37a111e4e01a7336a0d0e104ada15089605bc52b51b21de24540b7","metric":"resolved_rate","protocol_fingerprint":"c7ce3d3dbc15c2d5de949b75159fdd0c0d5fb476e04271616900e73893ee28cf","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-05-15/2026-07-01":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":62,"at":"2026-08-30T11:02:42Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e5b55272bc0c8263a108183c1c1c1c8e50c1fde3d297af19350011aceb9a4b89","measurement_key":"b5efc1b95f37a111e4e01a7336a0d0e104ada15089605bc52b51b21de24540b7","metric":"resolved_rate","protocol_fingerprint":"c7ce3d3dbc15c2d5de949b75159fdd0c0d5fb476e04271616900e73893ee28cf","run_fingerprint":"fa3b83b0c0df90cc80d9e3128d37165269a9df7f39d09d19a60fd4c1d5a92287","score":63.78378378378379,"score_display":"63.78","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"}}},"run_fingerprint":"fa3b83b0c0df90cc80d9e3128d37165269a9df7f39d09d19a60fd4c1d5a92287","score":63.78378378378379,"score_display":"63.78","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":100,"at":"2026-07-24","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"531add623541a6ba7d561e60d248944d86a0553de2fe948f27cb34264ba1cdae","measurement_key":"412c0e8ce4f1bd6b5ca51d0034385e84c797f2328428b7cdc5c7be078618387e","metric":"pass_1","protocol_fingerprint":"5e904dbd73f67cadb131197389e5eea603a8f90d31e89d354571d853b5d36e5f","run_fingerprint":"89acf922f06cc52fa6d098711bd3dfc117a3439012a1b61ac0380d2cda9af829","score":47.93814432989691,"score_display":"47.9","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5b85e46971c8d0e1a2f886a0e1fc1b277f55682b40ec80a902b71f289ffe7652","measurement_key":"dc5ce9298bf31ad35b25a90a871a72b7cb0c3506ae1898de0cb18fb59e99d1d1","metric":"pass_at_1","protocol_fingerprint":"75d8bf7afe74687378deb70dd0c118ff0b09997f4dbbda5c6f173943d12a2ea1","run_fingerprint":"dd328c124b4f720cddeb19ca8aee35e0d4fd0a4feb1d2df1d789187d7eae2182","score":42.061856,"score_display":"42.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"56cbd9f6de12dff4a023145cb09da184d947932170a4f43d20601f7e4cb63749","measurement_key":"cbace0a9d2f2a1d6fed54a6c550c7cb4b428d4c8f59819f32485c7c2e83c6eb0","metric":"accuracy","protocol_fingerprint":"99c1674da391fac1fd1fbf85dea47f0c8de61ed2e6d19c0965904d9211e979c7","run_fingerprint":"17f770532af16040dd3affb6cfa9843326357bb9c6fce0e8954ee60bee792405","score":67.79,"score_display":"67.8","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-3":{"benchmark_release_id":"release_ceb36f25882d8cea2c9d084a","benchmark_version":"3.0 · b936386b-4afd-4ad7-aa7f-6b52bcab9853","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":80,"at":"2026-08-12T21:39:34.661007+00:00","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5c089362da083b33cf9a25499c6a3d560c2f76e2002cd285e9f26504335c9dee","measurement_key":"62a786ecc69bf4b482594178749719611fd86f7cc36c8b6463dea3274a08d8c0","metric":"accuracy","protocol_fingerprint":"caad2167d6277230a98c08d572a03818e1f18c1cbb389f66f957eb8652e6e5ac","run_fingerprint":"327d9c632e04a2ae64e7b61a9765629ef0d2e0b70fed6d0254fb3c60f995a547","score":15.68,"score_display":"15.68","source":{"id":"terminal-bench-3","name":"Terminal-Bench 3.0","url":"https://ofhuhcpkvzjlejydnvyd.supabase.co/functions/v1/leaderboard-read"},"source_authority_tier":"A+","split_or_window":"official-74-task-leaderboard","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_cf7ce74acf6af29a63ba09f9","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"59d6e460b2a909c62f8da1df66f1977bf5b8c6e55df8491598118559877f3668","measurement_key":"f9e9fe043139b07452c8ea69d72b0ad61b3ab8f20094f5343a048d7c89e0d493","metric":"accuracy","protocol_fingerprint":"a431bcc5a38cf066e0c8266838a434cfb707d81260ce4d9a6bf13c91965c05b6","run_fingerprint":"5dd4a8c901f2d6972965c5a19d6790f1efd1ae0a2e7f94f5f46034344ea39bb7","score":8.586,"score_display":"8.6","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6d4a14e7448f5d085082eb9d05ae3d96d2c7c30c69c5cafc7a46e49faaf31f65","measurement_key":"58891e1fd20cbde1394825538178c31faddcbaeeb26bdfdc9d1ad8263dde1ec5","metric":"mean_final_balance_usd","protocol_fingerprint":"a9af951f1de03bf9cc633f76e5734942b582f6a9d28975187544eeb7ee252bc5","run_fingerprint":"b367e5577c4a8e8e69c31dc564a4accf642a23daabacc9db25f7264416a9dad8","score":3887.4259999999986,"score_display":"3887.43","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_22b572a08df9ceebd792a8c8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d872caf51ed0b39e93e0de26da073b053524a69471af30bfcfe7235bb69dba2d","measurement_key":"31ce98e74ef7ecc131ca9cdd75c9829c3902c75146a6fa809ed50f15c3f6c8eb","metric":"score","protocol_fingerprint":"cbfde0619c414bd4df277224befb997e5f6578498ebb9e9643f94192843e9cc0","run_fingerprint":"dbf52a394c9ae8e25fcee7f21d35e9157f4b35dbb3054df4c282a5b0894a531f","score":69.002,"score_display":"69.0","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_b7ffbaf8d89bbaac429d0b87","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"488a681974d5a218eb9c55daf7db24445cfcc201cf85ab6c47fb97a0bce73ee3","measurement_key":"6aa8f9bde83236b426433e6f55e4b278507a64348d8a2afb86ae03d204223417","metric":"arena_score","protocol_fingerprint":"f7ef2c075889f128d0b6e2992fb0632ce71f357201cd6e6aed06bdba3b209721","run_fingerprint":"c90aaf460373371a18fbc8e4cf73fa274a4fa2e8143f2402e60780f0b8ed8bc1","score":1553.032541111338,"score_display":"1553","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0a2cd2202522f2c34abea7da","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7b789d5e1cabd09cf83dfaad6aa79c1ef668a7ec0949bc40ccce5c0e5edd07d3","measurement_key":"3530a1c0a23b532d9f0b34269d0d921abffa458da80904ad58169c25a54c54d3","metric":"accuracy","protocol_fingerprint":"2b35c9e6af9f4c3d2d0c9da17a6e48ecc93aa147e7c71b994af82185394750e5","run_fingerprint":"954f3123561471df21be35d750c0601e4654bd01109ff39a5b93c3d81b0ca7c7","score":46.43,"score_display":"46.4","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_bc00c246c21133ce08995d8c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"xai/grok-4-5","model_name":"Grok 4.5","parameter_count_active":null,"parameter_count_total":null,"provider":"xAI","selection_rank":44,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ac075713df149595a16a9cc24cb902d6724d9e437dcdf2f4db476323ab7bfbf7","measurement_key":"25623c6e15603192577b016cb43b6a0cac85dce94c2a4b3161ae30db3ae357be","metric":"performance_rating","protocol_fingerprint":"921e8716214d093a8a220fc7e1c823ee9f3af73c6aebebe12122685d9c21764a","run_fingerprint":"ea0007d8fd8489216e0e73f76a5147aae00e2a86a90fc4d1f9f185e3dbbf5d79","score":1189.4,"score_display":"1189.40","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d772c2aef798e310edb6ef13","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bc8ff902d0ff5f06839ea27996704cc3d2d8c536e945630954829f7c707fbd7c","measurement_key":"cfa59de1531064cf6893257841189ae610e3f018afc9e221f256b125b377f38e","metric":"ips_score","protocol_fingerprint":"15f5fce34de6357feca787e195d1553ff7d07b9ff955fcd842be20dd4ae903a5","run_fingerprint":"82961265780ce4c7bf0c2f50f19258859fdd639fdd19477f0d3a731f0df661ae","score":-0.06586293614361291,"score_display":"-0.0659","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a11f0381d740fab28f4a990c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"29b83070299a20d6bcfaaa8c79854fbfb04973d7b44994ca83af81195507e57a","measurement_key":"691b87cfeb19b0436c1790c9808f2ae2ade09a16e1b9b03753b13194ad87ed74","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"c3b45739fe75b07836926a115a1c5f70e60d63c048120a15ec8dc287ec9b70c3","score":1473.7034427077983,"score_display":"1474","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4220a4a6f1311bc74f0c6484","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:33:00.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3fa090c062e9f1fc2e14356f5ad8788a38ff9caca6052783e95c417dc3d94ad5","measurement_key":"59a51254a233dba19b7a9d1378a7e0953d03485b0bbc3d3f29299c3260cd80b9","metric":"mean_score","protocol_fingerprint":"75149d26e5258c61b30592c7149b54f99213b246326aede07c4926cf81ac0ec6","run_fingerprint":"08d38057c72b066dd3720affbc5a6595d13826b651c306b39580e852bda15acb","score":26.0,"score_display":"26.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a74bf66befbcb7f81dd6ab02","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:41Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f79dd9581706f064c216341d18d40e31ef38459045cb7ca60ed0c2c3f6a2b117","measurement_key":"0a8c688e0e734355ab9d45012ebf3f1c2ba2708d5161a43a6e209caa722b4a07","metric":"accuracy","protocol_fingerprint":"91f50faa87fd0d841f330a8c7b2b3a0bce11c7f101afbcf432c347910ddd411a","run_fingerprint":"88551b7877cadcfc05839b5537f635216f76ca9f527b608a1bfb955d521a3c62","score":13.4285714285714,"score_display":"13.4","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d772c2aef798e310edb6ef13","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_0f94a5c34a87744f357d4816","benchmark_version":"DeepSWE 1.1 · Qwen comparison run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":81,"at":"2026-08-12","last_confirmed_at":"2026-11-01T03:42:36Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1729584b15d82d058282a9ef97c57cf522f9d2c7b5d81e4685df92b5e5c0dc2d","measurement_key":"dd9a838a74c58aa192111649414409044a3c68babae89ad7514cdf4b9c39c95b","metric":"resolved_rate","protocol_fingerprint":"26f7dbbbd59c10993e81bb31ec607ed81e91dce338e64d5c3ca6702cda935db1","run_fingerprint":"0e2a61089a7bdf299d96d35ea04a1681b730f592a7667daf9ce0042a44fe6079","score":21.6,"score_display":"21.6","source":{"id":"qwen3-8-a95b-card","name":"Qwen3.8-2.4T-A95B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B"},"source_authority_tier":"B","split_or_window":"qwen-vendor-comparison","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0d904d7fe29e536b30a70704","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c6ee3f040d9d5c72deccd2bdbe02f75fc4ecc5ad3b58e2dc90de98d2eb6c211b","measurement_key":"dda64b71157a6815431360bdd2dfb8d7088fcddae5186b3ac15102aa82c89d44","metric":"eci","protocol_fingerprint":"94af1f4d5b004df756ceffff6c0ae4ddf968ce83962e445af69cf84d736a3feb","run_fingerprint":"00a22d3f82951181d0ae14222caf1f2d0ae4a3f4e0cb70d8776e39413c34d186","score":154.22,"score_display":"154.22","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_438a0adfb228d31d4956122c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":141,"at":"2026-06-13T03:08:22.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5f70c4002615f5111a3959cd056ccf67a8b7b9f4467c858e78442b1965286ac2","measurement_key":"24fca7d71cb165ca0916b2582f9d97c93cfcb233b097ea7fa38461a35906a94e","metric":"mean_score","protocol_fingerprint":"664220cdf0cfc70a17f9aa1a388d66675817155056d69c7725a6617df98310bb","run_fingerprint":"61b59bd68901a84213ba31d199668291c65dc98a76f307363b77e61f7b739df0","score":64.56140350877193,"score_display":"64.6","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4a082360cdbfb26695a8efcc","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":141,"at":"2026-06-13T03:08:22.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"03733d880442dcf5b64eb5a7b6f9c082e47c8558f864897af6b62acfcff8cd95","measurement_key":"731ece7172ec886df013df396f0ee8f33352ea033e382d3d343d488be4372332","metric":"mean_score","protocol_fingerprint":"792de66b59f8316ef0e0a3ccce21e0a763caa123578ca4cff217300a967b5b1a","run_fingerprint":"4d0ff81e310b15d3cffad671549261918d521be552c0ec633a0f6e8a360cdeb2","score":34.146341463414636,"score_display":"34.1","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_898133c7fa458202db96273c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"74126c7317d5ac2412c940c3683e864c121115c29308b2aec54693eab03542c5","measurement_key":"a1ad4b7b75447de15007e2d06d707265adcc76e36290d9886bca55df2ae63e64","metric":"elo","protocol_fingerprint":"6472cc5c76109c0e8c0e0bf720a09f008491e120de73a07384de2bfa0c1b6aea","run_fingerprint":"6861a84590257cd083461d7016e285e1f7e6510c904d51b571d6cfbf537ed8e0","score":1135.46,"score_display":"1135","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b653e6b09c5d08a78703143b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a7fc22dc293641d29df9369c1649f95a3d26312646c192a4de9d616d470188cd","measurement_key":"47a634696dab8d5335087fcb84d553ac3b41d3d66b27f83fb6c3921df4dbf8e6","metric":"accuracy","protocol_fingerprint":"1797eeaac0bb99111e90ece69a584f98d8bcdae220648f20fc59ff1ad76c5d97","run_fingerprint":"9ce21ea579241cadce4279dd0798c5c886740d3cdc13497851b314bb6b7a9b13","score":90.152,"score_display":"90.15","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c851e77e82debc794fff6ed8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a2c677fe20e9f166841972b53296a41f9cad912c58910caf3ae8832aaf69116e","measurement_key":"14c50a6fc2e04763171d2a018cb036866367f46115ef65f368971fef8e0d1f19","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"15e63cb922421da8e22b5642e1fe2aeae3c2ed167ee866572da2610160bf6de8","score":73.13660714285713,"score_display":"73.14","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8a98f0234f2d8eb2f775b7dc","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3ea1d4393a90e42b67ce8612404c0b27c0d5cb54becbabffb6d42658b1913359","measurement_key":"05fbf8e573b814b975a7f56aac118719cd093be9de5c69f2eb24d97969b9de9e","metric":"pass_at_1","protocol_fingerprint":"337f5a3459785a096ef74e3c817e6bd9f080dd141ad6742996950ebad24555e8","run_fingerprint":"9827af0c22243d7b1b3cc9cdf61e31c1ee0a0d29f1503a7e8b0592b08d5d4e57","score":87.057,"score_display":"87.1","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e9712f59624c456abd520aa2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1b6b6d287a37ae899916b1e90a537d1c159db1f73877efa809bb93f9a58beba7","measurement_key":"952b1f814027daee68668639122a8e4e5b9e6e3d988a2182a63fc2e1c25eea5c","metric":"accuracy","protocol_fingerprint":"0ef4fa4822bbdc7dd0c7790eae132108d2c2bc17b9843999c396f9f4559d879d","run_fingerprint":"fb7091625697968065dd4e3bba4ff94f95d45a71681832474305861fce3573ab","score":89.311,"score_display":"89.3","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0e54016d3db95a8f54d1a2e5","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-07T00:39:02.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"be0bf1cce1d8e1e94e0703c4f390f60bb36211f9ccdcf67faad35afa102666e3","measurement_key":"77e8603f6018516e4e71d48e60083af6bd4efea584fd458067a9f5b97064550c","metric":"mean_score","protocol_fingerprint":"a5b341a2ae4d57ce93a4f520cbabc07ca59484bef7b4675d88563352687d0e12","run_fingerprint":"4f8ee2e5d94cfa918fb3a9ce5fe1edc918467d460d8b7a016034c3a86544387b","score":95.55555555555556,"score_display":"95.6","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b3e2c828e764c38eff97fcb8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"38875a5f0454de995f47ef262cbaf54107f698a3cf6567a7a4618bc048b1d207","measurement_key":"dc43b4036f7288fe49fc8773863db7c2f8aa7ddaceb99a16482ce554fdc35489","metric":"subproblem_accuracy","protocol_fingerprint":"c9f86708fcaa36df1d06c5b20b1487ea19b6b4ed0166ce1d63b6cd30bb0ca964","run_fingerprint":"9fbc0fe5397de6423e3cf02ba3c75d707436ae67dbe05081ed771e8ff84b076f","score":49.537037037037,"score_display":"49.5","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d772c2aef798e310edb6ef13","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c49f7ed6777a9bfcf1a71e71dfd6b417189cd69291168dcc5074171e283c6c4c","measurement_key":"9f1dfb0df357b6ff2560734ea71189b1d7b036e032969e597bc78b5c966cbe43","metric":"accuracy_avg_at_5","protocol_fingerprint":"29beccbaf009967b3fb5b2f9d46ebc0d6bb778cceb0260b854dd809068370284","run_fingerprint":"7089813c757b4e0b019034086c36220ec6feb416b17f8de82342642491dc0a2d","score":70.4,"score_display":"70.4","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_73d6450b88bda658f569c477","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:34:09.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4d4425dfed18342519838c5cdbc0957d75b1063a59c4f16e483a8bad30be10b9","measurement_key":"e6eecb8bea1d8eda7e40e0af3ec88e90a876ba07ca438df740241aae81ea2933","metric":"accuracy","protocol_fingerprint":"eb1583e703edeb823f406ba50e4126f2c85021e5a69a322f58b085a038b90fba","run_fingerprint":"01384844761acdcd679fbfcf8e1e42fd6452b3e4df4b642ab033fda4020aa132","score":55.76730190571715,"score_display":"55.8","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3a75cadcf4f028e0f62f9064","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"skillsbench":{"benchmark_release_id":"release_ff4a6e288c3c17d588478b46","benchmark_version":"SkillsBench · Qwen comparison run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":81,"at":"2026-08-12","last_confirmed_at":"2026-11-01T03:42:36Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0b4458942c5517b7ff7da7a12ca1e61d96bd31558641f769e07e419205119317","measurement_key":"58aad74d6ac108143626c6250471047a43488481deae386242fc69211ad178fa","metric":"pass_rate","protocol_fingerprint":"5a87a249627548ba41ab1e22adf8f465931b323f1bc4cc1e11b5f7988d5b1a3c","run_fingerprint":"e365ccca63745a886ccffc98dd77d5d3a48460c04323f088738897867f70d2f9","score":61.2,"score_display":"61.2","source":{"id":"qwen3-8-a95b-card","name":"Qwen3.8-2.4T-A95B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B"},"source_authority_tier":"B","split_or_window":"qwen-vendor-comparison","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0d904d7fe29e536b30a70704","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b1cf2fa70dce2998079516a33f81d27be51369094dcfbb196cdd23f348f021b2","measurement_key":"7d01d1a7e88ad7ccb52af5e21d6e52b8c56661a2117cfc666cd5751a7e310b5d","metric":"resolved_rate","protocol_fingerprint":"2fcb0eb9ad0659e6baebea2eb302f620041a4ec46e98b4ecdac7264d9ea2bdbb","run_fingerprint":"4e463f15a2658d06a97b6c6780a9f8964444941f63fad5ef4789583daa54e761","score":68.8,"score_display":"68.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8702741fcb32199baffce119","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b1cf2fa70dce2998079516a33f81d27be51369094dcfbb196cdd23f348f021b2","measurement_key":"7d01d1a7e88ad7ccb52af5e21d6e52b8c56661a2117cfc666cd5751a7e310b5d","metric":"resolved_rate","protocol_fingerprint":"2fcb0eb9ad0659e6baebea2eb302f620041a4ec46e98b4ecdac7264d9ea2bdbb","reporting_origin":"organizer","run_fingerprint":"4e463f15a2658d06a97b6c6780a9f8964444941f63fad5ef4789583daa54e761","score":68.8,"score_display":"68.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8702741fcb32199baffce119","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"09535bcd6be89dffe9eb1ffcb9e47746beacc76e9f85dc09fccf3ed70b82598d","measurement_key":"646d2b324ba5919db97fb2459fdd58ff9b0efed17df3bcbf72c9ed5ca322811a","metric":"accuracy","protocol_fingerprint":"612db9dc822ad0127ca02d953d2f00027f18f4556fa9f2ebd8563da305954e88","run_fingerprint":"1db710d74c3f09ca5c08868ebce3bb79a7f6a5e0942b5a57d2b59a6215eb5200","score":61.049,"score_display":"61.0","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9834bcc9b3e87e87a66577e8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f5ee8ab7fb7156f8a8fec8c3fab3742aa5bae0f5fde36fa4fb3aaa90209af701","measurement_key":"c69ab6f5bc165eb98a7dbea91bb278a73e5c0e98a38c36e74ad008d9fc12368f","metric":"score","protocol_fingerprint":"e45296bdd0fd9c48c3a514a81fad4d556c572fdb2f97fb2c3505e03d334e5532","run_fingerprint":"b0dc329898e71c57a427f461919f2c998c705262af7a71564d058c1582fedc9b","score":47.671,"score_display":"47.7","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_5db0d7d1f8becd7348837d1d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"821cdc5a846950737549e1121edaa7a732f27ad3b25851b60cd5c1f1a3024af0","measurement_key":"5a37012884ed241d61cc66c29b146aaade2f09455b79ea22c7e9f70fb91fec24","metric":"arena_score","protocol_fingerprint":"c221be49c9f7b24eda837bb55fb57138648e6cb4ad2bc348a4752587649f742e","run_fingerprint":"a054adb885a9e3112136eab9d72fc169da9cfe1974803aa31bc262dfb530d29f","score":1515.1361678106236,"score_display":"1515","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_93f8ad037c4bd04e2de7d0e0","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"alibaba/qwen3-7-max","model_name":"Qwen 3.7 Max","parameter_count_active":null,"parameter_count_total":null,"provider":"Alibaba","selection_rank":45,"weights_status":"closed"},{"cells":{"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:12Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8df08977f055f2c498938535fd37f20ec655e5d0ee9eebbded6fd44921b91a3d","measurement_key":"49d21651308f80569c67b4584cc63446b1e2e425ba158c97cc225c884358def7","metric":"pass_at_1","protocol_fingerprint":"f1f64516a91516ef2dee6544987d37bfe9ce300153eb3effddd38f983da5bb94","run_fingerprint":"ebeee9dfe22cc30fd5f983f865c6edc89e2832d8f11a171266abb25f8de46a1e","score":31.8,"score_display":"31.8","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_458ad66cb249e06fdb6aaf95","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"027c38508ee1ee2c04499adb29941a32e9be5f834e99b9e3952cd3969e076373","measurement_key":"f15190ea3a23982d40c17731d76990eccaf556830cde1a5741f4ed92191f446f","metric":"ips_score","protocol_fingerprint":"60b01f02ed9c4c36405f68356104ba7cc7a9781f3af21c7794c7a518e5dac833","run_fingerprint":"ae5019e3e316fd2d0f75ca745966100e411b9b3945ac7d1298eaa970d8f02afc","score":-0.0766934579263557,"score_display":"-0.0767","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_60c2da8ae56f193d786d0708","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d1070ce488746380f495b6ff70bebfa47ec29007a3969959dc9fe19e45f295f0","measurement_key":"3319b010aa6896dbdc52253e8fce985ef87e76446c42419320dcc7e3bafecdc6","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"37f4bf97dd1c683b5cc08d409d96fe7bad341abe39465c9a8153c04e40c37a4c","score":1490.2351603730194,"score_display":"1490","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_99814c21bc9361f199e3a520","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:13:33.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fcea5cf85b36c2dd99990bcd892111a606c8fd40d319168a304bdc5978e37579","measurement_key":"48f6ce431ca6ed95fc6dcd841aedb4a4382a2c1aacd55880b17cf9e93bada481","metric":"mean_score","protocol_fingerprint":"aab014abddad39d3755c5ecfb367cbcc57cb4069af5df8d584eae557b8f92d69","run_fingerprint":"4b35b204fa8d869012f980f716a020bd32436a58b2722db81feb8e5354ab7ef0","score":34.0,"score_display":"34.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_f65a7f664c0eb4433d5d5397","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"65ccc23508a058cd33abe9442a7a511b3e5d51190f830a8ada599541f9c158b9","measurement_key":"3a84b1c7c0ab0ce08f00e00d4104044092ba004c7c2023f6dacc60ff4a78b33b","metric":"accuracy","protocol_fingerprint":"2aa326f2519e1a10af2940c4581d65a5efdd1f244f87bbfaadb7feeff638287c","run_fingerprint":"d226c947164199cf42b44af140c8bc9d09d281fde7c0d07c1b352010bc219edc","score":15.1428571428571,"score_display":"15.1","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_f65a7f664c0eb4433d5d5397","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fdcc066f6b139ca82842e9053f1ff4383019e648a3c2a588c39aac61d680c8b7","measurement_key":"f318e52dffb01d31bfaca352645378caea7df8dff7d8c88074827dcdb5de7da1","metric":"pass_at_1","protocol_fingerprint":"9fa9b172911f42872d2217a905d99d07616d897ce35fabb291c5e9ab2403da64","run_fingerprint":"d1c241e03c555e41c0fa68926303824db73297f307756a1d8a0576db8f0dd4ee","score":53.31858407079646,"score_display":"53.3","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_f65a7f664c0eb4433d5d5397","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"eebcac453484d456a7e5d148a03317948642ea52f250641cb288928634f9deba","measurement_key":"5be27152c54f9f0403210c5f5261c2efba6b3036fdfc0e4e344e88eac56b5947","metric":"eci","protocol_fingerprint":"a2ccc4b27dbc724eda9bdb5a62a3d16d84fb3c9718347a54f9a0639ada6f9158","run_fingerprint":"147e0b7ce67d4e660e58d127e20b5373a830a1858b1614e68f105715561062c9","score":154.18,"score_display":"154.18","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_cd729d89537d94a3078f527f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2fee9caa64142e299728bcb1a9a29a0afe1ba17648f18be44ed8b117b5e5910f","measurement_key":"af239a6a00ca6c47da4cb70012862bbcad22669fb647985e8a1cb7de3c66f7b5","metric":"elo","protocol_fingerprint":"451b63da8bc955236d2c7eb34ff19569bdbd119e0e1bea553a226cada2372c01","run_fingerprint":"c2e24c0eb62e13612ef551a9a0128bf3de14496d0c1ac83f73aa56dddc6aa7ba","score":1217.25,"score_display":"1217","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_f65a7f664c0eb4433d5d5397","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"aa68bdeda3cd6061177600250fc1c7d5172c68abac197327f254c959d5ad8bc4","measurement_key":"14bdd2ea9136a7cc63372cd6dfd63e2183d50263b49edbc7b454c3aa2138680e","metric":"accuracy","protocol_fingerprint":"068ffd607359f63291ae31135ffbe94736591d10d6cc4f69a3b1faa658f51820","run_fingerprint":"ed0c328a1ecd7a93c09ebf6abc135b0f08ae5b672df5266cd1ef6926728fb6d1","score":91.162,"score_display":"91.16","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_f65a7f664c0eb4433d5d5397","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_5f3023448c2ae4632fe1a43b","benchmark_version":"reported-runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":115,"at":"2026-07-09","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"34272963f1a255e23d3a7525f678a28edd208a2a37fe40e21377f77381fb2c0d","measurement_key":"ae0bd486f0c0b8fa2c289eb45c6f627c45f0cba69678b72aff2b34fc78e7878b","metric":"accuracy","protocol_fingerprint":"4af2544e468228c0ae8c94b37bb85399d9527d09f75350cc2badda8609a813dc","run_fingerprint":"4ce906c27a5c7e17f069b59dcda1c7b1cac75562cecb33ba752bd7ecc7fd19f5","score":52.2,"score_display":"52.2","source":{"id":"evals-report-hle","name":"evals.report · Humanity's Last Exam","url":"https://evals.report/benchmarks/humanitys-last-exam?tab=scores"},"source_authority_tier":"B","split_or_window":"public-multimodal-mixed-run-configs","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1cb2c5290629fc013609d211","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"evals-report-verified","verified_status":"evals-report-verified"},"unit":"percent","verification_status":"evals-report-verified"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fb772e95f0047b71ea0dd7da8191268ee220385e52384101b827f8295acfe03a","measurement_key":"bafa18daea4f2397463b7683618d5b9568286fb842d91df81896afd10d44d539","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"ffe5b94b254a3e3ad19d584830b2396f68ae50071888153db32f0bfbc458935b","score":75.29954761904763,"score_display":"75.30","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_f65a7f664c0eb4433d5d5397","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"deab316c81419f3aea0c113013cedd5466abe56604996ba01d9b4b631ec17a19","measurement_key":"6194efe1caef5e0f17964c087f05ed8a0998de6daa8db3c6409c1b7b0ffec13a","metric":"pass_at_1","protocol_fingerprint":"59a5b7be6da495b040103b021a1254a911407f2c886a2d5b0c3ef34c196647e4","run_fingerprint":"1f312b912ed268ef06d2a90519e2d1c8a3dd9d8e28f44e16a99f2583303194a7","score":85.906,"score_display":"85.9","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_f65a7f664c0eb4433d5d5397","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":114,"at":"2026-07-09T19:46:54Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"27da4970ccfe4fdf79e1f0bfec878bb86a7f9cb215d57f9161b28cc07181a231","measurement_key":"2183ce7d33ac7bbb3eb345d4bc0ce6acf7c2ffd02700808309830c74b5e68dca","metric":"pass_rate","protocol_fingerprint":"c7c589fdf947968d00cc5d52a2e829086535d068515eda7ecae1db6453bd3f28","run_fingerprint":"8834c9c06b6b39821e6521c541d93cb97107515eaba193b0e5469fb80d62f877","score":88.1,"score_display":"88.1","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f46411f67d3ab003209ce38a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6c2f8b148ea6f56e86f214d24e80af8db2be3f8714bc8c46b9fca70a3533f4b9","measurement_key":"1ac8810e86f9a463cfb157996c3cf3ec56e6fd210c33b7cec1ea830a98b3efa2","metric":"accuracy","protocol_fingerprint":"fb8ec0afdea20c28468a51bdde7f83376d0cbede8ce7eb3509c5d99913278743","run_fingerprint":"f2a4a2e38323ced376bad1846546955b9fe0a31b548613593b024ed67b0f2ae4","score":88.726,"score_display":"88.7","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_f65a7f664c0eb4433d5d5397","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:41Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"31e79eb48f751dfd9dbd0b634dfb35765fd1608db2c7f13a80be899af6017bce","measurement_key":"f2af29d0a26bcdecbd1f072d5cd1ee99a1167ccbb3466506679bbd4292542fdd","metric":"accuracy","protocol_fingerprint":"50ab376774c80f746c4523aa636d752de12d7fc6b69dd3f69d8c98eae6f338a0","run_fingerprint":"51fd66eed857a3370462d059147291b667a316334177d4fe813e9cc04b16bf5e","score":86.59,"score_display":"86.6","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_f65a7f664c0eb4433d5d5397","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"446fe023e1b7ac411f5aab7f85971387388ffbd27f3ea6317d81f760d1d2e459","measurement_key":"069fd729d821daa60b8d21ae3996cd0866591d79db4a4891024aba34ccb0f3fd","metric":"fully_resolved_rate","protocol_fingerprint":"b7a5c952d8d739e3849fbe90c2d7bc13c10eb2bc7db560c341f0bdc99bf2cdac","run_fingerprint":"5aaa135d4f5c698462e9de7a6eb809986bfb1cf17560f0a276ea6ffcc9a2730b","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_f65a7f664c0eb4433d5d5397","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c1dac08f7aa8a08b63fcae6753dd3f31ef3402b8465039f67a9f6299636a1734","measurement_key":"6492642c94f7b88531256b93192c549b457889fe1832ab5fc8e3bb78a86d72c3","metric":"subproblem_accuracy","protocol_fingerprint":"561c3b5e0b6be568f854f8f88928ec242f42067d7899ef94ac31a6fabb18b057","run_fingerprint":"060dfe1e3046a4def1a414a1bab1deffd10b987c6710fa90963e8c744778da82","score":58.796296296296305,"score_display":"58.8","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_f65a7f664c0eb4433d5d5397","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":61,"at":"2026-08-31T19:21:58.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c34319d8c898cbb5e90f8dc6c8615afa231b02eec3807fca8c0d1ad2573b0a88","measurement_key":"ce6dc282e1594cf0de767644caa6f0a1803c8446778e48881c182cbb63347f7d","metric":"accuracy","protocol_fingerprint":"c8e8fa50c510fadf6b63e74fddf3368f09db7944e2accd9801f2362c09998e52","run_fingerprint":"28c390ef12dde21b3a10e1d59c86e6635087105c9d3ab1f9a58ac9c3efd8dc1e","score":57.78894472361809,"score_display":"57.8","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a5dc1bcf8ba60512cb3ee6a5","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1c62bc9676a9ff47b8cef6fb9d688b169119b8b0d6d108e93a67e430e6ddbf71","measurement_key":"10574da5951223060325cfec2b9cbbbfffe09923ceaf481ebe70d43326495092","metric":"resolved_rate","protocol_fingerprint":"17377d55f847c7d6a67b1ee45439a926553ef076ef7167776a5f15c416253783","run_fingerprint":"1767cf26afda607d2032caf009207c778e5de78681fafdd37a9d8ea3dfef6860","score":82.0,"score_display":"82.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_f65a7f664c0eb4433d5d5397","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1c62bc9676a9ff47b8cef6fb9d688b169119b8b0d6d108e93a67e430e6ddbf71","measurement_key":"10574da5951223060325cfec2b9cbbbfffe09923ceaf481ebe70d43326495092","metric":"resolved_rate","protocol_fingerprint":"17377d55f847c7d6a67b1ee45439a926553ef076ef7167776a5f15c416253783","reporting_origin":"organizer","run_fingerprint":"1767cf26afda607d2032caf009207c778e5de78681fafdd37a9d8ea3dfef6860","score":82.0,"score_display":"82.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_f65a7f664c0eb4433d5d5397","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":101,"at":"2026-07-23","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"18bfe3b62cd0d1f61b29dec7f5683da1cab38cc79c56d6e10a86cc18df622d66","measurement_key":"28239203f311f523a9b0dfea8f69ccfb930cf20ae0abe8479c7d1a0675370a2a","metric":"pass_1","protocol_fingerprint":"586a45dfded2cfa3639c1530e9bbc6ff3221b066b8305b9464d7b46e95b10f2c","run_fingerprint":"edc6b8eebf82c09582b9f9c9d00cef270186d741b7b42ecbbe81e24180e6dfb7","score":40.4639175257732,"score_display":"40.5","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_f65a7f664c0eb4433d5d5397","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c65f3da6a4cadd2a5177b4c94dca1032ed1914c34d26004ab7788748b2ab1956","measurement_key":"7e322cb287e08450267bee6f547104497a08c6c01c16896efbab83cc37659429","metric":"accuracy","protocol_fingerprint":"e920d28f173952295012036e458864bbc3e92afa535baaeb5a6049ff2b089e00","run_fingerprint":"a9ea18b5d38079cb47ab4ad83151abedd59d478c99281b39af5857827ab4884f","score":69.288,"score_display":"69.3","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_f65a7f664c0eb4433d5d5397","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"44d6176cd2ba3f099a6d4eaed90c4e94db0f61c15e636a808345a20a35fb6a3b","measurement_key":"4071656f448fb37efefd77d8c77444bfda8d691a01464c184971e00f15ec8e6d","metric":"mean_final_balance_usd","protocol_fingerprint":"b622d2048bbaf7ec329beaf3505277f8648ca0c8997f8289c3e57a872ac18f59","run_fingerprint":"354a74bc97c6af902000c7cd684229ac992140c89f35e0798cd1ac16a85b83f5","score":6520.474999999999,"score_display":"6520.47","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0cc4cc6b4e71e0063d4a49e2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8a0bf6b5046ce535a59a7770f2878615aac020fd8b2a5a37acaa3e687637e0aa","measurement_key":"168795fad58bd123455fece4bff2f163fd9c0e131385891ee64135a11bc51725","metric":"score","protocol_fingerprint":"e6ce7565d73a1482a676ee73e6312177730d24a3ce1b883d795732ef36940a29","run_fingerprint":"1d936289bdf0ed5b4936aa301e7c5362b1522d30e488a3909f63057d03e46c14","score":72.158,"score_display":"72.2","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_f65a7f664c0eb4433d5d5397","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"67c2a14ee0be74fbe6f8067cbed3f025abe3a8ef1346cf088bb0c092469be244","measurement_key":"a2515c7a63381468abe9fa27c01ef6222302fb732c32e58ce9522500c0960e8c","metric":"arena_score","protocol_fingerprint":"40fadaaf9f417c1c4b0741af70d570fb003240bb0230c2a10878164fafb18dc4","run_fingerprint":"ccde926dbe3a6c162989f74079c0eb5895099f2ab44968fe18a581de274e9c4c","score":1542.4822191942499,"score_display":"1542","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f91f386d6cb697210b7a2893","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"meta/muse-spark-1-1","model_name":"Muse Spark 1.1","parameter_count_active":null,"parameter_count_total":null,"provider":"Meta","selection_rank":46,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dc87caa3c7ef5ad2a65848c220d3102c7af01e21495ce3ae83dc6e72120a7c35","measurement_key":"d89dbad0c23c9968c8d3c09ad4329f72635437d0b5729b7b9d7ce19c5803b300","metric":"performance_rating","protocol_fingerprint":"f0a4cfc02667cf63bd3491e1b679861c8ac630ab58bfea090534396c2f2724dd","run_fingerprint":"8eae3ea9c9b1359dd15c0b1315acae669e2f330b9dd8b41f8ab5b9cb8c4f445b","score":1293.55,"score_display":"1293.55","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_da6fffb3400932260676d0d4","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2f339099068bb5dbe440746c19578cf6cc982e0eb1a6094576ba43f8a09a3d47","measurement_key":"e371eac97bccd58ce8de85017f20075445f499333ba746a62805bb2cfd873cb2","metric":"pass_at_2_accuracy","protocol_fingerprint":"5093acc4b109689bb8f30a930c66e72ace881fd78b814418150bdf331bc1ef81","run_fingerprint":"618dc545255240bbbfd490c6c655fc0fc3e983472960f07f96456364ea59cd4e","score":86.2,"score_display":"86.2","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_4a86c49777c47cb202b9dfc5","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c9ffc1648edefe35fb1bd6542c4467b15b8a9aa6f547b76dcc2dee40dc48ee32","measurement_key":"0dd78ad38c0fa4380b139e3f134b73747ccb9e4c412d0fea970332b67ea98ae6","metric":"accuracy","protocol_fingerprint":"d01d54cf6663c2478759bd86f00cfc3e917f8de7551571b190f30e5bbafc1a62","run_fingerprint":"fb35af866b01bbaee5a196f91a7d9eeef62bab5621accf41bd29382a9f3fb920","score":52.910000000000004,"score_display":"53","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_4a86c49777c47cb202b9dfc5","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cb2a9631f67a0b565544419f4c120721cb02dcb13845f842cc54973e719859d1","measurement_key":"0c2e435188f13ed778f7fd3ec6bfc6d9c29bc3ac9fcae745979ea712614a3aef","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"4aba70467063609624e6d0177f70d3227f9d5ad07ff186a766c3efa4f6413af8","score":1437.2916252001148,"score_display":"1437","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_da6fffb3400932260676d0d4","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"bfcl-v4":{"benchmark_release_id":"release_7d2560723dba9d549cd10b25","benchmark_version":"v4-ede5081a24bc","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":64,"at":"2026-08-28T22:03:18Z","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cd11e4923ff70e1c795e4bbd90bfac5836b96bc3614a13bad7820f0e2008e9af","measurement_key":"346eb40ab89c0304a7d339fd7a69eab3a9c72dd5b59f5de5e3e24d5e7d694be2","metric":"overall_accuracy","protocol_fingerprint":"6a9c99bccbca11748bdf70a2bdd6eb864726c94bf4a029f84ab95898fe96d192","run_fingerprint":"4be67636ef17c1b568b6dfa8779ab07fb926850d78ce4585cab0018370b48d3e","score":55.87,"score_display":"55.87","source":{"id":"bfcl-v4","name":"BFCL V4","url":"https://gorilla.cs.berkeley.edu/leaderboard.html"},"source_authority_tier":"A","split_or_window":"overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c45390ebff98a31c8653458d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":17,"at":"2026-10-14T16:16:30.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e0a04ac86a75d678999e7fca4acdcdbd899a11fa606e2921cc7cf79cc8da779d","measurement_key":"4fb5ff762db6f722833f8d7d703cacfaa05c7d1230e365a58d8c91e4b1d0b7e1","metric":"mean_score","protocol_fingerprint":"81b8d14850973a8d95f6442d108a5b2c736512f2bb68e3d0fb5f0f162afd9a98","run_fingerprint":"574fa137654a157be27f9f3ffd50eef211fe7321633c8b06fabb1aac6cc99d2f","score":48.0,"score_display":"48.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_4a86c49777c47cb202b9dfc5","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d35aa28030c86017798e182865ca49149ffdc4a1ac755914651d550c6d5b643b","measurement_key":"98650bafa82c171d61e6e9c801ca3a12b7cfc749247362468fa284a3c82c1057","metric":"eci","protocol_fingerprint":"ea5f75f9769e9199a30600f9008b8698432bc712e923c5597dd5e4a8d3b46d86","run_fingerprint":"480fd940819471109806eb515bf8592379d7a92646c3817e38626ed177870f4a","score":153.83,"score_display":"153.83","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d195c64b8a3ecc15e17b76c2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":143,"at":"2026-06-11T02:48:30.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7f1deb646f95d7c82c77c9d26b2a5f0cd938c908449b20821005af5fc1fb2f87","measurement_key":"824fdd58a09bfb039c7cece1f3004e9aae5f40826a764268132c9b9284614929","metric":"mean_score","protocol_fingerprint":"5686c6437aca0367bc365c1104f9271197e9b9dab735a9cea4972f021a45bc40","run_fingerprint":"746694c238eab19c468b29d852ac92bee0b678a81efae5b5cef89da836790c5a","score":67.4,"score_display":"67.4","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_4a86c49777c47cb202b9dfc5","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":142,"at":"2026-06-11T14:48:04.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5fe887e4fe0776f8611fd462abbd260b63a382108595552d22db284112a1bd0c","measurement_key":"c55013b341e7f5d09188074492659ec02c4f0d92320a52ce8cca9a8ba2a76798","metric":"mean_score","protocol_fingerprint":"549bfdf41fd03bd148e9ca762423d3d6b133ad71b87a65916b717b0b26fa4850","run_fingerprint":"61d7a1af699c9feafe0df5334b96c01a4d06c944a3b2b640ab1d4a5b88b3669a","score":31.7,"score_display":"31.7","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_4a86c49777c47cb202b9dfc5","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval":{"benchmark_release_id":"release_730527fa346470703bd19e21","benchmark_version":"GDPval official leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:05Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ef58c0e84c6163670f11b4d8afe1caf95b1d452a09b57de0b3c56ff5fd8ab42c","measurement_key":"766a72449ce8fd29a024e0b9066bd7ce0ec332cf2042563e901003adb777027f","metric":"win_rate","protocol_fingerprint":"5a3fcb25a7d145e0ee5aac9c23e0f8e4c772626f45806ef93461b4abdb803807","run_fingerprint":"dfc3c202922dd1e2ff81437d478664ab26175319fdd54e929f38338d1cda4a13","score":49.7,"score_display":"49.7","source":{"id":"epoch-gdpval","name":"Epoch AI mirror · GDPval","url":"https://epoch.ai/benchmarks/gdpval"},"source_authority_tier":"B","split_or_window":"expert-comparison-win-rate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_ff3aeab8b13f468a67900233","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"87f7e8712530d46c9281197219988f63ab13829419f9907786a5dc489809e91b","measurement_key":"df0821b50a29000f5a2b33a82e2165a683e969f6c7f316bcb5e0ce2bd4c1b9e4","metric":"accuracy","protocol_fingerprint":"4587329be7bbb42eae096650bdbe2d015876fd754bd8beef059af136cf9c3438","run_fingerprint":"8ee64d7a58e7bb289c9d96f013a3f1f723a2d68c11a80ae23cde89b801870187","score":91.666,"score_display":"91.67","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_4a86c49777c47cb202b9dfc5","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gso":{"benchmark_release_id":"release_176f07ea4e9e0b8dfeede990","benchmark_version":"GSO current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":318,"at":"2025-12-18","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"e1adffbcf0347ea927f8e3e7cbb8f559b2c328f4734dbabb8f6f49a44bae0afb","measurement_key":"eb12569cd69af07dc422ca65f973f8439761e85aeba5726f8fabffe4a58ab370","metric":"opt_at_1","protocol_fingerprint":"5e521ae728dfdea359144507dde4e6beeafe8b17a3a8ca8e8abbdc88798d0ee9","run_fingerprint":"4ed1dd18dbe03141c9e92970a5e69b360fd8661b3ba8c77d148446e0c36fc6e3","score":27.450000000000003,"score_display":"27.5","source":{"id":"epoch-gso","name":"Epoch AI mirror · GSO","url":"https://epoch.ai/benchmarks/gso"},"source_authority_tier":"B","split_or_window":"official-set-opt-at-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_da6fffb3400932260676d0d4","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"hle":{"benchmark_release_id":"release_8817af9d9a0235bce0826e22","benchmark_version":"HLE finalized 2,500 · Scale protocol 2025-04-03","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":320,"at":"2025-12-15T23:38:26Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"a766783fcb2ee6c12d6e377d6abb23b9b53478691ec8a4619ede08905b2efe70","measurement_key":"96dab9be582fe4e5c9ce9829b751a7644d3815ef04e52877bbf4455f7d8cdfcb","metric":"accuracy","protocol_fingerprint":"f243dfd0fcd058f417528e8bddca30eefd08e85ed2156fbe1b6f13eb62a4baf0","run_fingerprint":"6e29886bfc6885919626619c636744f593dd52e469dd90de7cb69fdceba76e19","score":27.8,"score_display":"27.80","source":{"id":"scale-hle","name":"Scale AI Labs · Humanity's Last Exam Full","url":"https://labs.scale.com/leaderboard/humanitys_last_exam"},"source_authority_tier":"A+","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_86dae51067db1dc1fc5309bb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e3caeed6cb3d9a4667b245a572be8879e4c28f5c32655439862ebbcfa0be4ae1","measurement_key":"9ea284d5d493bfabf013a579f0b258158e33ae4a129ed731e1998398acdf72fb","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"31b49cd4e2feb2a2849ee3fa16bdf57c2ba8487ad63c74ce83733f46b52c96ee","score":74.6349642857143,"score_display":"74.63","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_da6fffb3400932260676d0d4","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"32457c5f40a2ba8208b375173d1916ea3e9b0930e3975350a51d1e21b0e4f14b","measurement_key":"43644b4a3c73de4a720fa93fc4545a9167a327337fdeee1c6ab811698491d06d","metric":"pass_at_1","protocol_fingerprint":"83361460056ca95d46080cad51bd4f4b367db0cef05d53c3e86940c46e8c2075","run_fingerprint":"b40e0212061b0befcabfaee0cb39cdaeae6296ce9c84b7b9fd6dc8655eb1db7a","score":85.361,"score_display":"85.4","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_4a86c49777c47cb202b9dfc5","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f0d3873f45944419590fd7bab6c806ed556989fa9bc61702da0e28145f97ce07","measurement_key":"59ac551cba9a18ac4aaa30c27feed65212d19e710b647822153f58900544eacd","metric":"accuracy","protocol_fingerprint":"604c4461ee4f7b1a182791cde7471d23b2cd64d0acb40c36898dba53b6a141ac","run_fingerprint":"09852e0c41526b5fff3342e1e110e1dd68f718a2589c8892d425ddb8e99bea4f","score":86.234,"score_display":"86.2","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_4a86c49777c47cb202b9dfc5","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:41Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"184099246db7e2370cca873ba5962eadb7efa3271fae0299d790f20a39cc8704","measurement_key":"14cbe1b7673550bf9e13534172dee851f48b9d5bfc2f130a62c67882feeed0d4","metric":"accuracy","protocol_fingerprint":"a33dd7dc139050239d5ef09ebfbcbdf12eefb661c41d6a4da238a318313fb8e7","run_fingerprint":"c2e074776eb6a0738d2e174e5d6959bd4429ea4b674542f9bf0011202b10e821","score":86.667,"score_display":"86.7","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_4a86c49777c47cb202b9dfc5","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":322,"at":"2025-12-13T15:56:00.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"ad6572c5e09577fa86f5eb101835e6c8103bdc6b1ffebe3d93e2b7cf48d385ce","measurement_key":"feed646861d5799c1e21b63d8c179dba59d87a92f6eae66909e21397289f54ff","metric":"mean_score","protocol_fingerprint":"262d18a12360b932973b89b9d03963035c3c57ce099ed5777db7c6d87332a7f1","run_fingerprint":"46c91470889dbf53395c1f0180ea2a0bfe809ee3bfd65e33ced88e3e298dab7e","score":96.1,"score_display":"96.1","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_4a86c49777c47cb202b9dfc5","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cf1430603d6ba58d862e3622fcf8fc50cf9881c28e6e7e247d564572f8a52dc0","measurement_key":"916f9e0cd4fa9bef151b678901affa912e4d213f1d60283dc7ef7ed484d9f9b1","metric":"accuracy_avg_at_5","protocol_fingerprint":"3f440b29a11b0bbf50a91dff1d673b2869ac88c6ad8dd8682cb0a9fcfe3be965","run_fingerprint":"0ac7e166f6adc30adda7cfeb3db134273aa9d707ae2d11fe1e01d12b21e5a5e0","score":45.800000000000004,"score_display":"45.8","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_da6fffb3400932260676d0d4","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:27:55.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0886da10d91ac72c56e07ef5956734fd2a59d68512a4b2add7fff885aa613bef","measurement_key":"bc75a34fa9fb2853f3fcf07b82336569b547e350f3cf7287cb84a9e9425bbe08","metric":"accuracy","protocol_fingerprint":"222ed766bfebee500cdc2d8668f454b6ce0017d1a7ab2bb2f239ab09339d5374","run_fingerprint":"d39ca95785e72a0d40722b18af019a3050468f3e76a4523bcd70a9ec74922be2","score":37.1,"score_display":"37.1","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_4a86c49777c47cb202b9dfc5","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"skillsbench":{"benchmark_release_id":"release_093b45b8b752b3f08534f6ee","benchmark_version":"v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":138,"at":"2026-06-16","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4426c94fd8fb35d6d48b96094b86ab3ad420fc746aa7465c1ac352235c0431b9","measurement_key":"65c90bfbe694a62cdb97f9f063c20ebc7f3c00e699f23487571fa74fb55e5c53","metric":"pass_rate","protocol_fingerprint":"de4ee8be7ebbb4075f4b810c6a6dcd2e1f701030bba81db0d7f2320352479107","run_fingerprint":"e8f300a63c2e28ffb5ad2d802aec38f172b7a87b821113d7da1cdbf026f51851","score":51.7046,"score_display":"51.7","source":{"id":"skillsbench","name":"SkillsBench v1.1","url":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json"},"source_authority_tier":"A","split_or_window":"official-87-tasks-with-skills","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_5abeb85214411e952b3bbd17","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2594b06434c2a2829b1b63380f758557500414c4e6966e9b7416ad3db5966070","measurement_key":"57cfb8d5dc693185a114b152e41b31e158c834570289f460d8df13fe33a730a8","metric":"resolved_rate","protocol_fingerprint":"5b48f541e6e08a71551f7ee0691e079128f29a5c08a630fe9b7f6667d3d53219","run_fingerprint":"7280c518a6a3cde615a0a368db9691ac5e383b3da967af99fb9a0b90de1c0316","score":75.8,"score_display":"75.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_4a86c49777c47cb202b9dfc5","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2594b06434c2a2829b1b63380f758557500414c4e6966e9b7416ad3db5966070","measurement_key":"57cfb8d5dc693185a114b152e41b31e158c834570289f460d8df13fe33a730a8","metric":"resolved_rate","protocol_fingerprint":"5b48f541e6e08a71551f7ee0691e079128f29a5c08a630fe9b7f6667d3d53219","reporting_origin":"organizer","run_fingerprint":"7280c518a6a3cde615a0a368db9691ac5e383b3da967af99fb9a0b90de1c0316","score":75.8,"score_display":"75.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_4a86c49777c47cb202b9dfc5","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_b5f5937b2cb1e2b756288948","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":245,"at":"2026-03-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"d15355f780b41cb618fbf22675a85d380bb951e86e22e13702f1430428ddf0d5","measurement_key":"e8c8a67c05362234774db8ce4c34f2accb6ded535a964d718b1034aeb213a0ce","metric":"resolved_rate","protocol_fingerprint":"f288398b66ed709eb0d9a928ab5ecc2b376564d2d163f6ecd2518791219528c7","run_fingerprint":"2d2a0b7e33c974264cd85095cd877b3081a195aaa5b93699a2a941cd99d62dff","score":59.01526992508781,"score_display":"59.02","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2025-12-15/2026-03-01","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_9c94798e73be04b03372ecd3","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":180,"at":"2026-05-05","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"15c9fe172460154f3d0f3483b7f317188f1ec54ab46393d46b3c6f3448b954fc","measurement_key":"6837bf9a3a86242be4004255991e1aa5df5f5157d5529750d62f5a2ec2009cf2","metric":"pass_1","protocol_fingerprint":"fddc1da1ea5e3ec0812c175281f75e6b59702134f5a28ebade6fbbc00b5ce9fe","run_fingerprint":"beec4780e04627cab69a6e0396c1852621dad5f4b314dd3d126aa47863287809","score":32.22,"score_display":"32.2","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_da6fffb3400932260676d0d4","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"60fe15ef9c130cf445f0c84d1a117f88b90cd5e373acfc0be0abca9d92bd3df6","measurement_key":"2fa7eb69ce3d61f23d95148907f16321bd948d512b47649ba03fad2172ce48c9","metric":"mean_final_balance_usd","protocol_fingerprint":"6da35d09238c9df45d2f323fe5aeb267713f7fa3fa3027c58f086ef6272f3446","run_fingerprint":"1991f985c7618b1227a484879f8260b3d070aaad5aae3ffc4e3e321c404e5d44","score":3591.3259999999996,"score_display":"3591.33","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_71d5b9dc73fff7d1c5cd8972","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d065565414917453500ae80a2ffdb6bda021c822c7c693040cdf2ea5e5b89307","measurement_key":"cbe429488d0dab8beb65ef398eef5e17bdd4b8f61945ee09f277cd001fcece7f","metric":"score","protocol_fingerprint":"27296a73811abfc9e4144c985fb38423385f57fc85d2fda19967dcd197ace2ac","run_fingerprint":"cf6c8e9748239a619ffd046c086ca21c1e71b83f63aee8687a8895af49cdf607","score":53.499,"score_display":"53.5","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_4a86c49777c47cb202b9dfc5","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"67e45f436795f57f90bb8297b8e008b81f35c4f6286ddc12fa755cc9e63cc1a9","measurement_key":"160d974378c9371cc71c1827fd80bb25b3f6249580585b27e0fea37bfa2768fa","metric":"arena_score","protocol_fingerprint":"9d5228690ec00c526f3f023e0ef249f362499bd555fb83c92c1d3658117c87ed","run_fingerprint":"6292db1cdce1c2d6468f0712ec0cc72b448b81a06d7be82328ef34a4fb87e5fa","score":1416.424922259506,"score_display":"1416","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6393519d4489cc2ad96abfdc","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"21203e7dec2f79cc953e15809672b81edefd4ae82dea9aba0b70a93348278134","measurement_key":"63e4cf39496c0691148e39f42411f303f96604511bd82fdcae6601633afd149f","metric":"accuracy","protocol_fingerprint":"f0633360f72acc77df9d01cf9d2953ff8c176ba7ef401ce2b267e43c9b253c92","run_fingerprint":"728b4ba4bb8e86cd9e0b02f17c57dfbb7ed5d0b5e6a1e1d422b39e5613ae5654","score":72.19,"score_display":"72.2","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_4a86c49777c47cb202b9dfc5","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"037883f54c632adc081fa512f50902ac937ba67a324cb3b0519dd794c359e512","measurement_key":"1faa2947e2e5406838dd4695598ce5ce265143c284fe7bfeccd2a39f3d16e15e","metric":"token_efficiency_weighted_score","protocol_fingerprint":"19e0b2da70b62d41229da1ff68c86ab5dfb7ed43b789ee18dc77b8e1faeb521d","run_fingerprint":"79d45ce31ce4dc700a13b022458b05df29045422394c7b87325a97564f581f8a","score":5.00787722943723,"score_display":"5.0","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_4a86c49777c47cb202b9dfc5","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"openai/gpt-5-2","model_name":"GPT 5.2","parameter_count_active":null,"parameter_count_total":null,"provider":"OpenAI","selection_rank":47,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1a37b52dae7448b9f7168db52fda20b906fd7e007097635c6a2136b5935ac0de","measurement_key":"a2bc2dc8034f66e38957ce4cb0dce8b99ac7ba8cad3bb722361cbd787cb9c0df","metric":"performance_rating","protocol_fingerprint":"b90b91119d6e1c0d23d68ebf852ba81fd02dcd362d1175a124eb4f432f65cf7b","run_fingerprint":"46e9b31947bd643846518ad2b345dc81c0345df3ebea2cbcac50e647e0eb4a6f","score":1176.75,"score_display":"1176.75","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_adb9d064fb6ec60affbc6752","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f0bfd46c1967002ae32fe5e09f14637ba7fb1f50fad5b4d94b16bb86faed986b","measurement_key":"91a88cb0303febae8169c8c0aab3fb73476760a2d89fcf4a8ed702331e61f3df","metric":"pass_at_2_accuracy","protocol_fingerprint":"a61cc4282fc3788ccaa14ffbf2fe051a812472f438d814c2cfb9795c40923e80","run_fingerprint":"3ad436a4ff128e487d40977f78ff2872b070796485c20ad115aa4babf83c29fd","score":75.0,"score_display":"75.0","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_eea65165256ff8318729c400","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c6f0a222d2d82a268408e5dc58daadcbbf7f6765b25869f11a401b25c3e91335","measurement_key":"2f77893fd23c9089038c524ed602abc9c80d3cb6a1f8a141f6c660bb00e37b1a","metric":"accuracy","protocol_fingerprint":"99a1d91d545a77cd7589ab38d5e6c23ee720a21c66735bb8e5f3e86f432a91de","run_fingerprint":"839e4936351061d3ef52eb7d00593f4348a7670a352c142fa8c8f97efd560aa1","score":31.11,"score_display":"31","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_55859642c21787720a9cc539","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"99e700a4d333d22581147d91de6eda84cb092fe3ba15ed8ecf952e7dcb21e37e","measurement_key":"869ab65bd52c915259d35391a14a7ad854f35a633d38bc19ff271ae1ad45e90f","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"a94aa82d0e514ae92b4faef149e30eec21c8b45ec12cb6755ddfb09b3fc31c8b","score":1485.4329182845129,"score_display":"1485","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0271df1781497779ba7d4b50","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"bfcl-v4":{"benchmark_release_id":"release_7d2560723dba9d549cd10b25","benchmark_version":"v4-ede5081a24bc","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:42Z","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ce2a9ecb4b2ce21ab28a8d84f235cd24a24e419d12e1dc2ffd8eded987ba1652","measurement_key":"59960c0a7ec966b21ade02a5703eead0d0772db76570f0ab6535f5d62e112fb9","metric":"overall_accuracy","protocol_fingerprint":"6a9c99bccbca11748bdf70a2bdd6eb864726c94bf4a029f84ab95898fe96d192","run_fingerprint":"7f17039421980bb44eedcd74613dbbf5dd2682ba46d9b6e9cb1f9ddc7e9c1083","score":68.14,"score_display":"68.14","source":{"id":"bfcl-v4","name":"BFCL V4","url":"https://gorilla.cs.berkeley.edu/leaderboard.html"},"source_authority_tier":"A","split_or_window":"overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e10ca9a1e04ebb6244b12dd1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:41Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7259948453499b4563bb3c09f41849ff861ebfce6ae6dea4888d1a90100b20f2","measurement_key":"0db3c1457824445c7fa425d843dcf84ba4518d3fe53d0dd70086e0ab19256508","metric":"accuracy","protocol_fingerprint":"9162a8226815c167a678857e1353c87c3a641643f4952f0fa1f5b1558dcb125f","run_fingerprint":"5cef0609964e61f49a2286f2309e4813e869226bd44e93303ab1f5206eac8926","score":6.9,"score_display":"6.9","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_06cf7a8f0e7a9f715887e058","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c862d728559f855f6aa3e81983d3e2aadf2296bc63d98d1d1a1174a65dc6dadf","measurement_key":"d73580f77528f5c9347dfa11d27f41f0bace35424ca098ca151543f81f739de6","metric":"eci","protocol_fingerprint":"696f01d1b678fcf06fc846be70cdd27cfb20b9cb6a5c2b9c8158891a38622bf0","run_fingerprint":"217f141c60f91e43c280bd95b668f41044997cfdf0464f51fdd947443f53c306","score":153.22,"score_display":"153.22","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_21273f06524672cf31a6a06e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"gdpval":{"benchmark_release_id":"release_730527fa346470703bd19e21","benchmark_version":"GDPval official leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:05Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b152fe15f701d84650a0298ed88aa3b9fd79af6840de86f372cbf117c723f9ba","measurement_key":"c5ae953ff595d9ac8e6dd2a1d6ee991cd838218523547f3a8349135e12f74008","metric":"win_rate","protocol_fingerprint":"2b572160dc5691512f728679f7c793b9cf2eb4c1ed163081ee67c969327580c8","run_fingerprint":"f9251d32c4117d4bb6619173b8ef057924f4a90a65af196225fc90c840da2985","score":40.3,"score_display":"40.3","source":{"id":"epoch-gdpval","name":"Epoch AI mirror · GDPval","url":"https://epoch.ai/benchmarks/gdpval"},"source_authority_tier":"B","split_or_window":"expert-comparison-win-rate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ea20236fd014b2198d3a19c8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"933b8f00c922085ffffc476de9604a8ee75f9fedd83fcfddbf5f58ce01eb937d","measurement_key":"2f7f8c82f0ed4f04f701ba8aafb684ab56d810154659c0eeecd02dcda3fd91d8","metric":"accuracy","protocol_fingerprint":"0c969d64a5adce4cbf73e75fed860e77cb5d6a0c296fe2c63652882e8ea2027d","run_fingerprint":"1757d5b37dba58bc958ea67a6d67c76c0de56b3a2f99dc4212b5858ba3c55a88","score":91.666,"score_display":"91.67","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_adb9d064fb6ec60affbc6752","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gso":{"benchmark_release_id":"release_176f07ea4e9e0b8dfeede990","benchmark_version":"GSO current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":338,"at":"2025-11-28","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"a815a2e0b125c7f2a75fdf196f1a7dbbcf0e0e29e557d514a67f02df4271fdd0","measurement_key":"9f63627cbf1bf1d875bac0a0c8fc0bb0c05c313d29b344b216825017588e44d4","metric":"opt_at_1","protocol_fingerprint":"93d2c24bbb66465156fda6199944da881b585d0d0009827798ac52c8d19539c6","run_fingerprint":"c3af8c516bd038a63718a2d1980e5726f3c63c9c5980481cd2ed0b334ec581ff","score":18.63,"score_display":"18.6","source":{"id":"epoch-gso","name":"Epoch AI mirror · GSO","url":"https://epoch.ai/benchmarks/gso"},"source_authority_tier":"B","split_or_window":"official-set-opt-at-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f7289fba54bab2a09b2c9891","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"hle":{"benchmark_release_id":"release_8817af9d9a0235bce0826e22","benchmark_version":"HLE finalized 2,500 · Scale protocol 2025-04-03","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":346,"at":"2025-11-19T23:50:49Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"8e43ea87579dcf9fc892dfb338ec7d88e0e5cdad4e4a24124025d7d97feb9254","measurement_key":"58822afa551e98bd0c36241a8a38136f36a7f045a4b9b55d3ee803a5a001f91e","metric":"accuracy","protocol_fingerprint":"17fba628a5a7ab328f048d6d105eec887a1b5da1f7879f3e05965396d5556d2e","run_fingerprint":"763768d706872927e2099d761f596ec0f9165c3f0518d06487f864f1d5f76e43","score":37.52,"score_display":"37.52","source":{"id":"scale-hle","name":"Scale AI Labs · Humanity's Last Exam Full","url":"https://labs.scale.com/leaderboard/humanitys_last_exam"},"source_authority_tier":"A+","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b228b8ba7c4906d4189d84aa","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b9bea7aee720be6a1e80bb1ee84ba6d0339f749f54e51ccebfb133dbd8e7d992","measurement_key":"70c11063bae8a965c1be7a277a0129d586f39bfe8e29b70f6d8a5b716e2fdc9a","metric":"pass_at_1","protocol_fingerprint":"bc9d2db7e409a56aeee431f3e4d3630507bfcfdd8e727f129319995a6df577fe","run_fingerprint":"bea9ef226c9e087280ea6c048f12db1425e17ab812eca07774b802b54214d33a","score":86.407,"score_display":"86.4","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fef4a508fae5caf5110e0767","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":317,"at":"2025-12-18T18:01:43Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"b03c6a7e03ab938a52322eb2fd52ce2f9f2032a3dc54cf35fc2f2d1a00a75a51","measurement_key":"58a86a3bc86954d75054d0e64b787f2f29413c9f98b8a9875161f81e60c50cbf","metric":"pass_rate","protocol_fingerprint":"097f51dfa7acee32ff96d9deb181a29bfb4d28cc12041f2bd6881fae31a7e54b","run_fingerprint":"51926f87e6b0fa8a649d16d9fcaa876bb00c489a19dff07adcb6f6728df9c1cf","score":70.3,"score_display":"70.3","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_671f7a505d0631492846b729","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b1e3ae907e658376bd5439a5493ecf1e438e6353eee755321be614faa32d6d83","measurement_key":"8a96147ad6b5b54fe6fc75f8128b8dd1bc8f6524633cab61103d6f7a65c0c81a","metric":"accuracy","protocol_fingerprint":"2906ce753f69028b9c07a9f314a3c07a2a1d0b2bfa51b5d2dc7b948185013c3b","run_fingerprint":"429612b980e9a03188db52e44b6bd4c2c31bc5e9d68a45bcc4ca40f752972816","score":90.102,"score_display":"90.1","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7c54b62064912898a8a23a9a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"50983d69c7e0dd7cdb65ba3cd42ad39702da381644f9c633323d49d94095cddc","measurement_key":"127d9b7d05c0b2a893391b0537610c335fd763fcf2bfd38cc5b04c7e41378929","metric":"accuracy","protocol_fingerprint":"75ff959ffe948428097e0bc8e42317d066196c8703d86c6002167b22f98e1184","run_fingerprint":"14bc5cbf255a4fcf023de6f5acd2657ff8f213c88fedbd3862fce58cdf7051ef","score":87.514,"score_display":"87.5","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_adb9d064fb6ec60affbc6752","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":346,"at":"2025-11-19T15:16:13.231Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"ceed1a5499b83d764aa861848a89af69bc4ff3e8b79b265fcb32b96708d04134","measurement_key":"456b2b3948cf2e948e3e3cdfebdfd872abdf678122b7819b742cf7cd09891886","metric":"mean_score","protocol_fingerprint":"9dbd0a5981231b06590c4da0465a446a5729320593618e11466b8ee4c9e19f03","run_fingerprint":"e494addb2004393b887639ea4910bfd29372b67835b4d37202b5df9cc979facd","score":91.38888888888889,"score_display":"91.4","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2f83be29a9f1348d44b039f8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"78fb9d1271b2d874a29e85f54dc75a06c061ac92650cda0914a4cd0c802457ad","measurement_key":"58bfab8096ae9184d5212812c6b12915a4b91cb4560b6ac86b5ef5e0fd2a229f","metric":"accuracy_avg_at_5","protocol_fingerprint":"5598f250eee0f48592d2053da9bdea88c7a82ed2e827eebbbc2bc6954db727a2","run_fingerprint":"fbe8233ec0de78536a6be1d991750038b3b3379f51d3b676033d5042fafb8893","score":76.4,"score_display":"76.4","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2f936e9456cd58720653f4cf","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_ccacd6f679c9142b534364b4","benchmark_version":"task-v7","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":353,"at":"2025-11-13T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"131f109e88713c4eeed3b24b4f53909c70536e723213e56005e53576617a284a","measurement_key":"b5d3c9b2bed90f0f940890979a44d196e430e00a762a11b749578b72bfc09b92","metric":"accuracy","protocol_fingerprint":"b3f27ff774166a33798e6609b791b03ff7b9c2a1ba3229d991c2865b8aa97513","run_fingerprint":"3753b61f36ec3a84e7c5fc4e68b9ff31069afe44c9bb02811545d2e1ba2d9fe3","score":72.10300429,"score_display":"72.1","source":{"id":"simpleqa-verified","name":"SimpleQA Verified","url":"https://www.kaggle.com/api/v1/benchmarks/deepmind/simpleqa-verified/leaderboard"},"source_authority_tier":"A","split_or_window":"verified","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_99f15e2ba246f14793e1e251","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f9dc7da3677d2191ebe5bfa1505841ab78f8399e31afc8adc269ae2cf4eb08ee","measurement_key":"b5d2ed5b162c18940eef4ceec1a1291505c22bd594d1207e97453e1a1b77821d","metric":"resolved_rate","protocol_fingerprint":"f328eafabac495599c18cfa83048fdb84b506a7b15f398ca693d6429ece72384","run_fingerprint":"f3694aca98844bbcd7ad132ff053e46233cebe650b2073a1bac79bf5f104590c","score":76.4,"score_display":"76.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_adb9d064fb6ec60affbc6752","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f9dc7da3677d2191ebe5bfa1505841ab78f8399e31afc8adc269ae2cf4eb08ee","measurement_key":"b5d2ed5b162c18940eef4ceec1a1291505c22bd594d1207e97453e1a1b77821d","metric":"resolved_rate","protocol_fingerprint":"f328eafabac495599c18cfa83048fdb84b506a7b15f398ca693d6429ece72384","reporting_origin":"organizer","run_fingerprint":"f3694aca98844bbcd7ad132ff053e46233cebe650b2073a1bac79bf5f104590c","score":76.4,"score_display":"76.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_adb9d064fb6ec60affbc6752","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_1c18f4398e32b2e0fe7f7d86","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":273,"at":"2026-02-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"08ad310b01ca4ef1f0154b5b5c62604db450fd74b5d33b118cb07bbcddfe6fd6","measurement_key":"372a6e28e585c3c687fb286aefa29a1bd3e4214bb7c07eda42d1269252dcb02c","metric":"resolved_rate","protocol_fingerprint":"aabe485e331299acc0f7029513ee3a87f1b24a21da19427abfac925db891570b","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2025-12-01/2026-02-01":{"benchmark_release_id":"release_1c18f4398e32b2e0fe7f7d86","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":273,"at":"2026-02-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"08ad310b01ca4ef1f0154b5b5c62604db450fd74b5d33b118cb07bbcddfe6fd6","measurement_key":"372a6e28e585c3c687fb286aefa29a1bd3e4214bb7c07eda42d1269252dcb02c","metric":"resolved_rate","protocol_fingerprint":"aabe485e331299acc0f7029513ee3a87f1b24a21da19427abfac925db891570b","run_fingerprint":"f4e92d07c2e51715b7e2c507a4278775841d0f1a1277c63bbe9e1e32eb28c8ab","score":52.74342105263159,"score_display":"52.74","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2025-12-01/2026-02-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2123e902a08dee70792ebf5f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"f4e92d07c2e51715b7e2c507a4278775841d0f1a1277c63bbe9e1e32eb28c8ab","score":52.74342105263159,"score_display":"52.74","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2025-12-01/2026-02-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2123e902a08dee70792ebf5f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":244,"at":"2026-03-02","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"42cfbe1f2bf5ac74c21877004b45d22fb5e275f9c1238707a72f4f3285615c5b","measurement_key":"33062e043f3d7594e66fac5de691cdf35ed2b6dc0b086b7a93fb417b0bb69aca","metric":"pass_1","protocol_fingerprint":"6070e5eb3b8465e8c6f5c8390e51640e8e9064c49cf8b5ad9ed333ecc2cba0e6","run_fingerprint":"7c7cb1dd1c896f1b3a91af7417c1e4169bd1828332a39c84c8bb1dc22294401e","score":18.04,"score_display":"18.0","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_adb9d064fb6ec60affbc6752","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2802a552f3919cf79b50da4d2da202f33225b418ddc3dc670c0fc5983e66d3f2","measurement_key":"f72a433c00a9ad1a9ddf49ff94f5591daeb995332848c7d391bbba8ba041674b","metric":"mean_final_balance_usd","protocol_fingerprint":"8c8835ad8aecbf44202e08a057c93f84eca18a816e9e74d6574afe97bfd73116","run_fingerprint":"3fb6d1f6b2a4d183cd039e815557035278badde43938ae02deb41d46329898ba","score":5478.158000000001,"score_display":"5478.16","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_cc3ed16981114b07863ab4cc","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a02cac52083e378a76574520a2892555c8216d14d3a5c574f1d1a5ee78256d30","measurement_key":"d7717fef313a132d31c24bb44e252516b6195d902ba8bffd853f36079d2da354","metric":"score","protocol_fingerprint":"6a1a55d7b3845f0e6a5a7f34dfae97f692b4aaf56df868dbb014fdd21a7cea5e","run_fingerprint":"ee8f71157d45511f4f610a86376e77ca6c964b3252590645487dce53eb2aa379","score":14.3,"score_display":"14.3","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_adb9d064fb6ec60affbc6752","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"31e257c47e363a356f8cf64c7cb2cf3cfe90ba5c7d08622c378439c1fdb00de9","measurement_key":"0372e9797756aebdc4a68126ba1d3560fbfa5e247db7c0714b75217f825428b6","metric":"arena_score","protocol_fingerprint":"df2c2f21fe2bd96c34853b96b34807d9504e27ae1b41fba0a2f85c184ef1956f","run_fingerprint":"0d8c1096dee778bb7e42c88202be3177ae2507b46cec9102500dc790f420733c","score":1439.9733520268244,"score_display":"1440","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8b1d5607f64765be6892d3c5","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b3771364320f7f4b99a42e35c9cbb91b0d41bb26d077f8871d37b703a04cd5c5","measurement_key":"7ee8d4c4b6458da0b6aa344ad431c900837269c061cccbc962d103d9c586a571","metric":"accuracy","protocol_fingerprint":"823d1839ab557ec28302622ebf9b212fbee470eb44ec550284a1997c2dbb10db","run_fingerprint":"ec1f1b9c1b0b3e6cf1e47c94f1ca6a529150933913854738afaffb1c9b9a05da","score":69.93,"score_display":"69.9","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_cd9c62d22639dee9b3c647d7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"google/gemini-3-pro","model_name":"Gemini 3 Pro","parameter_count_active":null,"parameter_count_total":null,"provider":"Google","selection_rank":48,"weights_status":"closed"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T01:23:12Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9d3487cc96aed2d87a07a1c0a63fd84c050fc106b58aa68e0aadd1f0e7776acf","measurement_key":"7dec67e6eae8bc3da9c4a413c82be682b6cdca50695025dfef9776f69d2bb8c9","metric":"index_score","protocol_fingerprint":"5e55c1514e444ecf4ad66390b0108bf7bc49a54c6267c173b782ff7d6ccf1242","run_fingerprint":"8da61771f4742a7b781a4b75f96976f2a4012ad1348079a29eff731fd226005c","score":27.753889,"score_display":"27.8","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_626f9b1c4e05a66a41042aa2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T21:27:35Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bb6e82acc810b2e1eefe95e267bab2be09116d8e581170c89ac1b46f0ba61695","measurement_key":"4563afc15b1e40740456fdb4ae931ae736aa4f181d0c0a7b50f0c7a7ff6db24a","metric":"performance_rating","protocol_fingerprint":"871e7a4ce82d510c855fb65d3bb95b88e7fc08a92581aab4e2f537171b51df37","run_fingerprint":"06f4b3f0e704c566e5cb1bb38ff933962905c5e6ee3c62b7413a1db61f29f492","score":303.55,"score_display":"303.55","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_549ab507d1f6fe5b6e3cb294","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8e24f2964f876e540c0747a2587ca6735a6fe4976615ba5e4ce2027a4f6d5f12","measurement_key":"45b64e0adfbcb8648390a690b8101a58d46041e3e7a14284942cc05d82db9dbc","metric":"pass_at_1","protocol_fingerprint":"748f9e1e1c80f60ea6a805a41ca001a50b989b3ac76a07b81ff5ae423b61bc34","run_fingerprint":"16068ed862433ee6b3f760755d376e1e4fae65af9bab18a6e1539548de04a0fe","score":52.800000000000004,"score_display":"52.8","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_605f0eded166b30ff74e07bd","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:14Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7900244bedddc2c363145ec01711d601a6ecc0dceae929895b28ae599869be4a","measurement_key":"7505aaf90ec271596e3ee85646374f4bed6cd456acb710cabc323b0d42fa9c57","metric":"pass_at_2_accuracy","protocol_fingerprint":"983238485ae334c26bf791458ea3f413b5ef0c8c1f03258aebbba99789675206","run_fingerprint":"d73e239b65ff09cf47179f4e2fcf9d6717fd010b4bdbf64081a8414ff909d5e4","score":91.0,"score_display":"91.0","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-09-30T18:53:20Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f095cb78e5aa194d2430fc8c557b2da9d42cd7a2b81adf0a227b3554e4c30e2d","measurement_key":"a076d2cc18e6f48a80677bb987d3bf976e91ee54632bb78cd13a4e603a6574d4","metric":"accuracy","protocol_fingerprint":"43a790acf37c517ffe418e9a2ce33e021e3dd50d977f332795071689b4f024d7","run_fingerprint":"5a313256a133813e76fb78d71ce82ab0083b16d847b9908d19a0a498427991ba","score":65.83333333333333,"score_display":"66","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4f6beb641cad092d9284a690cd28bc2cd043968ca73a5a36e45622505df8806d","measurement_key":"e5551776cc9b343e62f586ddcbcbe9af25d95c6d40fb2fa73443ad3722702bca","metric":"ips_score","protocol_fingerprint":"f32ae22a180251071c523302d889eb0a7b9cedf0fc80ce48c2158449d34bda72","run_fingerprint":"79a68fcba02ead526213d6a5db73c90208055d895d683f34236bf42d5185f8e1","score":-0.023262807029308576,"score_display":"-0.0233","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9b74d27daa9d9ff35df369b7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2abc22484ec60294e9a714258bd96b493a0c977fb35cf4892b19d922d1a4bb8f","measurement_key":"2faf767cc23b5504b99edb5ec42fab4926a1c59f97ce7e0d5dc2cca4f26eb54a","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"397d90a88f911de24333977fc9f63155880c9086fd0f25ac1db23d4431507901","score":1476.515607263063,"score_display":"1477","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_939a9cca21255a0df9b67f4d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T15:54:34.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2d55200bfebb70a9db6b40a92435a3f895b394fbcb6bf080a8e379622478d934","measurement_key":"d99e0296752f429bb7a7089ac0f7b945c173c87aa6f72bfbb4f3b5403693d3f3","metric":"mean_score","protocol_fingerprint":"b4e5d8f5043c440de4c94daf32e4fc02f32d603d698499cbebc8bf50f9659a0c","run_fingerprint":"3c0cf0a317fa4d773377bb16fa79663c392de3122edb50f1e35ede62c45c5bad","score":21.0,"score_display":"21.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T21:27:01Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"70f68ab91f20c4c66062c49d4a4d3a774526c78eca795ef85947f5c11fd07e78","measurement_key":"ad06d8b9e9a38deeb080cca714262c2e4ff7381c76d4e9527274f30751cebb88","metric":"accuracy","protocol_fingerprint":"cda300ed2945c80bbe368789b74d06a20a060a0ecff520d376230e8f02e0de36","run_fingerprint":"ecac7e2fc0297528f621077244468d4a25e5fcde5dfbad33dfd9b462d117d2ab","score":15.4285714285714,"score_display":"15.4","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d32f80db8f8edf3a161d1982","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"cursorbench":{"benchmark_release_id":"release_9acebd5b002e9c3f18a30606","benchmark_version":"CursorBench 4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:11Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5de983a2213ae8da2024a1892d08a58888d5a7dc26188bfce6cde8f5360e0769","measurement_key":"792dad760a715b00d7d4c3e4fb81c12c1ecf74ebcbf9b4fddfed88aa662835ac","metric":"score","protocol_fingerprint":"67f9f9b40e690cdc0b038d5009351228093a756098f53fcfee78843cf140a6a0","run_fingerprint":"c6bbfb8a96e741a34486573447112c5c0aa41af123810d1d0c51193f40247123","score":36.8,"score_display":"36.8","source":{"id":"epoch-cursorbench","name":"Epoch AI mirror · CursorBench","url":"https://epoch.ai/benchmarks/cursorbench"},"source_authority_tier":"B","split_or_window":"official-current-suite","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cb923b3372dc619c5d97dd0cace2f1ab6e2ed79fc013843aef22c7e82e7a0568","measurement_key":"a9b168ae01c4673fc339a5049852792f57581e3bea39166b947a02eecb8bd101","metric":"pass_at_1","protocol_fingerprint":"600d6a11dd0c7650a51ed4c33e6676ad6579879e8b378aea81b58fa00e0ae39c","run_fingerprint":"23a44ecb25a1383a9d24b3ad23ce046ef78317b1f2e423d712186d7a1f15d39f","score":63.39285714285714,"score_display":"63.4","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"02dd9571b0bce809e6d5d1dcc1db7f2371fcf8b6f487b4b978fb2cef931cf08a","measurement_key":"7d734aee6aa1d5dac457b6e28250b050c048e05dce3550229a271dd23f33d001","metric":"eci","protocol_fingerprint":"7adf462e707292e2d51ec362ceea354fda4f62e1175fd019adc5fe91a029573d","run_fingerprint":"883004aa7df86375478e0cd78a1ab3ca072a47877d1bf616fd122f3b027fcbad","score":153.22,"score_display":"153.22","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4d4e599ec811239ce079646f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:01Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bc1e42a6bb609eb1578b20b9ae3825eac1e23d69a6dfe63f68d05d02fafa2a19","measurement_key":"3f6ed168bc79cf8a68185236436c1242b82cfeefd880b71481e6b9eecf7fa96e","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"8cb81a03ff70259cef6db7966956279ca9dc3fd8f754cc3aa01719a706d65d7b","run_fingerprint":"4cf9e64c8296f58a06d6265a5135e7a572488a2ac73e423a73b4d190647ec9b7","score":31.830000000000002,"score_display":"31.8","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T13:29:52.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d2640f63083ed7df8aa9f62943ae4e9091a3083e33913ac2e34c1efb14fe9541","measurement_key":"abfba007aee088531fc115598b0201caaf3f3b8349c2957ccd3b3d47de30b0a5","metric":"mean_score","protocol_fingerprint":"38abbc3adc3f7b833dbc0883b188a1ffc38ddc878e9e36dff4d67f43e808a1af","run_fingerprint":"a2be6f3f648ded04ba25e512794af6029790cc28cbd7dda8cf1a2b86643189e8","score":55.78947368421052,"score_display":"55.8","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T13:29:52.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"53557551c330f69fbf2cc13d901dcee3989858354395db04cda31c05e3e30ad8","measurement_key":"24025b6b22ccba580c1b552203c731179a72f07093fc5485a4f13cdfe57f71f5","metric":"mean_score","protocol_fingerprint":"f8aa604bd1c0f91a30ac21123b2b364ca02105a735bd72c50c5f559b6a2d2ed3","run_fingerprint":"d535456016ca2fd782e6e164b195227bf2b7de6b8ce8e2a8bd103190428d7abb","score":17.073170731707318,"score_display":"17.1","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a80a3c34b2cb6326e9f439d4cbaa7f1ad50953e3b189dda8dc2738e4966686f0","measurement_key":"7cfb0f9d8a92df23cad770e02383c9341a0d93e74f63f3b661731b558b120aec","metric":"elo","protocol_fingerprint":"d2d1902c6ed889929fb7ead8645016397d6e778d104975fc8296ced9a9393a71","run_fingerprint":"3e2c5fb74da9fa3d9b57097661eceaa49428714ea955869c0be90d4fa09e8657","score":1649.37,"score_display":"1649","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_626f9b1c4e05a66a41042aa2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":61,"at":"2026-08-31T18:49:02Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"69dd7fd206dd82e2099d3a20a7ddebabed028de8e50f6d6206ac5ccb303391c2","measurement_key":"aca8b4f65edeb39c84ec39eb68832842c08508181ba7013f6a5c46e622478264","metric":"accuracy","protocol_fingerprint":"ba0acd2b6380f6d31223b2c703e121207197f3c3baa061cd4b93ea020e111f23","run_fingerprint":"2ef1dda6ada50dc3a861a329521fdf7171326e9a4b4813aa37176f0fc1805c85","score":86.364,"score_display":"86.36","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_fa9e908ac04b067eb00182d4","benchmark_version":"HLE official leaderboard","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":67,"at":"2026-08-26","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"deb8901d0c21d6a3ce34e41376e012aaf3907e872006bb05ac9ecdf4e94c2bba","measurement_key":"f8846d678f07d48e46a74ef3fb645e8726d8f95c09944e7e5d731f7cef4eabde","metric":"accuracy","protocol_fingerprint":"cdd0be69efb364191bf0190a287662dcbb64c930f0f964558a199ae456ef38fd","run_fingerprint":"22485b6ac0e19bdd1f35ca12afe1fc9b8ea6cf0f8ccf688ea7bd610ffbe9c37c","score":55.3,"score_display":"55.3","source":{"id":"hle","name":"Humanity's Last Exam","url":"https://huggingface.co/api/datasets/cais/hle/leaderboard?limit=200"},"source_authority_tier":"A","split_or_window":"published-leaderboard","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_87d39e2d4e9d451f3ef67d65","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"C","evidence_rank":5,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"self-reported","verified_status":"self-reported"},"unit":"percent","verification_status":"self-reported"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7ceb053021ca94c49f4ab34986b453979e748d288afca21d65ff91fd8ab2fc5f","measurement_key":"60c1a241df6ebb2937aab1758e6ad2b1af3b7f697108eba157c7c884f51dc35c","metric":"accuracy","protocol_fingerprint":"13ee860e88f983adc2c47da369567d12a1d1f8395723e394cb1382efe3f68f5f","run_fingerprint":"11e28dc791bed57fa4c2c2b246b231403ede2517252d4a6d27e2ee41b65b118f","score":39.851715,"score_display":"39.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_626f9b1c4e05a66a41042aa2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4fecb7b5fe96d28f44477d00eea3ee39a56abb09efc66d3107f2736b09082100","measurement_key":"569e5a5914dca05bcd0c688ad1ecda1be5fafb91937220eaab82c8096668f334","metric":"score","protocol_fingerprint":"89c8f336bcbc552acb7fb1ab594d4c5eae7ba289d39321f7da95665d4151de35","run_fingerprint":"b29830093ba1074c77a4e217bb74553fa83789de1da478a4ebc1ffdaf7676451","score":52.5,"score_display":"52.5","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6fb83191d8d301477d8b03347f28ea129f9148f4f5cf6a874e672c545955a2c1","measurement_key":"d80bee137ba82201d2721c66a79616ac8658d843469596db5334315276f0fff9","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"f385d93b3f327e7168e6d188ecc33f033b1d13d37a76337d7c8d6a75969abf4b","score":71.59078571428572,"score_display":"71.59","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ea7550e0cb1aa3e5a0a3c455","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"97cd5d613dedc19d2984979a77cabdd521a9509b101b1c146a9d322cf9a5d920","measurement_key":"e726928427fcce727442a2e8917bf5c0f1f14f2198771529c28aead35ff6002f","metric":"pass_at_1","protocol_fingerprint":"7e2098411bf4d25a7549ce193a1a70c35cbeaf4d6229edbc8c3ce65cf4acb865","run_fingerprint":"54cea8f77b707fecfcd51d5407c42d021fba10ef0903d6aa3f29ed82fcae9339","score":80.51,"score_display":"80.5","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"74bd3b9deaa56bc2f5d898fd273861f391a26c9ef97314f67c247937e6f51645","measurement_key":"0431d1e518632f7de33b0340c3e80ca7dc88acc44c66084aab68e483991a12cc","metric":"accuracy","protocol_fingerprint":"6fbfa8b1534aab5b541593f750003c3cc5fc52b021490b23a4a333d020c7debf","run_fingerprint":"79d24c81778865c06f24e0d3975da20fd8f554d4f2b6466d267d3d761742d626","score":86.059,"score_display":"86.1","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b30238cb6fa78f5d4a1b4848b13d09134845ecf35051232681ba360c30b900e0","measurement_key":"79217f1ff92b9bd02ff3abf97880aab5a213b4600db089a6000f2d47549e58bc","metric":"accuracy","protocol_fingerprint":"10722aad1392375e0e127a11421484e6486649b1bc97eb8f4d94df6e1c672468","run_fingerprint":"1cec2b4b5e1533803cd47356c620d87460350413fbe64ea2c46d168e14f3bb2f","score":86.012,"score_display":"86.0","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":66,"at":"2026-08-26T22:26:55.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0618903d95a8d584d9390b3cf584dda512c42555bba835215d194156eb16270d","measurement_key":"36bdbce7099d9ab09a071545a162aaea4f379ae9bcf67decf67d8b28de119194","metric":"mean_score","protocol_fingerprint":"0906296fc2e811218f86a4ba9b8dbcdfbc466389c3fa10d3c7bfda2fafb8e2f4","run_fingerprint":"7cb500e95308f79a05b356e35f8df30297ac5359065c486558dc820e8a591309","score":93.88888888888889,"score_display":"93.9","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2c955b72c37574c334f9f87fecceca50b20737887bdbd97290be0c9dc5532819","measurement_key":"fd804b126c1ba30a3f5a2e666c58ab7582f9301a8a0c4e3bc574cd76a9a2ab6f","metric":"fully_resolved_rate","protocol_fingerprint":"c3ff61eb4b72330d8e0f03a14ae1d0d4bb285fe548c6627e75b1e25d141a02a2","run_fingerprint":"5f8ab151b62c4767ad29454fc0c0e725ede96bd618f9cf87431b463dfd79b030","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:02Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"89e477a09683725297bcbacd7366b588acb6781ed80a72c1027a0b4b5cd694c2","measurement_key":"1d6abe824f5b25151185964dcd8ec059c14475c44d1df0b41a24a33412931508","metric":"subproblem_accuracy","protocol_fingerprint":"f18af38465f37df2ccbedbe4e44a9262b759b5e6705605a37f58b3188cb7020c","run_fingerprint":"310321cc916493bfdc993ed57a7814593ce8cee66d28edce66044d3c8546d829","score":51.6203703703704,"score_display":"51.6","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7f5a892f8608b1bcfaf9c196","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e0ef327efedd37a8368dc09eef029bc438f166c2ec453e3d0a4262b025c36930","measurement_key":"c6fb5656c1e80bcd34a4b315934f1afd37c631132b69e3340cd1a11ca6cc82f8","metric":"fully_solved_rate","protocol_fingerprint":"b1b49e04ca5b9f0a65e383c32a5cb751f9b877d63d20ae00ab459c2d1789e6e8","run_fingerprint":"e480326db71798dc1adc5e7f62a26df416be5d97805999717fa71542fdd8d2c6","score":0.763,"score_display":"0.8","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-28T00:52:15Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c55968d4289ba43277c4605c6bdeedf1079cf88c4626798b29d8c84ef2e47431","measurement_key":"a682b2ae8537a1fd053796cf3d738e20ef996118df42116beeabad0c8756cd76","metric":"resolved_rate","protocol_fingerprint":"eaaef31849ec7cec8b278a82aa41a3cf59c6c7b2ebfe351ba73dc096c1b2f259","run_fingerprint":"fadd0d0cb7b3c181614e1ea8769502249ebb299ae1d3b934f72db024b14d66c6","score":92.0,"score_display":"92.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-28T00:52:15Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c55968d4289ba43277c4605c6bdeedf1079cf88c4626798b29d8c84ef2e47431","measurement_key":"a682b2ae8537a1fd053796cf3d738e20ef996118df42116beeabad0c8756cd76","metric":"resolved_rate","protocol_fingerprint":"eaaef31849ec7cec8b278a82aa41a3cf59c6c7b2ebfe351ba73dc096c1b2f259","reporting_origin":"organizer","run_fingerprint":"fadd0d0cb7b3c181614e1ea8769502249ebb299ae1d3b934f72db024b14d66c6","score":92.0,"score_display":"92.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7cf6e9201f688ec9ed4df9e0bdc9882c242f49237d015308b6ef4aab95cbdd90","measurement_key":"9199d39f40b8176dcea86fa575ae193dd5c3d5e297d4316925e750bc559398f1","metric":"pass_at_1","protocol_fingerprint":"f394d968a83273ebd001decf638fa6dbc38319aec1849a6a23d3a8449fbd6409","run_fingerprint":"7f3369652346fad3116e5d1fc5baba8183dc234515b82af66f35f4171c54d756","score":47.216495,"score_display":"47.2","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_626f9b1c4e05a66a41042aa2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"08682204c130ec84e22c2fab61698b619eec52b38961d52b19cd0ff109ff1ede","measurement_key":"a00a6981c1e28280a914ee4e71cd305006855f64c817828532e8b4e8df74eea4","metric":"accuracy","protocol_fingerprint":"257b32c7a4567a3f859c0e3d0dd78686e4e45b052e7fac2e6e540f245c84eeb0","run_fingerprint":"351c25277cedcc5f4d55bffafc4ba87519c3756908993afe5aea66149f69eec1","score":62.921,"score_display":"62.9","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6da1796139959b91feb92ebca7ef2cbafd80dc6dd5fcff9f32baf78d76375e2c","measurement_key":"ad3bfbc4b7b31320641caf3c38a51a34c22a4c49dad6c46a2330d77e59f81542","metric":"accuracy","protocol_fingerprint":"c8f224bf5c0a14a85fa72a49eaa756c39cd9366b8ae75222099568309784684a","run_fingerprint":"cd4388d9f0c377a3d58ddf62d13164a623c5fb4494acbb0fa1c4eebeea121760","score":37.374,"score_display":"37.4","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1febbe40b94b58e448bf6d3146d73e71b332a18e52470d143983f88acdf49300","measurement_key":"03c90975ea840b3457f8ced2db8f0c25ef7517e130f0857008cc2a4ed48c4ed5","metric":"accuracy","protocol_fingerprint":"1726706cba26acaecc716e2891cb6e6729cd38f8e0f730d847be899d1d50f1b0","run_fingerprint":"cee37d1440e5e3d3a09140c1f2f4e544ba562a2e1ee18c6d7414fa3759d1d2ae","score":2.857,"score_display":"2.9","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d3c922ed9af924baf253054d61ee838d5e97d57c6eac64ce7d2d065e7a9bd98c","measurement_key":"43332c5fd8a03d1e329b260a51b1f79c45c2f833bd662b13f867d62930594c51","metric":"score","protocol_fingerprint":"fc496087d9740c9dd19f058a520713a048f21283f2524025ebeb98759e7438d6","run_fingerprint":"f3ae63fa468bd32f5890a6a2e51efb2db2ff611cce74a6d0286ba8aa667066bc","score":30.759,"score_display":"30.8","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_d3256297c99cce45effb308c","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fbcc424cbf0b031c3c61be61d8f2ad505012137bfa678e627718f148c498f4a7","measurement_key":"dd763961b4b2c9bb4830821ea040908062b04ba34d2ce2d3e57524619380468c","metric":"arena_score","protocol_fingerprint":"0f8e950b9cf98b2ce00266645ac047eefa3fea4823a3a40b09d6e44c4b0668b3","run_fingerprint":"9cffc18df28a81eef6a3feaa20b1c8ce834ef0a5bd17a6da259333f4dfe19f8b","score":1606.6486731495352,"score_display":"1607","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d35421dc8bde7a8d07e82ffb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"zai/glm-5-3-flash","model_name":"GLM 5.3 Flash","parameter_count_active":null,"parameter_count_total":null,"provider":"Z.ai","selection_rank":49,"weights_status":"open"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b32bf193a1f48e0fe7fa63322b8796d84f36f6851d14530baaa52fb1abae3e05","measurement_key":"ba0576c73e9689e38a1cbc4d541ab8e69a22660e321f6870b5a02109af3c1b9e","metric":"performance_rating","protocol_fingerprint":"ca66496b8f55b81a101ae4184d534d5bfc193662ff3fab9d6667fef5f94674e5","run_fingerprint":"5711530b200dc72bfbe0d71e9c8e8ed3ab023cfd8c97bba5958d6c73cfcceaff","score":1327.3,"score_display":"1327.30","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_02f18483087dad439956139b","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f74ef540e5c350970961b4f935fd3da46af26eaa0b0a44f2226e1ee1220491ed","measurement_key":"3efcd30fb9261a531182d1c6be3dfc464690d2515eb1af9f420bf10b5e1b0da0","metric":"pass_at_1","protocol_fingerprint":"f55b74255d42e0de1f4b986a9e4804117c4d727b32e7720efb953f25c62a8c39","run_fingerprint":"453274bca5a7a2d5589423d36f84c333a5161e0e59a06b6dccca580924cfc6b3","score":43.0,"score_display":"43.0","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_d4a7e98301a45fe263315cae","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"appworld":{"benchmark_release_id":"release_3fa145932216c0afcdd9dae6","benchmark_version":"official-c1f56015cf7c","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":164,"at":"2026-05-21","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"97c558a666620ee86562bba0f0c3f218f73282a75af6151e219cb8ba46bf6cfb","measurement_key":"7f524e8d54485087c93d5144720ca012b4240f80d2e520955d19e81a7c08a85a","metric":"task_goal_completion","protocol_fingerprint":"fffd4ca8543c5af8b9de05f6bc02595ac6a01c285f093c90520fc13270ab41c6","run_fingerprint":"6336f94d4b9c028c2bcb250b8e0efa3899b18f7da3d69c822fc82f50f5e76276","score":98.3,"score_display":"98.3","source":{"id":"appworld","name":"AppWorld official leaderboard","url":"https://raw.githubusercontent.com/StonyBrookNLP/appworld-leaderboard/c1f56015cf7c3441ff1933f5bfbec879798d7bbe/experiments/outputs/_leaderboard.json"},"source_authority_tier":"A+","split_or_window":"test-challenge-all","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c0a0659ba50bddf183888efa","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b2cdb1d5bac86a9ff0b2bf4000dd98cab2a0b5519dd508ebaab4253dfe6a48ee","measurement_key":"e3242349d2b0295a4298640b1dec391685472e6ddc39c6aa77d84e7813f1a835","metric":"pass_at_2_accuracy","protocol_fingerprint":"1524582ed693ccee7f08afa2bb1f91e502bc548f5f232eddfb3f196bda91939c","run_fingerprint":"4b99b944cf57eb25a115c48d921017a24927c2daa7bc87ea6609816ca1f37255","score":86.0,"score_display":"86.0","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_258fcb8ee8e5667bc1ac3d85","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4231a538322dfccf09c8ae1601c6a8035d5239cd383ce76bfb9153d9207652b4","measurement_key":"22a830d9f701c43b8e74453f511ca3dce5308e614c5a23da41ec2ec32515b2e4","metric":"accuracy","protocol_fingerprint":"11a379dad5a9bd83ac82b0619340f7e3af4d02aada4a2643ff8f4053b46d0328","run_fingerprint":"a67d92ae67f71abb062495d8ff1c179bd7266130c6d5d8f75b37fab002a994be","score":58.330000000000005,"score_display":"58","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_258fcb8ee8e5667bc1ac3d85","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"eba54b3399f0a45b5ffe6a58662f9efe9ad83489ae5e16a26e9358a1946b9ee7","measurement_key":"ad42ea8a826d2b144f13b2da4febdccbb569e96213917793f5a0f73276845b4a","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"48f7035713a59a0af997563bed8c8bef8ff9aea04b06cd9676ac973ffd3965be","score":1471.9506765539006,"score_display":"1472","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_5f4b5142e38dcec1edde2831","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:44:15.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a04336f1d7cf355a900c576ac9cc982f60458f8685ecaa465bba8ddbebf7f033","measurement_key":"7ff648b149a9a8eb05d2bb2ea470fde36ba3306989113d42ae1206ba8b4e82c2","metric":"mean_score","protocol_fingerprint":"c66da0092512f74de68fd680771d6018e5452bf64c86abc4105294326535b87b","run_fingerprint":"822548018c46cc69aa86623673db241dacabee2e0d754a28dbcacfd7d8da4379","score":23.0,"score_display":"23.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_258fcb8ee8e5667bc1ac3d85","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-09-17T14:33:50Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"57d7a9803d957a1f48918e10276593816061d826a83ac34dacbae9a860e0a72c","measurement_key":"5430393c349b73d94681aabd11ab9bc25bccfe3414859aeea01385c4ccc6f779","metric":"accuracy","protocol_fingerprint":"a5b147e0e3ace6b42d6a12d624727187fa8b751251905e2567ddc62efd7d79c0","run_fingerprint":"9bc907a4d2f34dc58209f40923b9c18b12a8953c9ae5b76c341c6fa690fb7bf8","score":0.857143,"score_display":"0.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_e0bdc98a9afa7f9145f07deb","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"165d363bb652874fea00c9e143c951ca2e1a6450a3fa20407b50794f7b4fd176","measurement_key":"5f241a65bd3e2c0ecaf7b601293306eb515acc7faa6db8fe72de676c4ba28213","metric":"pass_at_1","protocol_fingerprint":"ada28153a47df2486f049859a8052f5c5e8be46e72fd73892686844c49cb15d6","run_fingerprint":"da795be427acf83b346f70b1f2dbb787623e71a42c3e8aeec4627c3bdaa176e9","score":29.933481152993345,"score_display":"29.9","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_d4a7e98301a45fe263315cae","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d1d93580b845fa6b43706607808a77c1500c57816f50cd2d2c96608445d8895c","measurement_key":"a177181643944d0a6a402939441a253f6e8a6e95cbaed318876fc83e0e6ac7c3","metric":"eci","protocol_fingerprint":"980f8f93595b05b888c932ddc39ee9695a3bcbe72f2c039fb66705210ce2b2f7","run_fingerprint":"974e54d1630df925dc9cd7c8835edbfe6aebe16917ea9a1fb6c42205987aae19","score":152.9,"score_display":"152.90","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_da95b541a68b4f050b9475da","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f7de25978d229d50f1f62781804744fc458fcf7b85e51a593b9a5e084d708cce","measurement_key":"16a56188c377276b7ae7299d27077999949a2101017720d0aaad36ff27ce338d","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"363f5ff210e51b2137fdcc9eb345984fc28f27ee9565cbde91a4859553167d2f","run_fingerprint":"46690b72cc6c4769a826e86b5058060c40886b3e2f5f7c6d28a8bf153b490e59","score":24.310000000000002,"score_display":"24.3","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_258fcb8ee8e5667bc1ac3d85","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b00ba0b8f87159c55d7bb32e98c9f23dd8afb4bc817307e304b5f38085b82733","measurement_key":"bf0d824a57a6d22a4998a3d491a2f0ea51599061af6b34be3ec1a399df0688fa","metric":"elo","protocol_fingerprint":"b597932890c8fc89967f508f21a13feb75690351602b3d29d5070926c8463835","run_fingerprint":"6a9189e1f9b59f1c2329b6a7d58410430c63dee837d08e7b852a2c3378a545d2","score":1240.5,"score_display":"1240","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_258fcb8ee8e5667bc1ac3d85","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3387971a9211e952e23148f51ae38d8e6115f3fe1c1bf3399647f9cfc084acb0","measurement_key":"3ae07310654dd83c10da0c6859900be9a8b48b526cfbce16a5bac4e8ae6d65ba","metric":"accuracy","protocol_fingerprint":"9823003a075d79bbbc67d654070bf256fcbd99aa52e3e41701ada9dff0700b04","run_fingerprint":"1b1fec15bae678cdd6ec970b54d94f111d30955fedef1e428bbb05a5836fee72","score":85.606,"score_display":"85.61","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_258fcb8ee8e5667bc1ac3d85","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_c1afb6c54b8ceec8bc1f121c","benchmark_version":"HLE original full multimodal","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":124,"at":"2026-06-30","last_confirmed_at":"2026-11-01T07:28:19Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ff5469580f4c8a133ad1cde008b35a24d9aa88e1ea5e12550f416c0053755308","measurement_key":"deca8d5e69fefedeca3a80255e64670de989f051cbe3b30ec68a06f74b710501","metric":"accuracy","protocol_fingerprint":"f3369573ec5fa708c2fb1887738ca58a6da3b6f6fdd4087151c44904e7e0c723","run_fingerprint":"45041b8488488b3f51a0825fb39be6084ad10a2ce27b301d8c35e49eb1377cfa","score":34.6,"score_display":"34.6","source":{"id":"anthropic-sonnet-5-hle","name":"Anthropic · Claude Sonnet 5 System Card","url":"https://www-cdn.anthropic.com/283ef97c476cf442c91d9a37d5b214242a55bb92/Claude%20Sonnet%205%20System%20Card.pdf"},"source_authority_tier":"B","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1a899ff2f2c99f660795bf87","raw_label":"reported","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-17T14:33:50Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d86d22cce346e8c977776f4cd2bbae51a3c10261f807fa65767d8b5c52dffc95","measurement_key":"2ae4d5d5cbab150557a4e8900b102c2d296c8aff0f2f4473718146e86099f39f","metric":"accuracy","protocol_fingerprint":"b982a6b744e7fd55a5a61ca3b7e90f01a548066ccee70340d09bdca8af5787fa","run_fingerprint":"d8098d508d4db58dc96463124829d48b7c35450809c3bac6d8031e0ab3c50235","score":11.214087,"score_display":"11.2","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_e0bdc98a9afa7f9145f07deb","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a4d9a46c15df94831042edeee6f8b891198849d05a0b713aa3c656e73df8ca24","measurement_key":"3b5a3ba29a8c27ff83848220b9807d56461988fbf02111961019617c3350166a","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"ec4361f63ef16f39914180cc5b0e517f7cd8133e6d2c84f7e8ce48879ca47cb6","score":72.99002380952382,"score_display":"72.99","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_02f18483087dad439956139b","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"61c6ded338265d644829ea59503d8772387ccc977dc031e72903e9cf5d89331e","measurement_key":"81c301f3a08bba97b4786e3a83341ebff0fbe2d530dfa216be34a9bffb6b7a3a","metric":"pass_at_1","protocol_fingerprint":"aad869c531a6e7a41ee6b771fa40c013448dfd0b1a25c1a825727394cdd11df4","run_fingerprint":"871aed967fa02ba434b002838fb7c593796b2d57278848e5569743d6aa67c61b","score":82.091,"score_display":"82.1","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_258fcb8ee8e5667bc1ac3d85","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":359,"at":"2025-11-06T22:29:16Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"8b90a4fb6de64ed27d3defae00977198c32f9cee97fdb6db6e655689cd2752d0","measurement_key":"948c54e5f1e5a8a1e98b8f7b09fbac69c3cff603f04a7b8c451b3878b3e02a86","metric":"pass_rate","protocol_fingerprint":"19d7bcfe73d61dd06c69b40a32f6b61a5f08efe933ae7ca022d096f95c78abb8","run_fingerprint":"a993c155d02da8f5a9b2d53333886ade047ecb5659c08eb977eedd0252e51207","score":69.5,"score_display":"69.5","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ea6c6d9a53bd19b358288011","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6f655341c19f9e7419b7a3043c2bb2353dc8e88b58f5dea29ca3625b117fbf92","measurement_key":"40c504bc549f2787fd635c06d87a764a14f25e67698d7d222b84c64c3f3a7385","metric":"accuracy","protocol_fingerprint":"3cb39cd3839198940da29f05c4c5f7967c69f284104e7cfb8033c3968b9c1d5f","run_fingerprint":"d7f91be7380a159287722ad3b73e57d0b969cf12796aa44c884c3830a3f2bf96","score":87.341,"score_display":"87.3","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_258fcb8ee8e5667bc1ac3d85","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ed8343c16b1addc92d65ed9da2e909575f00445b3f163432ad58b88d57bbf31e","measurement_key":"e186d50ce2062e21a221beac80f59963135f6a5a746cfd2629db7962043af67d","metric":"accuracy","protocol_fingerprint":"aa27cc7123f0eb619196124a5c8b8020d1af2c5faaf52acfc63a1cdb5bb3c67a","run_fingerprint":"913c8b928f388de356b7fcd1f1ecf22b8431e81cb43c39ba0751a19c4e768d5b","score":83.584,"score_display":"83.6","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_258fcb8ee8e5667bc1ac3d85","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"osworld-2":{"benchmark_release_id":"release_15c5525fe39f33bc181dfb69","benchmark_version":"OSWorld 2.0 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:06Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c297b4714f322c5e78a6770bd01b28c5becd745efe97eefc230bd777881a0051","measurement_key":"6d3fe76b0315683303163543c6cebd934ab76aa141863a92b30d137c2c47596e","metric":"binary_accuracy","protocol_fingerprint":"420f7d7c5f6431f39a1c12e26e98cb549477c9ac8537259a07c290e052f5f225","run_fingerprint":"eee6d26c91842eebe82db7a4092b9e10eb9124ce3597e7e411589530db7c2b13","score":8.3,"score_display":"8.3","source":{"id":"epoch-osworld-2","name":"Epoch AI mirror · OSWorld 2.0","url":"https://epoch.ai/benchmarks/osworld-2"},"source_authority_tier":"B","split_or_window":"binary-accuracy-500-step-budget","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_258fcb8ee8e5667bc1ac3d85","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-06T22:21:16.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3811652be3b0fe80aeeaba391b48220f97fb8af4478be65b69c7825a8629e3a0","measurement_key":"da539f5eb413af74cd10648082d30d7fea9625ebe2ebc9f82f714e62fcf46584","metric":"mean_score","protocol_fingerprint":"0f46c770def16a961a1818eaf4b929b42f199ee5e3b9864469ec01a2413995cd","run_fingerprint":"a4f378820f42bcf8b92239a8aea8e141cad014b52dced10da3690d51b746a189","score":71.11111111111111,"score_display":"71.1","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_258fcb8ee8e5667bc1ac3d85","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c26c9b6c5a94ee20074df3ddaf898111e17b0ba6f661020468211d047b93d58c","measurement_key":"cae5792343844c1029b8d80e76b184a9372e1037edf4e104add774ded51c67a4","metric":"fully_resolved_rate","protocol_fingerprint":"52f7c8e9d70bb8553974275905dd71dbe6ce063254ab9a26da54298ca112d509","run_fingerprint":"b814b9b1ef8f151a38cac64809ad1cf105f56e92535bca40d47d367bdfd647a2","score":0.5,"score_display":"0.5","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_258fcb8ee8e5667bc1ac3d85","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:47:54Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b651a3be322381977b8620ed2273f737abde6ff69a16a96964acea8364e85daf","measurement_key":"2f1b8d207c06249e6f83293ded77667995497ae28076026467f9cab4908f9883","metric":"subproblem_accuracy","protocol_fingerprint":"efb8fe7fec2a2450eac8fa367c73e99ae36b1f2644c728fa4cad58d2a1ab1c4f","run_fingerprint":"472dd3d75969c41764766376ae2bd714c60b35227632f4dc43e58eb5d13a7ec8","score":46.7592592592593,"score_display":"46.8","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_258fcb8ee8e5667bc1ac3d85","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:27:37.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5be1d687e66076e67e980a89293ef262a5f049b95a195480d33f1b20ea81c63c","measurement_key":"4c7e89b374e5fe74cde935c9893a8fde9d672fbcf23a88ddbd1f4e16c8d306b3","metric":"accuracy","protocol_fingerprint":"b0e6d3b8121dc6f9eb2cae0167640e4069ac1148c0d8cacb2a79d747591e72ee","run_fingerprint":"08be4d2e546c4654e4297ad61f34549ba722e68740c4fb04c299ec4c175a70f0","score":32.800000000000004,"score_display":"32.8","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_258fcb8ee8e5667bc1ac3d85","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"skillsbench":{"benchmark_release_id":"release_093b45b8b752b3f08534f6ee","benchmark_version":"v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":138,"at":"2026-06-16","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"31bcbd09a0b42b64548d2815acf867e65b21cd4ecc5e9efd0b00e05e6069f9bf","measurement_key":"2ccecb580ed40e9c718ba33d5c72855b2780682aa18484611d137ee2aec644f0","metric":"pass_rate","protocol_fingerprint":"c2ed2025e534826e5e627446f4493a128269710491b35eb2122abbaf19d56304","run_fingerprint":"209061e382ac90e2297519b0e9919b8330faf6c64a91d83a31713a0db3e20f4b","score":47.2,"score_display":"47.2","source":{"id":"skillsbench","name":"SkillsBench v1.1","url":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json"},"source_authority_tier":"A","split_or_window":"official-87-tasks-with-skills","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f443077f18b018dfdf0194f2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ac475b4d74b4b8dc67abbaca4bb08ddef41781ca3096731376a6a9087b441dc4","measurement_key":"41a87e02bf39376b22717ccf3041360c456ded83b0d9b2383f0a7f4f3ea4b947","metric":"resolved_rate","protocol_fingerprint":"8e5f67404b253591e5c15671113eca6c244d022802e49f968e736452412c83f9","run_fingerprint":"c2d46aed4af0a99d2ed5858e99a4a1feec24bf56ba04f76bc046ecc9fecdc9cc","score":77.4,"score_display":"77.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_258fcb8ee8e5667bc1ac3d85","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ac475b4d74b4b8dc67abbaca4bb08ddef41781ca3096731376a6a9087b441dc4","measurement_key":"41a87e02bf39376b22717ccf3041360c456ded83b0d9b2383f0a7f4f3ea4b947","metric":"resolved_rate","protocol_fingerprint":"8e5f67404b253591e5c15671113eca6c244d022802e49f968e736452412c83f9","reporting_origin":"organizer","run_fingerprint":"c2d46aed4af0a99d2ed5858e99a4a1feec24bf56ba04f76bc046ecc9fecdc9cc","score":77.4,"score_display":"77.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_258fcb8ee8e5667bc1ac3d85","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_72d764965dd7baf34f983249","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8d5c6403f38b12208106d7a4460c0b870b1caede8d7fcd6ecc9539cc5229104b","measurement_key":"890cdd400b5198d56dd9ef5b06cb29b554015c55abd2272dc7007768a13e0139","metric":"resolved_rate","protocol_fingerprint":"690f71bd7ea1ef47ffbe550903858995f642b0efe28b1a7c4ea90de3356334b9","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-03-01/2026-05-15":{"benchmark_release_id":"release_72d764965dd7baf34f983249","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8d5c6403f38b12208106d7a4460c0b870b1caede8d7fcd6ecc9539cc5229104b","measurement_key":"890cdd400b5198d56dd9ef5b06cb29b554015c55abd2272dc7007768a13e0139","metric":"resolved_rate","protocol_fingerprint":"690f71bd7ea1ef47ffbe550903858995f642b0efe28b1a7c4ea90de3356334b9","run_fingerprint":"d5bd5ba287f21671b93a9c7a9d584cdccc472474131a2a2b0f115faf67c5facc","score":51.272727272727266,"score_display":"51.27","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-03-01/2026-05-15","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e6ae4e8ef0b5692fde876ef0","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"d5bd5ba287f21671b93a9c7a9d584cdccc472474131a2a2b0f115faf67c5facc","score":51.272727272727266,"score_display":"51.27","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-03-01/2026-05-15","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e6ae4e8ef0b5692fde876ef0","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7b3f63fb2ac19f8d49fdb24412102cf6f079e887498d5364285522eb60a3480a","measurement_key":"ba5c8a3edaad02d85423a8ca198cac318d50e460282ff930e1fd895daee44577","metric":"accuracy","protocol_fingerprint":"8ed890fcf8d1451ae67246ce2f9adab263633f997f49cb98fc511069ce87215a","run_fingerprint":"228f77432156606581145f4b4723a4cb32e8b16dbf9addcce9cfbabfb2c95fd7","score":57.303,"score_display":"57.3","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_258fcb8ee8e5667bc1ac3d85","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ef1040d9f5d5c4da62a23a33e532859bdb4096adeef9e21721ed8383a55942e2","measurement_key":"e79b0c1827d30aeb97e75c66669b7de2650dfafd7b512baa84120fecaa0896b0","metric":"mean_final_balance_usd","protocol_fingerprint":"592565df30e1bc460e6d17b003278a36e3f11fe81435287d81c0fdf1680364be","run_fingerprint":"e55c98a6615e13f3183066b69bc5d1b10c15378771758a182325453d145f993a","score":7204.139999999999,"score_display":"7204.14","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2d36a21873281878c5a3aed5","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3ba00c5a446aa05b3807c5aa6d8efc2d2025854a8fae8bff21e2d70974fa221e","measurement_key":"cafc30e4988398edc1c074c3462f56b02abb3760c74786fdfabddecf06481ee5","metric":"score","protocol_fingerprint":"dbee190ae846a89beae131211a82cdf080cad285932d0350b9fde2c272a22d1a","run_fingerprint":"f1572b7f5df743ce5ea86c78572363f7f1f67f4f30751244b2ee65dc38cec2e6","score":51.476,"score_display":"51.5","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_258fcb8ee8e5667bc1ac3d85","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7c4f0ce11daaf748bc508f92e1816202aa1b910443a128e28e187e33b282288f","measurement_key":"2275ba780aa84be486dcc4189131d59d3706967c4512135559af223e7fd13493","metric":"arena_score","protocol_fingerprint":"802905efecee23aaa096cbfca9dfed1ec427d2d6e0bc76b1017d71ed61c7d305","run_fingerprint":"1a458ac971e48b351480174ab0279c01ca592185e88bcf615126059877fb4c99","score":1522.6524947374642,"score_display":"1523","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fdb9efd11c7d6668480eb672","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b7d5a83a4b3d3087051b276d3d55b5bcdb65c2bf9ffe50c40d12364c3e0593ca","measurement_key":"b080305a31d5ad59ce208c4f69417ca3de61fef2b666a5b345c9d5aa53a12e2e","metric":"accuracy","protocol_fingerprint":"88463472ba6da2c04df6df5156dfed5441a09f74efd6bddf4e43c096e3295fc0","run_fingerprint":"4c30244f6e2c4dabd9cefa278cb5212af4f4a531821adb61deb172ad8a933434","score":66.07,"score_display":"66.1","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_02f18483087dad439956139b","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"anthropic/claude-sonnet-4-6","model_name":"Claude Sonnet 4.6","parameter_count_active":null,"parameter_count_total":null,"provider":"Anthropic","selection_rank":50,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4312ece7fc314c2863a7d980c30e4d7fbdb7b55c30c38c68f94e110b2e5eb320","measurement_key":"4385c6c34cf9f41a33389ab2cdef3bc285554c1da0b8fa81629cac62b973926d","metric":"performance_rating","protocol_fingerprint":"8b0eb079783f5c9bb32287042ce567a1452c3399a3ddbc9506476318f495e6ac","run_fingerprint":"e11a42d03c713212717b1a4894aba20cb28ab220a3ccf013088bd5ce09a1305c","score":1150.28,"score_display":"1150.28","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c7ba76e47c689d327667a5a8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"13df1fd4e0d4f61d2b5ba15e71860dd34c8ec131e14cc685cae19a66e83878b6","measurement_key":"437e0d1285f11f0d824c84695e7622985b967878545695d48b07113a12301d29","metric":"pass_at_2_accuracy","protocol_fingerprint":"c6afb855bbe79a876e8648668d61283fd4fa5aec6eb157ac1907db4cb7ba6129","run_fingerprint":"77d2d19ab79c543cfe1e321998afe6ebc2f98bb4437ff13b03bb3285edc150b3","score":89.5,"score_display":"89.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_899434b1ccae0f0aa50272f9","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"49073a92e6a13982bad282b7b6efdb6971050a620f80933f1879318bb50b0ed4","measurement_key":"635bc9f64733cf65475eba4704cde07d5968137e2fc74c0de5013a30dcc51473","metric":"accuracy","protocol_fingerprint":"c3fa0592b6441af3735d852e2d062d733783e4f6e00f6d83561e492ebf372c72","run_fingerprint":"33d6687ead19ba47d8616ec109f4543df42fe7fb2684ba4c160d01c92a6144a2","score":65.14,"score_display":"65","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_586ef081fe8e74ae64d06ed8","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6c94d0de4ee6551417683ecc0f76640e39c9c4db5bd4c9a8ac14aed32bb7958f","measurement_key":"be1c5df7a8a989d2894d36b6ecf81650f901451c2f00dc4f6708c65cd612723b","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"351135dae2f83c5ad92d6c9e4c14aa68f02ee04d29ca7cebbaf7c901d03393a4","score":1471.7400417518265,"score_display":"1472","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_586ef081fe8e74ae64d06ed8","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:34:38.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6edf63d19ca91f2d5bb5d83773cb4d232ba03eb5e8b25427e99359da642ddf0c","measurement_key":"d9d4298b9d4b3a473c699d34c919c05006b4fb748e36617e96ccb26b2ff84e1c","metric":"mean_score","protocol_fingerprint":"4f5dace898c3c357370c69540392f8287ef657acaa458f53cacfeafb48ae6024","run_fingerprint":"76a2b11fd202f219d49061f4eeede64917166b27d7ccb77a8fdc736d3f221114","score":28.999999999999996,"score_display":"29.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_586ef081fe8e74ae64d06ed8","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"56cac6e8c7b960175be5d72b88f9a6735fef2ac76f1a9b127aaf48aa8b8f0f97","measurement_key":"edd4b4e7f4248a5d248785a8fcaf4b225c4ed5177883ba40a71de12c7b684595","metric":"eci","protocol_fingerprint":"a1ccfca62b1f49597d8087fec9f2cef23768e4b846b52e21eb4a41ce8b793c17","run_fingerprint":"ba440d569f4450866a2c2827c76e511532711ac9436a718cd3361193b84057ff","score":152.26,"score_display":"152.26","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_907345bd817b4bd0177c506c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":110,"at":"2026-07-13T15:51:35.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"32ba05a67afa0bc857f3ed8724713c0ea448f6b9250c077586fe136f105d909b","measurement_key":"45af515a200e5c63178e9b3d1d94ffcc56800362bddac036f1d33576c8b0fbf0","metric":"mean_score","protocol_fingerprint":"107b35476888ddc67d09c05c0c48dd53aee5142afadbc44eb185acc3f8cec81d","run_fingerprint":"60918ddf07707c67d5cebea0f0997eee0657f32676d342f1ab03929612d19aeb","score":44.91228070175438,"score_display":"44.9","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_586ef081fe8e74ae64d06ed8","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":110,"at":"2026-07-13T15:51:35.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"acf13b329cc9fee84f57f1616208fd5731eb697b4a3918f74783db6d7b8ffc81","measurement_key":"b24ce530180d14a22870d6bc282daf7c516683cce63f383f8fd14b55a6b2f7a0","metric":"mean_score","protocol_fingerprint":"55c3e2eabbee1ba0c01a0bdac6bfb587021b6787918995cf0ae59abb2103760a","run_fingerprint":"ccea13b7b9f513315847d29ab4a00e81d36fc121c3cc4db162a6ff33c55c0797","score":17.073170731707318,"score_display":"17.1","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_586ef081fe8e74ae64d06ed8","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":233,"at":"2026-03-13","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"37b0c4e054dd8d9b781bc891a9e7021248eaad094a3c77c9bd56e403f8afb39d","measurement_key":"7d849145d83491df40469cf572b959d00e25eb2234f357a5fd70cda9e5398b6e","metric":"accuracy","protocol_fingerprint":"d139806585c7948dae97cf14f6c8e3161b21a91323f1bdba4dda4c953cef256a","run_fingerprint":"525b2e379e2a2c881901fdee3bb659b21a2911e49352b7ab7b4f16e246845ab2","score":88.636,"score_display":"88.64","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_586ef081fe8e74ae64d06ed8","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"40c0ce67c0b095d43170b0bf1931bfb0a7a7aa6e7c199af25ce856feacc34d24","measurement_key":"f6752835280fd8763d9c9fef22660f272b976e42e01b478c9acf5eaa4414d57f","metric":"pass_at_1","protocol_fingerprint":"c9ce2cd99fabe1fd928be2d8007501cf70f10e002dd25eaab7a4b664aa20afcb","run_fingerprint":"c4cd50e107e56f2ec7ad6ded3b2fa557f78ce827f735b84dc04c0d78394d5013","score":84.265,"score_display":"84.3","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_586ef081fe8e74ae64d06ed8","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"37e42b6fccaebf48ca4662816ed6942ae4f72e47bac342188b0e4ad8a9e4f6e2","measurement_key":"cb69b1b833efad4c535230885e4b2aba6d9bd5c9c4f85040d096168f48b58f62","metric":"accuracy","protocol_fingerprint":"6670a4d34719b13c91512ccd0718df885c2b66d4e4819df6701967bf1fbf6dfb","run_fingerprint":"fc6c6e7514edbbd32af7ecfd9d31c60b8d89d10f0d3efdbc855ec7cc930769e2","score":86.254,"score_display":"86.3","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_586ef081fe8e74ae64d06ed8","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":233,"at":"2026-03-13","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"fe7318023d1b681255d990634c27d4fe8302b16cc742d72a916a8dac13eaaaf0","measurement_key":"838b520a718c967ab2dc7d36eb3aa1100b35f679bf93e6fb226476feb314f75e","metric":"accuracy","protocol_fingerprint":"baf76148bf8f3e45d14335dbad417dfdcca6a6314a043d95db1f64e234bbe891","run_fingerprint":"f2cae986e2b6c4d182ef30afa93926a5d872c4346bac471125999dea792f70c5","score":83.468,"score_display":"83.5","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_586ef081fe8e74ae64d06ed8","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":110,"at":"2026-07-13T16:45:48.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dbc47bcc2ff7de4725ca2c16341a9ece1efe1fdf708281b53d7fe43cfb6cb3f8","measurement_key":"04032e36a245fd49aadce362062437548bf57fdc0bdd248b340e1e0365f7f2f9","metric":"mean_score","protocol_fingerprint":"82e13eaddc2ac54e19768a7bd6791e3aa6e226b89a4a8d14629617a9d47cd1a4","run_fingerprint":"bb48b7e5cec6f16ac88e738f880146017f03f25224a07feb31e2f051d2507e73","score":92.22222222222223,"score_display":"92.2","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_586ef081fe8e74ae64d06ed8","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:29:44.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6e913b1f44638151bc6336a71298e51db43904fc27995b1eeb31e637c3fd6919","measurement_key":"d5f40d2f08d9e5c16968e546e2194f0e0dd0c7716e8788d27af2529ef956d672","metric":"accuracy","protocol_fingerprint":"4605760acc55f59e9cd7de869182ff241c553644767751f7e85e6c82330175d4","run_fingerprint":"aab135ec8b860538d1e149125c3ac67615b2dfe03f1f6788eda573b392a3c222","score":30.2,"score_display":"30.2","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_586ef081fe8e74ae64d06ed8","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"59a6877c6755585e1cb47a40a6de6a87400dbd530797baf45289ce9315b36807","measurement_key":"5ea6e9cd624db347aaff79af854b9acdaae16a97c967129bbd093d27150ffaa4","metric":"resolved_rate","protocol_fingerprint":"cf0baf539458fa193ad58ce64c575c7887469b4195c3ed1940d846835a7d72bc","run_fingerprint":"3bbf8edf6eeac9833a624a1721cb723873b01aa6ec69c7d836a9de21a21f61c3","score":72.2,"score_display":"72.2","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_586ef081fe8e74ae64d06ed8","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"59a6877c6755585e1cb47a40a6de6a87400dbd530797baf45289ce9315b36807","measurement_key":"5ea6e9cd624db347aaff79af854b9acdaae16a97c967129bbd093d27150ffaa4","metric":"resolved_rate","protocol_fingerprint":"cf0baf539458fa193ad58ce64c575c7887469b4195c3ed1940d846835a7d72bc","reporting_origin":"organizer","run_fingerprint":"3bbf8edf6eeac9833a624a1721cb723873b01aa6ec69c7d836a9de21a21f61c3","score":72.2,"score_display":"72.2","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_586ef081fe8e74ae64d06ed8","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"70454c1f1d47da3efc2702ad47f0dd903078b56c5d5123e85704cdce017a4e29","measurement_key":"59a55cec5a5bf864daedbcde1e4b283dab1aeacd9fcfe808d4577e0619a5f663","metric":"accuracy","protocol_fingerprint":"16472b06cbcbcd02677814e45388df9d6d7b2063dc0912d53d664b202a63ae35","run_fingerprint":"0a99b96fa3771a4202757a3d5ab6de653e5e2accddddc5bbf80d3cb129e6c7cd","score":44.195,"score_display":"44.2","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_586ef081fe8e74ae64d06ed8","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"af9ed87e23073ed45b82789027b9b65a14da4390bebdbd0472981a1c698a56a9","measurement_key":"304703c04027c791fce1c8f380884433bb8bd4c149bcf28c09a16649b5f1771e","metric":"mean_final_balance_usd","protocol_fingerprint":"9c035e4c8ddd029fc4d331442cb9952ff1acef4af6cb436912b4d82ed4942647","run_fingerprint":"9f95c10ee1e0e88c20da99fe61dbe4a5ae6567761994ad450bf4f2cbf34899aa","score":4662.846666666667,"score_display":"4662.85","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_91997adfb8f527350e6f7228","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"375e89879f26626043f2e5123ff159f04b63159565f6d1a75c729cb981d9004d","measurement_key":"820fa2db8b6e0a40d4242c45db40589b078f8ca836e3ec256bf5334a09606b65","metric":"score","protocol_fingerprint":"4b84df3c29186774ea86cf3521d8d64f489b089eefabe0935bd4420b60916c85","run_fingerprint":"d1ca00307c37674d1dda7ac5a80a4a65fcffb18d4fd5db6ff3002e7c2e3f1fc4","score":4.063,"score_display":"4.1","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_586ef081fe8e74ae64d06ed8","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6854a66ecb1bc9a23a345d8f48cf0840928239511d6f72df632ead68cef3c501","measurement_key":"06671167de481863ea12742708b51deddc74d2df9ea3b5b5480429dc6647c3c3","metric":"arena_score","protocol_fingerprint":"e640a3952747a7ed76657d5adbeea1fc2a75949a0fc4a4404f765f97ef071e2a","run_fingerprint":"1cd8ff0a8f44ab75d69660c552013be27a09084dca7a7fd307e2dabe324dc2f4","score":1375.4624441703345,"score_display":"1375","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_586ef081fe8e74ae64d06ed8","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7d59dcc39743128197e63a95fbcbf6bb3edaecc73c1dadb7c74608ac205b7a11","measurement_key":"9b9fce5e668be1d4bae75f6a1ab8769d4ec1f9cc53d7aa4d77ceef733c206fdd","metric":"accuracy","protocol_fingerprint":"fba795302480298a60aef10f1c2059807bfae19ad21f591caad5eeb0d0cf6c22","run_fingerprint":"33b2adbac8ea65752be7acf4777db39d6d3361db8dcf538dd3567ab83abbc7b0","score":52.26,"score_display":"52.3","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_97752946e06fcd42f05804fd","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"xai/grok-4-20","model_name":"Grok 4.20","parameter_count_active":null,"parameter_count_total":null,"provider":"xAI","selection_rank":51,"weights_status":"closed"},{"cells":{"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"548fcd7a18be4345693ebf86d576de2d43019f937ac45b7a4f82a1a121df6263","measurement_key":"b7cef134f387b73b6390a1826d39a0c1acd163245ede5b33c2b7a66d7e1955a6","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"363fd42ea9d29c7c11dc17dff4aac9c05901bdeabc54bd5b74e75db28cfeffcc","score":1489.0250787876926,"score_display":"1489","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_54436950921b18ec0c2e019b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:41Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"13cbf17052cddddc870d5bb604db6704740b717caabfceb515a8ba4492bfcebb","measurement_key":"81cc9c84235c8fdb5e41f3561e425e996e6dfb9623beda22886132a6c0e5ad63","metric":"accuracy","protocol_fingerprint":"65600d09ac84b2d20072d49a794cfb11bf60e2bbae25e4f9cc8ef0e82c365666","run_fingerprint":"0784446646e931b2df38416335ce3dcaaff2d4b33e89076d1c1c7f11d459b584","score":11.330612244898001,"score_display":"11.3","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_5638767fc11cbaf7aa5af326","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"663e2150930325559fae75ea9af1df0710b39096358d2527a468c519f4b797a3","measurement_key":"b1d520f6d46da2694107d558dd549d33c765f0180678fd2a0755df3e1b0360f3","metric":"eci","protocol_fingerprint":"539c531a6d50f29417df7c7cf89ce26576f029275954f1a6a17af0db5ec9149e","run_fingerprint":"702d741c3ef0147c50e9877211072277c2fd559d0edf31138da4d90ef65a6c2a","score":152.15,"score_display":"152.15","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8fb9ab5df9eef640038582d9","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"484ef473b7c75e4b6e708b36492684ab3d75c9c2a921df456110fd28479280f2","measurement_key":"4ca1a166e3960dab67011a2da921da3743defca4981ece951576a7c075715886","metric":"elo","protocol_fingerprint":"3514805a04926af1a9e75d945bbe905d97eed2400f8ee962bdae38ac8c054ff1","run_fingerprint":"22bd6716c75805b9e2aaac5e6d510b3d9489e811cfd18fa8d355ed3635d5421d","score":1006.05,"score_display":"1006","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d20f8a5e90eacbc5f8ebdd68","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a807c4623b3e8b45f92db984e4cad279029cd153e8ca5398b02e93ffe2bccabe","measurement_key":"80b66ae5e0c8d625d604032a0f8e184f7c3ac72f2748a2e7c42eaa6b912946cc","metric":"accuracy","protocol_fingerprint":"8eb94ce1c7eca4bb5ccb6ed3fc544b3506d0f84ddc2e21b3ba13374795c6a4d5","run_fingerprint":"c8cd5336606e9672becb7fee4b80de6a7e63a0d17e40fe2b47a4e36d303e9f28","score":89.646,"score_display":"89.65","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7503d5cd94f11a21bb05a963","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_8817af9d9a0235bce0826e22","benchmark_version":"HLE finalized 2,500 · Scale protocol 2025-04-03","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":206,"at":"2026-04-08T16:57:23Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"e122621b8bc52e8ff71c0a156d96101bfa7c4cddc22ac9913774f426e40d810b","measurement_key":"614aab525ead7b35f00428e3b3b87a1a8274d4d42a86cd70854cad0b0f897748","metric":"accuracy","protocol_fingerprint":"29a9169698df5029c4a6b85c5b7daea8dfa93d721983d47ec6c0a11c105f9ef9","run_fingerprint":"c3d65461620c8d18498231d2893bd153034c57b33f93971dc0e9ef1ee726f73e","score":40.56,"score_display":"40.56","source":{"id":"scale-hle","name":"Scale AI Labs · Humanity's Last Exam Full","url":"https://labs.scale.com/leaderboard/humanitys_last_exam"},"source_authority_tier":"A+","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_353e71505b6265ea76a3923f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":206,"at":"2026-04-08T16:48:43Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"e25bc00bad362f9433c6e64503352bddd82c7039d97dba45126794bcc323f61a","measurement_key":"f44ebd5925d86174801804bed938f98715b015cb58fba101c4d8a2576b50a757","metric":"pass_rate","protocol_fingerprint":"1344601c19fd0d96e2d88500e9650e5fdb22dcc813ecfcce82e2ea756a23999e","run_fingerprint":"d98ef2bc47ae46048a0a25b2397f9017cb6b576c42a22a019b6a74a41f2b4493","score":82.2,"score_display":"82.2","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c20d16cecbbd58186fa001f5","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1c6577c631648ca00b15a89b33ba72d6a8d53e491001e794079ce61607663881","measurement_key":"46126814b14c7d29b9e011381948f84c4e5d7534c87ac08691f5e5e210fdb3e7","metric":"accuracy","protocol_fingerprint":"488b985a7c1e9ad31086aae5ef1dac2f5c490af43542568bfbf68d78e6c74855","run_fingerprint":"c169d5759e81e0a5402ad68162cb8d8e552a8a0b470826aa047f5f637c440902","score":87.316,"score_display":"87.3","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1f4805d656bfdb6334fd4c90","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:41Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"35a5006f32850ff4cfa34e4351ad66d7c52d63aca10e9d052b90da6a2b284048","measurement_key":"3d2cc663e4b45974b6a8c9697feacf9bf02b46ad11538b6bf0d0ddd6066c25e4","metric":"accuracy","protocol_fingerprint":"75f6dbdd9b3b5a4be5d3e13162b6b7beae758793ff8e63f79bdcd40dc99a4d0f","run_fingerprint":"f76486391beee52fb05848249a61486ce555f5ee703c86a630e8042b4f5e1820","score":87.399,"score_display":"87.4","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8166611feaa70b222ae62c85","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":206,"at":"2026-04-08T16:30:04.184Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"494277d066064ccdf37f29ce588d0f4cb39c6faebe40430d65fd9d174b0e5164","measurement_key":"96a3b688e433a6f037e2dd03520c742426cfcfe0689e495217f25a79df83482c","metric":"mean_score","protocol_fingerprint":"828ff4b76440946102b6be1ecff774931e036c25110ae2a236ffab6b1605b468","run_fingerprint":"e6d038725a8e71601f5b1bd8741ab12a13c8096a71bc9505ff5b2520d28208bd","score":88.9,"score_display":"88.9","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_34bc8136627a1b5e0353c16c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:47:54Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e8a5198327ec04b34163dfcc54655701b1b35fb0e5f90532432b87cdaaa9ac90","measurement_key":"37a3b907901a985181a37de2d50034ef73cd7aa49cd96cc8040080b53d9efff4","metric":"subproblem_accuracy","protocol_fingerprint":"ff35bb91ca728f3e1a6604a6494745a4224ae935d13a0e1e1741a70135b63771","run_fingerprint":"c90f43397baa0b60f64d13aad84c3ce977ceced0f8866b305d859bfd2083dcd4","score":51.5046296296296,"score_display":"51.5","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7c87f12cd9a3ae0363f7226b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8447496a87e86403ff6a41c23746c738916928da6da0eac54b78d8af08e643e7","measurement_key":"3ae96b37e9d14f749a2e31c667058996879e07713739c01ffa992861fb413ed0","metric":"resolved_rate","protocol_fingerprint":"7d69ea4737f37bcd9bc25b6bfac9c4467657b2e6f16c887fc9bdfaaca48c26fa","run_fingerprint":"3568c676ff6d77664f19f8e27854ec5c1ad8b81c50df63fbb3869682b24f3b76","score":74.4,"score_display":"74.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c2ccf01d838a7e46f5423db1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8447496a87e86403ff6a41c23746c738916928da6da0eac54b78d8af08e643e7","measurement_key":"3ae96b37e9d14f749a2e31c667058996879e07713739c01ffa992861fb413ed0","metric":"resolved_rate","protocol_fingerprint":"7d69ea4737f37bcd9bc25b6bfac9c4467657b2e6f16c887fc9bdfaaca48c26fa","reporting_origin":"organizer","run_fingerprint":"3568c676ff6d77664f19f8e27854ec5c1ad8b81c50df63fbb3869682b24f3b76","score":74.4,"score_display":"74.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c2ccf01d838a7e46f5423db1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7a6bafb9fd8be57ed41b4ae5fb4764a656cbe8c9dfcf778e9cba59664eea47ab","measurement_key":"74a96ce5d4eb740c8cc9bcc8e33336a7d1b92e6f27449e5de7c88e8c394a4802","metric":"score","protocol_fingerprint":"f2a6d59e558bf9711e27caff7908e4b9b45d55c7b9a25d02f9f628dd62ad98db","run_fingerprint":"8bd1d25523be36454ad0272dfc06a7d3de4f35e28dd20f5ecd1b8eb92673dfee","score":19.674,"score_display":"19.7","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_caf27ae6f0e02b627cb46007","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_65fc140e7ffbb7bf62021f84","benchmark_version":"Text Arena Coding current pool","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:47:56Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"90d65fd5768874c5bd7a1520c4e48ada0fe66e7a7c619ce23b0bd5ac19f5a643","measurement_key":"632e5bf195869cb1eb7e30f56a13dacc0f232c048ef778c995d740bf974a22b2","metric":"bradley_terry_rating","protocol_fingerprint":"7478f140435c0398c7174a5112f26ce28b9af101e641529581b4f498d38610fe","run_fingerprint":"7dd26befd75b7f0fcacbd2120f81958cb4133fb70977cb9871b18aef48869d80","score":1512.53,"score_display":"1512.53","source":{"id":"epoch-webdev-arena","name":"Epoch AI mirror · Text Arena (Coding)","url":"https://epoch.ai/benchmarks/webdev-arena"},"source_authority_tier":"B","split_or_window":"text-arena-coding-bradley-terry","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3bf852297bfa61c449d25840","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"meta/muse-spark","model_name":"Muse Spark","parameter_count_active":null,"parameter_count_total":null,"provider":"Meta","selection_rank":52,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5b66724705786655a4bb8a26d3e0bf542525d88bd00721d74c0af1f118ff0e70","measurement_key":"b72bee69c2f94960e209ea7d0a8656101bdc73b1a8a0d376bd3c067365b3b18c","metric":"performance_rating","protocol_fingerprint":"4c1cf9e791c0b26576c00a51c42d25ce96855e5afbca22f2f22be725da0ad7e0","run_fingerprint":"b8a27406f4199a328f7bcbb5c6fed5ba4c93ee3a90bd5a32c6cbbd847a4d6c6d","score":1010.17,"score_display":"1010.17","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:12Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0b629c408b95276a12a2fb9308b636d137b3913a4fc5b4603fe7e00fd1e65443","measurement_key":"07e39fb0f9b5ab02dce5a602a6dc7bef14c9e835f51d1f48ba28b574f4c57010","metric":"pass_at_1","protocol_fingerprint":"e825f781a78eb80c3ea82eecae389e14eeb60209868b63e1f166b59662c1e788","run_fingerprint":"57ed3b868adc7190962560cea289fe4303feff166fda63f3d02f83cd2b9df7dc","score":45.2,"score_display":"45.2","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_27cd4b5c9a4a27c645ccfbf4","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f3817f812f44b714cae9cd96af933fc7705348b8fe289c3bcd629b3dde47e57f","measurement_key":"3aaeac2fa4807e4822b730c25d04be5bb675deca31bf572693a2e5f767d41b48","metric":"pass_at_2_accuracy","protocol_fingerprint":"0bc797d563c9920ad5117d503a938d125f8b22dab8024cd5dcc36cb2971a2a71","run_fingerprint":"897b95370c2fd09f6264509d0432cf7d607a3c711315f55894fd5b22b13eaec7","score":77.0,"score_display":"77.0","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fbde99d386073827dc60739c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e3992e98e916cf76698d29d0e9edd822c3a9dab8904c55ba577d4a29960014d4","measurement_key":"a1051d67850d652cfd2b73922847bd48bcf83ea75e26141a1c01ed18cd50fb16","metric":"accuracy","protocol_fingerprint":"ee7689cab2ecdae3f0d03646646ae70a43a48a3d5e8191ac81a5dfd541badceb","run_fingerprint":"bf8f587b3b34ee9a08654e4993dd2cd134683882f0683591c58b3534f3c7c4b7","score":22.775000000000002,"score_display":"23","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_35d0fa8752189fb3eac4cea6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ab5ae7b983caa4a8af9424c3d85a51a849c08a48b6f29454421574f00483731d","measurement_key":"8519b60dbaa3eefa5772c52a4e9827a485d50b7a0efbf8fe334930d71f77a4cf","metric":"ips_score","protocol_fingerprint":"1cb3309b6d5b2110a73414c995aa350cfe90961842152694d60ae49890cbb3e9","run_fingerprint":"e1494bd3e9ab47acd11ed9d63a28c265fccc585c3ffc18e778d44ddf6975317c","score":0.012550529818184046,"score_display":"0.0126","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c77ffde998cae4f5dc55e016507ad16fc41cff23652ee9bb4c219afd306741fe","measurement_key":"8daf3aa4daa64ca8156722550d534093fc3eff92a52feb8e760c324e887ba2b3","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"1cbb8bb4cd74f49c4123cfbc12b00ffc2e700ade20fb3dd5246ebfec3a90716b","score":1475.289755722248,"score_display":"1475","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-14T05:10:27.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"750f872f72312e5ecacfd7b4fc8fda8e4a7420db333d7b7f99bbf33bea3c6e59","measurement_key":"bf742b5fee9866cbb568fbc20fbc325ad5cf126392e563ba3f1cf8acd5f666a4","metric":"mean_score","protocol_fingerprint":"bf68acd2d1d1dd5a3ab2ab019a17e25dc407ee5827526e24fdf2af98912663d4","run_fingerprint":"6130247474bf3d3f934e92ff3a522222df499ef0374947d417ed5ebb04745cc7","score":22.0,"score_display":"22.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"288743e29cea37a7fff38008aee987f8f817cbd4c09b158f976e3d523e50d283","measurement_key":"6d4a298aa9da18c8208aae694d73625f3ca8326441c4e3a48e1990f2f8953216","metric":"accuracy","protocol_fingerprint":"74f6788998c46fa98e6574d81e5167a10d43e1335629992c67c2f44169f45533","run_fingerprint":"3e614d8861fa56bbbf08bad4157f67b080177e8bcff97b91e3c0af57200339c6","score":20.8571428571429,"score_display":"20.9","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e07424058e54e99848dbd34aa3149708cc2ddec67c0f70687d75563f39da3deb","measurement_key":"6ce8bee2768d1563827afa082a5d8ec075eef3a8cc004600ca4a7d2157a73bfd","metric":"pass_at_1","protocol_fingerprint":"7c64f1205ab13b5ff20787d49fd0c8b5dda15db5f0285f7bad596dd073bcb96a","run_fingerprint":"53857893dabf0f8bdf12a0aa54e6e5ff0538ee519f53155c070c28c8759178e1","score":43.77777777777778,"score_display":"43.8","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"77f53344c4d90b211c70720515ab5c242347168f3192bf8a55b7752a8e5e589e","measurement_key":"e18c0dd7a21ef3caf1038ded87a536072e494de3e7553425788837ebdd780e5a","metric":"eci","protocol_fingerprint":"b3816f11696cb8e3e7ba878f4e89cf8ad004083419a05de1b3e82c71bc4f6ca4","run_fingerprint":"b41bebd01e6b698e663bc503a156a7095624bcb68e6c9e1096ee3dc35cb71ca8","score":152.07,"score_display":"152.07","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_04566da2338e5d8f2694eef1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f0d9d3c0b954e5e0e2706c5e9d94db8679127c3088856cc80f4d50c271b5c6cb","measurement_key":"edaf4dcab169a4eba6ad07b67cd5f31cea5a39d998477955718418a35623d5a3","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"6c9a24d40701bbc2cd3467fabf75eb78af4cf0a4f8ef7cbc7fd8ef9023d0dd90","run_fingerprint":"19856017c6b6ee034cc9ceb370eacbe0b6f1beb5acf09df81796b0d573cb514d","score":24.5,"score_display":"24.5","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_2dc4d509d97ba2d565e36ba8","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":134,"at":"2026-06-19T16:13:05.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ae26aef06935c7563507324dbdda6de55d9aea04a786378dc7743b72f2f837cd","measurement_key":"a39362a799dbfaadc97a9c749da6cbbecae0bf1f5f8740aa509b88235ab83046","metric":"mean_score","protocol_fingerprint":"2b719d2dc1d51447164fab6e154bf5117436d13b91c8542fa3543c966796cda1","run_fingerprint":"93941b7064c8d503bcb71ead41fc56f7881549c6e7664ad4ca16227b7f417121","score":59.205776173285194,"score_display":"59.2","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":134,"at":"2026-06-19T16:13:05.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c8d8a201c44659ecb20f465ff765b63f1d2c85ca22a15e6cb4e132abee97e363","measurement_key":"5785fd0ddaf12e296d5cafaf84c14e2d489f6c6e92345c9f1aa58a6649158694","metric":"mean_score","protocol_fingerprint":"908684107da51a0d817af2b4d3f9faf3d656f68c7600d9fae11ffff479060d82","run_fingerprint":"c5521725ac630b02cf3890dbd975f1585a8b2d6c8a4a2b808510b7324d969b33","score":29.268292682926827,"score_display":"29.3","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f62257abf07a529e0d4c4e150ce87f9eeadfbe3a4e5445714e5537e68f6b3a1f","measurement_key":"cb5bd60f9636342f4cb4c5f8a22e1744178e0d8611af7059dabf4d6cf80afd49","metric":"elo","protocol_fingerprint":"df51cae64d9007c26a3fb899335384920dc40dfed17fc094fc27bcd22f51de16","run_fingerprint":"89df3082d21e0769fa7016f31bb508ec0c5fa02e2f3f9550ac511be54e277a23","score":1381.49,"score_display":"1381","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"512ef10152bdb77490b44f0b5ab6581bdcefaaa401401f6f950c8ed9aee46efb","measurement_key":"48afc063ffe69e8f66a6186b84cea24a9be93de28f0ffa89e07ba60911773a70","metric":"accuracy","protocol_fingerprint":"e78e34ddf169b110243367a84e6552e35050e46eb492a50a41a03147cc0abba4","run_fingerprint":"e2ea70f54b451f5ee8b58304ae35efcc2c600f1f093df7b11725e8f998f40093","score":85.606,"score_display":"85.61","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_43b1a4c9d140c7bbdd7604dc","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_fa9e908ac04b067eb00182d4","benchmark_version":"HLE official leaderboard","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":63,"at":"2026-08-29T23:52:43Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f6dfb4107995dc93dc2f4d4b88fa14e3b55170809fe5be0345a9fc132ba4bcb1","measurement_key":"4e7ac0f840cf6076261c63fc046cbbc8f943991ba81c94af629c165bd4a4f04e","metric":"accuracy","protocol_fingerprint":"e1f956386a97e6ba42a3c396757902d19f19cdabb10fcc91e345af5c771a2890","run_fingerprint":"16f3e75e23e33f4fd48152976a0f47b27678bbab45c6786bd0495477854d8971","score":40.5,"score_display":"40.5","source":{"id":"hle","name":"Humanity's Last Exam","url":"https://huggingface.co/api/datasets/cais/hle/leaderboard?limit=200"},"source_authority_tier":"A","split_or_window":"published-leaderboard","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c54b095bc209fa08007ec46c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"C","evidence_rank":5,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"self-reported","verified_status":"self-reported"},"unit":"percent","verification_status":"self-reported"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"17a4f5e7d0a64b089983052d4d6df4e56cab1a65491d2d9d1db2d51f8ab702a5","measurement_key":"a9fb9fad4863f47c2ae5f0a300bff77f43dc94b1d918118e8b9d6b0fd42eee96","metric":"accuracy","protocol_fingerprint":"92ed48917c513acfb6e6762c693dc06dddf60cab9a314f607c515ab653f67106","run_fingerprint":"f3c57afdc7d1b2a7aacb0be4cf36e8d39f6caa48d960c2e42e64384a4b2c0845","score":41.149212,"score_display":"41.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"57b7e7b67593dd884f3cbcae7708305e3d7fdf3003ab58e1726b8f440f31dcab","measurement_key":"54a36b9806f2ffb67e795e07f072e4716d26a0f2585ecf91a112a4a6d602da05","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"25b911f9e4ec247bb1dc6b80dffbf69a02c3321a6f8295dbe1a46b4be380e87b","score":73.15728571428572,"score_display":"73.16","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_17119771e437727ff7cadce7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b06976552a60b413b091f62058113dbf796d71d5d24666585cb50b55aac32496","measurement_key":"214db4a5e0c92881259bd32ad3bd4b8bbbaf262a4130d6365a26bb1aec8093b4","metric":"pass_at_1","protocol_fingerprint":"6890c60f64018dba271634c7a4f7252db6a28528826624dcef0d31028896de19","run_fingerprint":"1f0b0ce1708028c09b05557f856b28d04f0e7fc4d447c8defaaa08d3782139bd","score":69.5,"score_display":"69.5","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7fa74e2701e012fb5d803f8c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":103,"at":"2026-07-20T17:09:57Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"06cfc3a5518b211e64dc56a9b44f52968c8ed96c37f7103173f538f9c7d1e295","measurement_key":"d8ab09ce3b15d6bea0e79d6e26be5cbb7c1d7b13f80b2f9662272897fa81d28a","metric":"pass_rate","protocol_fingerprint":"e1adb4d27b244ddd0f55076fb3ca29b12284f51c93fb098a7aa6390950ce1ec1","run_fingerprint":"c9d6a89d08832bba18866cc46d0a1f76fc80de3ab755565501d8c202c1a6c253","score":77.8,"score_display":"77.8","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_485b19c39bb21348a203eb53","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cd65da2c458fdd5736e069aa85775f87dd80430acb157df52fbd506231673d85","measurement_key":"ef5e768ff56d04a7f1bee3a7dae84ec7554468c0a06703fbc9b959aec0eebdb0","metric":"accuracy","protocol_fingerprint":"85d72554edfef33ae0f6c22cbb1638bc9e295243b01dbacc99a718cd0a9eda9a","run_fingerprint":"0b322b988f4e472d23d6eff59f145761c15e1b9ffdc646ffc092b06489a1ef8c","score":86.714,"score_display":"86.7","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_21a68f413995c1824054e5f0","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":129,"at":"2026-06-25T00:15:08.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f076089806a686e0695391ea6b2b5bd3c3920d9d4cb0fa0ecf4f75a18ae86602","measurement_key":"6db989c29c96d61c076bb124f0739c941fff5c70ae1731c1fb2f1f865d013cf7","metric":"mean_score","protocol_fingerprint":"15d072ac1920c685176ffc0de7e75f477ea07dbe82bf73801bbd24efbc815915","run_fingerprint":"dac846086da0be0a58d5ccd83d413edc80316873f309ba09363449126bc634d6","score":86.38888888888889,"score_display":"86.4","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d0111b10856c844d05dee5aba9a3990aa24d04f4fd4e308b7f01eeb0575f7bd2","measurement_key":"25c93d6b85cea4fceab7d22aaec1191c74529c0ee425751dfbd18a06da856e22","metric":"fully_resolved_rate","protocol_fingerprint":"0498d1d4ec0b44e63a1b799dd92f4609f582b4309c3b6d7f1e5b6b5c7b58a6ee","run_fingerprint":"9821a9721465c677c4b3a1dc214cd15b04397fdd2df91b4224105f8857567f23","score":0.5,"score_display":"0.5","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"48fad2d3268780bf5771aff570253e7996fe8d9203eb7f571d8336e25f61fa0f","measurement_key":"5a5db39a9d2bdba25e6b129730b4dccf992e3e06b2546cf14d5dc481487ea433","metric":"subproblem_accuracy","protocol_fingerprint":"9c5ff701c4d182724e8ff1d1149e16824f94497bc929364f5ab62d237a85eb48","run_fingerprint":"0b1ad08946d0ac857c8d2b8266ac045fd42ef5f139384aac7afb13159e169009","score":51.1574074074074,"score_display":"51.2","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6be0d535110e7a5f1317791dbe0a261d117b3786ca5f34c53c8bd3290207d0c1","measurement_key":"e79f94282ca2cc3ae2a083a49e271f607321b276dff80bfd44719b07fa6c28fc","metric":"accuracy_avg_at_5","protocol_fingerprint":"fbbd9e0d0e3dae62501f10feb8ae007290e95726caad1c8211fbd34936a787a9","run_fingerprint":"d15ac7579e3fc64ac60f8920505d3c68e744a2ee7b70a0d527d009228a83978d","score":58.8,"score_display":"58.8","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c362d9b546b44a292da204a3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:36:05.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"887f6314b80e68300f8881661cf8f4e9f21c73f35b156979376cf61d3604ba15","measurement_key":"c08ce7c3f36fc7ef30406ab898e76a5598d9a19060ad85c26ec261008958fda8","metric":"accuracy","protocol_fingerprint":"793a7e19bb4532d6fd827caa77a0e7c75b6fe3c7661e7cb6dc360e76b8ab1b4f","run_fingerprint":"0d63f637af49da91f99d4b7ff69dc59d1d360d7f00e77e6a4fc3ed8c474cbe45","score":34.2,"score_display":"34.2","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e78384cb1fe0872fbf52a8a87ec0bd472b094d2c30e72763ef2c25ab7565e503","measurement_key":"f073e3f90a9663b3bebcc098cfc30c666b7a76f4101851c8e80e94f6afe90315","metric":"fully_solved_rate","protocol_fingerprint":"d11c1b5a93479123d6856b3b4e086745ad082b0349b8837d9f2cc5091096620e","run_fingerprint":"5aa007d9a7efecb7c86a0201dc15602d19d6c1f6fe7613991ba91add218a9f0c","score":0.0,"score_display":"0.0","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":137,"at":"2026-06-17","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"699181b7257503d107bd7b262a960640ea5634bcc4d75e7bad0b275d4cac1082","measurement_key":"a653473b95a86db684ce5e5692681c6c76a762fc5c53b84df22ff9ec490bf4dc","metric":"resolved_rate","protocol_fingerprint":"bf256637ab7c031c6ce221713d534fdbcab5facf122e6dc16b3a624a75293036","run_fingerprint":"4ed0b4565f976acf81eb06526c3c209db17bdc0ee0bbb2aef560e013e565fd8f","score":82.8,"score_display":"82.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":137,"at":"2026-06-17","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"699181b7257503d107bd7b262a960640ea5634bcc4d75e7bad0b275d4cac1082","measurement_key":"a653473b95a86db684ce5e5692681c6c76a762fc5c53b84df22ff9ec490bf4dc","metric":"resolved_rate","protocol_fingerprint":"bf256637ab7c031c6ce221713d534fdbcab5facf122e6dc16b3a624a75293036","reporting_origin":"organizer","run_fingerprint":"4ed0b4565f976acf81eb06526c3c209db17bdc0ee0bbb2aef560e013e565fd8f","score":82.8,"score_display":"82.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"contamination-risk","conflict":null,"directly_comparable":true,"display_role":"contamination-warning","evidence_grade":"C","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a0a57cf3d28bcd91bd306d1abf514f7107f0486cd56a6c7d30c085709d1eb8b3","measurement_key":"64e013a6e607e51876b017d4716c30a6be97530091d8dfa572b25080c4836feb","metric":"resolved_rate","protocol_fingerprint":"ef3c892e6111a7703e93a922e80e35358681f631e166e5fcacaba61b8a3f3d38","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-05-15/2026-07-01":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"contamination-risk","conflict":null,"directly_comparable":true,"display_role":"contamination-warning","evidence_grade":"C","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a0a57cf3d28bcd91bd306d1abf514f7107f0486cd56a6c7d30c085709d1eb8b3","measurement_key":"64e013a6e607e51876b017d4716c30a6be97530091d8dfa572b25080c4836feb","metric":"resolved_rate","protocol_fingerprint":"ef3c892e6111a7703e93a922e80e35358681f631e166e5fcacaba61b8a3f3d38","run_fingerprint":"2c185be4b4fa421c03cd92083933a8ef1b134e9238eac4d25873241b33bf5bdf","score":62.88288288288288,"score_display":"62.88","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_0a11b05baf509af0577d53c4","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"},"2026-06-01/2026-07-01":{"benchmark_release_id":"release_8d9de222c7fa49c448653fc0","benchmark_version":"rolling-v2","comparison_lane":"supplemental-post-release-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ea033704eceb2357e6eee97c93f2177216325f4cf5d9989d85b1543595587994","measurement_key":"e830d107cd69bea6276fff51848c909b1f1f345882ce91ba5cc5fe71e5811fef","metric":"resolved_rate","protocol_fingerprint":"1fb1e70500a875cd246d716d74f2891f497e4167a1987d26e3411328082014a9","run_fingerprint":"e9475e09a9470f0249bd043d3a1d412887eae00a2476e20d4bf5bb011bb4087f","score":58.0952380952381,"score_display":"58.10","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-06-01/2026-07-01","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_0a11b05baf509af0577d53c4","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"2c185be4b4fa421c03cd92083933a8ef1b134e9238eac4d25873241b33bf5bdf","score":62.88288288288288,"score_display":"62.88","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_0a11b05baf509af0577d53c4","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":100,"at":"2026-07-24","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e76aad992786b59da7894b4ff8e53b9c3f1a3ae58a28ec354f91d05480729a79","measurement_key":"faba3959d19eebfc70e6046caeb85c2a0ea572fc8166b46239e22ba96fd04d01","metric":"pass_1","protocol_fingerprint":"8ae31a68885f85099acfd11744c8b6482786a6c228b5cf38146830c9fac67e2e","run_fingerprint":"96141a69e70b1b53b101757f601cada71ad6f50f91c8fed6ccca7f4a9ab9954b","score":37.11340206185567,"score_display":"37.1","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_731f1098dce287a031491f2b","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"78b2c48aba9e1db877bac7109448c24136061c70c6648434338ea976696da8e2","measurement_key":"0741784b48c425a27824630af2d7fbe53f265ae28c30826747e00089b06bc330","metric":"pass_at_1","protocol_fingerprint":"4c59c099162c4a01f2649c2a1a8acc544f302d9a3204752aadb34fb996add352","run_fingerprint":"945012d71431e412d45ec6b0a12aa17eb6e71c3e02b18d5f4834f1ef403b6a3e","score":34.639175,"score_display":"34.6","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":137,"at":"2026-06-17","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5df6aba2d10250fb2d0ce62f2506a50d70335f9b33685e7e4143421d59b56610","measurement_key":"5f08b737c93bf97a32ec825f21dac54b5ac1073ccd9940216c180faef8b12a4a","metric":"accuracy","protocol_fingerprint":"9aa3cc7610c1afcb4b30fa74e682ff351eebe92aeb2dc21c15821014d832ba19","run_fingerprint":"3152fc91790200d542342d18ebee111beb6f1002beea5f91e83f4b4ae7754d9f","score":67.79,"score_display":"67.8","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-3":{"benchmark_release_id":"release_ceb36f25882d8cea2c9d084a","benchmark_version":"3.0 · b936386b-4afd-4ad7-aa7f-6b52bcab9853","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":80,"at":"2026-08-12T21:39:34.661007+00:00","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f25aef2b4ae365ee4e57dc7b13e846600b54cab946f4165a35d2b864a2b8e986","measurement_key":"60b034bf11177a12a8f829d3cdbf406f0e1820e95d15084a0b39029b00dbdb48","metric":"accuracy","protocol_fingerprint":"8193d21ad0eb789a1ec26ea50fbd3379bed4aad4e8b492bd1b886fd1b07a3897","run_fingerprint":"6d26e312adf3154eae3de6b419df7d390cc6f7fa31e2c86f95cfac4740fa7613","score":4.59,"score_display":"4.59","source":{"id":"terminal-bench-3","name":"Terminal-Bench 3.0","url":"https://ofhuhcpkvzjlejydnvyd.supabase.co/functions/v1/leaderboard-read"},"source_authority_tier":"A+","split_or_window":"official-74-task-leaderboard","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"50b351c689b98ae27e7211c8bde7b868fe55135ff00328fa80c87ec7db221f05","measurement_key":"c50f2c31fa318d9a78a2e3fb2dabce9030790cf70215874d2fc64dbe92a26a88","metric":"mean_final_balance_usd","protocol_fingerprint":"30bb57dda941478e098ec5e225aa9517aeeff59a03ace8296132a1a40706b998","run_fingerprint":"013cea20f1a660a1a55f9d59c72300b49efced23146fbc93e315a10abec58592","score":8313.778333333335,"score_display":"8313.78","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_20ab07deb4f86981c9497a7c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":137,"at":"2026-06-17","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5ef4abb4c5405144cf77aa59c296ad23ba4676245bc49881748c83379be92234","measurement_key":"b8910db288e9bc0e07af6e6e58d786db2c57107169cac9278dce75f6407158cd","metric":"score","protocol_fingerprint":"90d16c84acfc61cfe588d342864108a487f6d96c8dc17c2e54d0aee03aa20b62","run_fingerprint":"777284d28cd2eeeeaf88b0546a38c17f9a57a63526e75154c460b30ebb7ad1cc","score":63.961,"score_display":"64.0","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b67ec8809db01575f08d5ddacefb2152394deba470936bbfaeece1fe547c4c52","measurement_key":"7442cda2438ba890150238063ec2f03aa4d41addaaedc3857df550c8e6ae512b","metric":"arena_score","protocol_fingerprint":"554ee0b55045d03ae4f0841b21ce34e16bec34e23700bc5e40b71d2decede08e","run_fingerprint":"466ae71b334ded0e94eb668f5e836c63ac20ffc308c7ce6908206b9d060a4677","score":1605.639209438289,"score_display":"1606","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"224309fa504415cab2525617b28001cdef1acf4c105677cb084d878e6c23cf50","measurement_key":"9d2c038dc74d04ce99d0e33cca7641cfa2f92c156c7c48c669d4bbe15930670d","metric":"accuracy","protocol_fingerprint":"8c398aaaeb7298f9c247a193edd1cb9b66a708611a8f3497fa2c2efe0634120c","run_fingerprint":"9dd1f5060edd4a97413e923f608fe28f59cbc22e16c41723e3f625c7cbef321e","score":70.12,"score_display":"70.1","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a6e3ca6e600d7d7ad3656281","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"zai/glm-5-2","model_name":"GLM 5.2","parameter_count_active":40000000000,"parameter_count_total":744000000000,"provider":"Z.ai","selection_rank":53,"weights_status":"open"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0b5224b2da2aa5baab1bfe106126ab300a363e7f0e7bb58dae8cc80c814d9f70","measurement_key":"adf21331d7c3ad7857b305566cd3d179f85351dbcc96b5ef213689b638c5c7ca","metric":"performance_rating","protocol_fingerprint":"3b90e109f668919c06399d02a95b3e09bad004e7366346c6cc39d5c44dc328a8","run_fingerprint":"253ef954cdd6438bf3af944b6feb56bb200430e8f9b2be780571712893d32976","score":1367.2,"score_display":"1367.20","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_385ff75e5783055d4ca2f505","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"88a2cf2fc17bb2636acda8e51cbcebf3d1074fd32c94344aa6c91536946cbb01","measurement_key":"5e78101fe82acddfc99fd2dd71d7f0990802785f4f77022f520f2ab35557cfc5","metric":"pass_at_2_accuracy","protocol_fingerprint":"c5ce19de294519af53926129ed4992f7ed8e37de295da6aa5c8ca2f057ba9cb9","run_fingerprint":"c38458179c8a70105aeaed946bac67e97018a9e3854846eb61d685ad972ac19e","score":84.67,"score_display":"84.7","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_385ff75e5783055d4ca2f505","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7a0b468673edf91acf510b8af10039e5a1b59b266e97b13d1a3fcb7ec581a25c","measurement_key":"e33dc3aaf6047e25d087a2f3e73546148d31171a4db78b67b9278fb8224c4be0","metric":"accuracy","protocol_fingerprint":"f8312f452c1590fb2d8d5d0058ebce8a3f1cfed597e44f9ed6968b16bd4b9dfa","run_fingerprint":"4ea646b0e9cc3dec38df6b3e8487ad885ce2f864af5f85e3173d16d5f2f24eae","score":33.61,"score_display":"34","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_385ff75e5783055d4ca2f505","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2df345827c77214c2ca7237a728413b4b5a2d0ba060c935df985c184954ccf94","measurement_key":"89e5d9c446ac2da2711a8408bfdd6dbdf67f2ecf9d10a0e1ca954fda6ccf686b","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"d5bd0306f3d39c23745a76e621b4e98e3f0e7664a8a45b30c78032f23f1e0966","score":1458.367316107511,"score_display":"1458","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"minimal","profile_id":"profile_57d19654e2ae916ecd0b5c09","raw_label":"minimal","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:42:10.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a90f7327b5e321cb56f848e0c34af1b14316e5d90f3e2bfa46061603478f6f68","measurement_key":"8369335f0e0fb4c210450d56edcaa3221e6215bd14136ddd96701eb27062707f","metric":"mean_score","protocol_fingerprint":"11a80a7acb36a3b00a89f6270c751bd02267a824b332a75adfe71aea5d5102e3","run_fingerprint":"dcfbadf0ca69e0c505bc7f2c5327a0614a158319b53ae1c7d1aa44e15df8e437","score":39.0,"score_display":"39.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_385ff75e5783055d4ca2f505","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"beb3b847649045a74a0be47a20f04d8bc0397e6c27d9769ccbc3756cb324a180","measurement_key":"caa13859610144fbbda3adddef3a6868768f05613d8f550cc6a1ec17365dd753","metric":"eci","protocol_fingerprint":"d36ebd95915c2a8ad6edce1dced434dd6e2ebde185c64651559ebe84632f0954","run_fingerprint":"9108aba44181b3b11054ca04f968d816caf5f20de5802b5c56e8e524f5713d86","score":152.01,"score_display":"152.01","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9ffb97cc9acccbbc83ffb92e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":142,"at":"2026-06-11T23:44:30.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"483152cac0547daa61a2855db08a442f3d6a2d1fbd36a2190b92456148d9dacd","measurement_key":"b4d85f57e562aee15ac9141b0fdaaf3378b0e96d21e9f2fee24d9f6b8ea0ccfd","metric":"mean_score","protocol_fingerprint":"96cd26da29a9ae656aab7d662b37cde34e048e9768f2ea03150eb5a79fcd803a","run_fingerprint":"69c127ea24cb5dce5fdd4d85924891031f8e6bbb80472b57a123c9c1c12c2bda","score":51.2280701754386,"score_display":"51.2","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0ba24c793659a66d8cbdc90d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":142,"at":"2026-06-11T23:44:30.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6cdd70fb231105a87661ac862b6485bbd3c03a3081d751e4deab4d1a705b9220","measurement_key":"a7e0c593b2e423677a9b9615725e658f17f47d56b9fb0076e1329fcb54244a28","metric":"mean_score","protocol_fingerprint":"0ff253f7b5fd2063e6cb521ab31fc665724c492b9c6f1484984fbe7bddeef367","run_fingerprint":"a30f13062dc47c611faf924eb2176b1335d1a7e6f83791331764d89a025f4608","score":17.073170731707318,"score_display":"17.1","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_92976465691e2c940c861d92","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"542df8aaf17127c731fdbaf75b457530c404cfb66728bb5a62f2b21fe14a7568","measurement_key":"212e178dbfc1f54363bc82f6d53bf615eaeba01d7aeffe5ffe9dc4fd8deb0bf6","metric":"accuracy","protocol_fingerprint":"737c99f1149726c71406ee9ccd875de1bbb060addb1bf113a504ba2a11f16b99","run_fingerprint":"3e7e850d5233073abd7bcb706d6b2f3fc8aac4a16b1653a580e0200b09582e39","score":87.879,"score_display":"87.88","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_385ff75e5783055d4ca2f505","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gso":{"benchmark_release_id":"release_176f07ea4e9e0b8dfeede990","benchmark_version":"GSO current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":317,"at":"2025-12-19","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"1ce28c8c910ab4e3b3192ac1400da75d3c7308a663e8c44363798b1c44f583d0","measurement_key":"214a6f10eeb681c56c781ab357db395b57ea1665e2f4ac3c45e7fa807f94eab5","metric":"opt_at_1","protocol_fingerprint":"c20751fb7a44d040c598104ce00cc785040a219233ed3f47b0b005fc63dff5d0","run_fingerprint":"7cb57f5613fc098aef1190cbca4e117c8cc54f0dd5e8498aefda0b8ac47d2849","score":9.8,"score_display":"9.8","source":{"id":"epoch-gso","name":"Epoch AI mirror · GSO","url":"https://epoch.ai/benchmarks/gso"},"source_authority_tier":"B","split_or_window":"official-set-opt-at-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_525bef63a282c86f51e299ca","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"hle":{"benchmark_release_id":"release_5f3023448c2ae4632fe1a43b","benchmark_version":"reported-runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":319,"at":"2025-12-17","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"1328f88b0775ea781b01ca80ddfee244a6e2e349952204872c2029a0deb25c06","measurement_key":"4c8fc7cffb3f8c35d1496cec111cbe879a1b05bdc2d711e8333eca74eb4dc811","metric":"accuracy","protocol_fingerprint":"26c8fd00871cbe3c4d547eae32d78e6ffec3b09798c45289975fdd0b75864645","run_fingerprint":"3363893cf9e742cee93dda00777449346362ce7e2e56df2d111008ceacb3734e","score":36.6,"score_display":"36.6","source":{"id":"evals-report-hle","name":"evals.report · Humanity's Last Exam","url":"https://evals.report/benchmarks/humanitys-last-exam?tab=scores"},"source_authority_tier":"B","split_or_window":"public-multimodal-mixed-run-configs","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a37ea0078b8bcb4cc5bfbaf0","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"evals-report-official","verified_status":"evals-report-official"},"unit":"percent","verification_status":"evals-report-official"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7fad1e2c98d50b21ae1c22c9d0c3c5865bb5197e23ee3460dd8a6a2c02c0bbb8","measurement_key":"061123d625f66bbe9b9cae51bd9a35812b8ab40dbc38e86c1e324e86e991fa38","metric":"pass_at_1","protocol_fingerprint":"36fedcc4dd8a8e2034baa70273cdcb97304308390dbb24653a1553ce66b20a20","run_fingerprint":"0ced2e793ef9f91674865df20e70511112ff9c7805ae9d4a9ab053355330e5c9","score":85.591,"score_display":"85.6","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_385ff75e5783055d4ca2f505","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"add417da102d1dbc28e763805e89bf632907796249fed14501eeb81f2710a86f","measurement_key":"83a0437b7282f76a5e1b80a68009658f3edd86d6b878439aa150649888dd3f39","metric":"accuracy","protocol_fingerprint":"740646b0391029bbbb479a7d17da7b6e53ff9aadf90a736b49f3a4ade9288e0c","run_fingerprint":"c902955d5440e81f1c1bfbb1a32ec5a21df091f29afd05a16b46c1a8203d675a","score":88.592,"score_display":"88.6","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_385ff75e5783055d4ca2f505","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8973f1017aacb97397d8a74b475a4b20abd1f478508ebdd1bd254e4d7d78383f","measurement_key":"cc5de4d1def312c80564648f77b0d54125e1ab2738445b42b13847cb1c65bbcc","metric":"accuracy","protocol_fingerprint":"7882730b62ce67227923945d91d9b57b6413cc45e1dea45311898ada3ca0eb8d","run_fingerprint":"136b6516992aacf16747db97ae2eeede950f8a806a50f3062199ceecb19bba9f","score":87.63,"score_display":"87.6","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_385ff75e5783055d4ca2f505","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-06T22:25:57.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a5b7732bb496ddf59399e195f4c1863d8f784f3fe9f07138289ac3d3cdfedb12","measurement_key":"34ad57e95434703e90f7023b14f711ecd4b033188cd17df720b0765dcd8a3131","metric":"mean_score","protocol_fingerprint":"ee7434d0c3b0d41a21b877f0967b93eddf632c1e85f5c451cedbf79f383c609d","run_fingerprint":"2a2715bbd4b363851334448e5d992f78eeef6af4e567ad709ba412952c77067c","score":95.55555555555556,"score_display":"95.6","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_385ff75e5783055d4ca2f505","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"afa809aaeabb0144cfa90a73c7ecaa2e514d37384084730df438c54245cd8b63","measurement_key":"5bea18e33035268063ff5aac874ac317370902336c4dd3276106dc445d529692","metric":"fully_resolved_rate","protocol_fingerprint":"7cb216d52eb88a3debefb4d02a2f246dae971db4823c6e0528bc1843f043ae35","run_fingerprint":"7c74cde97fad43c22428930339c711ad9e7bf1c1968ee48618aae907a8baa8a2","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_385ff75e5783055d4ca2f505","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"69b87bffea7346d93188749ce43bb8c7c1ad8190236c9cdbdf5be8726f5e4e2a","measurement_key":"9334df40ffe3e7543d9ce34b5e5499f0dfc3298e4f3901c2990b43533ab90361","metric":"accuracy_avg_at_5","protocol_fingerprint":"3314247dc49fdff2278501e4ff87391a4638f65db8f3227c6256e5e39a236aae","run_fingerprint":"bed09e5286fc298fda73e7e601c2adf807f6b7f66363f888b0a8e9932f0e8430","score":61.1,"score_display":"61.1","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d6963c4fa76fa587ee8fc818","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:30:06.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"03c5a256a2f869328d699943e908205834fed8b55194dd209c8eea65fad033f1","measurement_key":"eae5b9d7dab00749cf803f47856abc7ca3b5c92f6d630c6b9e5f287d0bdb9d59","metric":"accuracy","protocol_fingerprint":"05f29e9b0116a60ecf7ad7e2990a0fdde7e3db4fd096daa36075437027847a71","run_fingerprint":"bb93b3e4e4fc7f673cd6ca989d7cb87fb34ad21964a264f02dbe67e769f5200e","score":66.8,"score_display":"66.8","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_385ff75e5783055d4ca2f505","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"skillsbench":{"benchmark_release_id":"release_093b45b8b752b3f08534f6ee","benchmark_version":"v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":138,"at":"2026-06-16","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e1f9e64009a75c086993ae358540a7901f1e156b108aa23731e624e6f7d05d71","measurement_key":"a8b13ae7e006945aec3a751af63b87cd40ae005a54351dd2e2802c860bd22a12","metric":"pass_rate","protocol_fingerprint":"b364c19f09c3235a2849dcf46f5f7497a801c57e4a3db1ecf5efd428de0c8418","run_fingerprint":"f1096254a2e3b14483283fe2787066724e728caa86ac256ba3707c65b05d0b73","score":54.6068,"score_display":"54.6","source":{"id":"skillsbench","name":"SkillsBench v1.1","url":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json"},"source_authority_tier":"A","split_or_window":"official-87-tasks-with-skills","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_24a77b9d93725e789667e3fd","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"27fbf1c8baec83d373c0ce0f3d12091022506a5b004f627bc5dbe5c1081e7053","measurement_key":"319b87a54606fd3c54af9f7b2f741a14ceca075d0a6e3b4f65f3ad0b52e0ec9c","metric":"resolved_rate","protocol_fingerprint":"33ac1d31a772d74c58b6e9ad2d6f823170018890c79c206152a471b6b184a331","run_fingerprint":"e36d5439ec9c4cb9dd250b28ff12b712449341ff7d054d40460ddebe770ce154","score":75.0,"score_display":"75.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_385ff75e5783055d4ca2f505","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"27fbf1c8baec83d373c0ce0f3d12091022506a5b004f627bc5dbe5c1081e7053","measurement_key":"319b87a54606fd3c54af9f7b2f741a14ceca075d0a6e3b4f65f3ad0b52e0ec9c","metric":"resolved_rate","protocol_fingerprint":"33ac1d31a772d74c58b6e9ad2d6f823170018890c79c206152a471b6b184a331","reporting_origin":"organizer","run_fingerprint":"e36d5439ec9c4cb9dd250b28ff12b712449341ff7d054d40460ddebe770ce154","score":75.0,"score_display":"75.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_385ff75e5783055d4ca2f505","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_b31e2006211423b08d16b59d","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":245,"at":"2026-03-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"ffe691496fde7034c7b5b18ba3e6a219fcbc81444b4106d2378c9f613dcc8ecb","measurement_key":"0e46fc4e89bd391ffd2a67d6d12fa190699dba27b2a647a99507dd8b4bead3c3","metric":"resolved_rate","protocol_fingerprint":"41b89107cff12d693d8637505f026e8beeab77a4802fcd952a837ac613bbdda4","run_fingerprint":"f995ba60151bf9bbe00b9e42b17e2ca9dcf14edad9220040f25a4868f5e9f279","score":49.81135531135531,"score_display":"49.81","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-01-01/2026-03-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e83e7303a3376faa702de988","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":244,"at":"2026-03-02","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"124c9e2cbe5409801996892616788d6ea62df535c3204a655de06ae9c5cffb70","measurement_key":"588b876e877f8f3e82b80daa67db71241791f0714df899e20dedc6690a2114c2","metric":"pass_1","protocol_fingerprint":"65cc8cfab0984dda436d298ef1a18fd2db48c8b2d5c686cddf0f37bf4300de51","run_fingerprint":"bef732cb790fc79463fdc4cb595b6d1e7175d4be85575ae76f93522c8329f6f5","score":27.32,"score_display":"27.3","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_385ff75e5783055d4ca2f505","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5bd622d09a0718853182f539798270083fa665e45595fdf8c4a05c4e482600a6","measurement_key":"2bd26605e16e723220ee20e5cf90c51439d62826625b27cb4f59d85f8c47b173","metric":"accuracy","protocol_fingerprint":"def158633bb02d1fcbf46ae225455ec309684f39357003ed5d57fe3abafa472f","run_fingerprint":"62ed62cb3c934097e16af4749897f65f04753b0298b40cec891bc5b310ec2caa","score":53.933,"score_display":"53.9","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_385ff75e5783055d4ca2f505","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b8945a0fd64232dc7996a42fac2a2316aff85b513899c1254c872a44922f18e3","measurement_key":"cb36e602585482d0757d14a77e3356a05ff153d8b9003ab36d20865be8b56c9d","metric":"mean_final_balance_usd","protocol_fingerprint":"b62090d365143d132738ff4217234b598cb3a10704b5d2fbccbb260b57b3516b","run_fingerprint":"ebe63c4454fd54da024d361b056c383dc23a6d320d89e1019e187cbe11f31088","score":3634.715999999999,"score_display":"3634.72","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_bc2d3b57176164ba1eac2f22","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1bdc159788a93f42126e872023031baca4f279afc0a6945c2e40bb2c2249f846","measurement_key":"83a3e312058b69e3988aa1a644be49981c4b6b3629e323458a7bd8bcb35a303a","metric":"score","protocol_fingerprint":"96778b7801a377a5e232baa65e0b0884c17061f9bdc0b804c4b364e17647d406","run_fingerprint":"9b16e0ab06e83c6b03116c8cb83baa875635776bb332d69ba4969d447bb409a8","score":20.204,"score_display":"20.2","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_385ff75e5783055d4ca2f505","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a15b359f28b37b893d8c5cc81afdfad8d66b5ffb9ebf0161a3f506dbabc58db6","measurement_key":"1ecf8a2e0e7f5a10df99c16aed50e01fde7a4774e433548430aa74a9145a0179","metric":"arena_score","protocol_fingerprint":"e4789560e0f2725c957333104d2d603507fbc04e3b8942226a4185824881a7ff","run_fingerprint":"075ba180e933d115d65a9e5581714e323426185c6ab40f754fa258928dd89c76","score":1384.4938378264999,"score_display":"1384","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"minimal","profile_id":"profile_57d19654e2ae916ecd0b5c09","raw_label":"minimal","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f580756accaa82461b980c8acb1d9b1fc4b4f557ea2e1613604683758d62aca6","measurement_key":"d443b7b87a0fdf783602c82a0c6fc99ea84f1e584011bc763d56281d17636797","metric":"accuracy","protocol_fingerprint":"c01698a40f8b0cbf99e6adf29d614a2f39760fcf6be2ba1feb28f0cfd3503b90","run_fingerprint":"9e5a8d9462a3c451cf3260c731111b922aa01bcde26918731554589738aabdec","score":61.6,"score_display":"61.6","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7572b28212257731460cd760","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"google/gemini-3-flash","model_name":"Gemini 3 Flash","parameter_count_active":null,"parameter_count_total":null,"provider":"Google","selection_rank":54,"weights_status":"closed"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bbffe5fd00bba0e480fa0e4b38eb5db3fdff35048142ca4093cd72813b55d25f","measurement_key":"43078c79a840a480169a7feeba3e7638ee7800d6d295f94ca70aed119490d149","metric":"index_score","protocol_fingerprint":"e5ff73a88b689a809909cb15a8327c9d57ff18fa7acffb20a1f9e9ec7c674b3e","run_fingerprint":"bf78e68170288cee66caec6c4cf92404bcf7a81fd62806af15212f1fd86cee82","score":20.106876,"score_display":"20.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:12Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7221f9b7fe3c73a197cc12437c05926f60da2c629cbf96c90f6cfcf85f579812","measurement_key":"5646a6bb2549ce83ec7525504318d57823c9458857a3ebdbab6ee4da1efc4aff","metric":"pass_at_1","protocol_fingerprint":"8e74ff2f86dd73b1aac7df55aec635a29e92bfdac1841491c002b06a0589b170","run_fingerprint":"1111d5bd36be5a4387f076174b673c330fcb912b809978d54bf25517286f50b9","score":47.5,"score_display":"47.5","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_bc57e8524f9d921805459b5e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:14Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fc66952f5de68732185970ad1fc735883f4df60d1898f4e67f6cf82e1fb2ae3a","measurement_key":"002b0ee69c24d63fd376f53bfa14eecec3bcaa36a68a6b343c8cfa5c3971c35d","metric":"pass_at_2_accuracy","protocol_fingerprint":"44ae69528a2232914d2fde6f474b0aebe672c3d23dbf8f660231e00d4aebaa13","run_fingerprint":"66ac94c0af5ae5438b8bf3438e0edd3df5c9e47c22ba4c3cab5aacd618a096ad","score":87.5,"score_display":"87.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":30,"at":"2026-10-01T20:29:26Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6ae153f9f44807c7838b68a834c80a76e0675a427594000f1481cdb8c16ceb96","measurement_key":"1a06f12fe0864c7941e70de1016feef8c76937d66edb992d65d804c075e606b4","metric":"accuracy","protocol_fingerprint":"3a51d79cb6ec2f0dad6101a036a1aa9a9031c99698e9e69ec67d4b2b40a089b3","run_fingerprint":"550348c0f3814e6f9765f6e21dcb377d1e212053a3c218b63c29a273eb846d0f","score":42.36111111111111,"score_display":"42","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"66baf338bc9c7e033d8628964c290251e878c7016a8d879349168cdaa3923322","measurement_key":"00588d292a2b2bd54596a889c64d702084fb7d20e0372f430b5d261a81077a77","metric":"ips_score","protocol_fingerprint":"5b76e190acde094a3c38a328485bd4d2507b444537856511b98c48136301344f","run_fingerprint":"93357dff5bf2b0b058869d352f3b2b884e88e2f2ebe65a0ac648085d37854b0a","score":-0.04459740534602481,"score_display":"-0.0446","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8d97cd82dc667edb7aa71a27","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e1f9067ebf77758ca348f5307ea3babdce35a306167acff1f690ef5597c8e859","measurement_key":"2281892d87ec5e5e7836724a0bfbbccfe17a29d2cf1646d00ea6588b9d9671b3","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"e17018a162bce7cfe550e1345dddcc12f616681d854fbe41e0df6627616769cc","score":1435.5994372146474,"score_display":"1436","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c384460647f97ae85afeb51c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"13f22cfb731021fea43aab01105acd8b50ff04275de8af8fcdca53591bcd5a34","measurement_key":"e38da51e8b304941e796be36db4d8208b3f6e640236d011585b39dbbbd2deacd","metric":"accuracy","protocol_fingerprint":"21fffb98ea7e780900cb75cf671674542ee9dd3fdfe75569f984945bea08fc71","run_fingerprint":"8cb88e9cb559d8bee2b18e864f566c75e2ef8e23a9cc4dfa4904c01d996ce0e2","score":5.42857142857143,"score_display":"5.4","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_12e8a62d68d933c29dcdf020","benchmark_version":"DeepSWE 1.1 vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":79,"at":"2026-08-14","last_confirmed_at":"2026-11-01T03:42:36Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"270fce12814894194fea42642329aba5171abf32533cd921bf9726121fa26c04","measurement_key":"e40c0d46d0060b4707451bc71f5069abe737fb5e7137af8536a9bff21aa1fb7e","metric":"resolved_rate","protocol_fingerprint":"54122d35ffdbd0fd3eb0527b7ca43a75f3d8c6d231a28990b2a760d842259ee4","run_fingerprint":"f4cd227ec382a01c5f7fd9b5b3525235783e443217ac6dabfaca7071d9084d66","score":42.2,"score_display":"42.2","source":{"id":"qwen3-8-27b-card","name":"Qwen3.8-27B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.8-27B"},"source_authority_tier":"B","split_or_window":"vendor-model-card-run","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f97c4e36649aacbbeb6c72f4","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e217a410cfa92fe7f76c5be5ee64be192a3825593832ed0c0922cab0bd949fb6","measurement_key":"10ca3bc693ace72c4c861180d406aef312d530b22fbf2944efb4cdd8e77fb8c2","metric":"eci","protocol_fingerprint":"a2b66585d4fb313c0a42f3df71cdb16702007590c303c6b03b21c953655145d9","run_fingerprint":"db699378a9a72ff9c1b9c9c879d2d02df8d33db870b8129fad52970b769335a7","score":151.8,"score_display":"151.80","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e182cbfed410a4de7a2d42dc","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"941544562df39f15f0557103341b1f148c35113f59c47863b5b20df5354eec6a","measurement_key":"029b23b9c15b05c1628855a1e24bc60bf30cdbd71f59742e2ee103b759029ac2","metric":"elo","protocol_fingerprint":"7ce1a8177eeb6e001dd24b30122741e3332afd755f792975fe1307ceacfbb34b","run_fingerprint":"a55635d6b0c827b4dbfdf4d1862ad1aeaee5c84ddcf6ab3373274618be729def","score":1426.73,"score_display":"1427","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a12a5689fbeec4dfc278bd48eeb83fc0493adba56ec03d5374435feb0d8e989b","measurement_key":"2f8f9e42d476956869a1039ca62dd165c5b8b588599eb568baced7fd0e1aa137","metric":"accuracy","protocol_fingerprint":"7d010d340bdba9bbef6871bd34f0dc3c1070a1804b1fbe100135eb17f6597a32","run_fingerprint":"abbd50e9a8b769ef951f75782dbfd8ab5d234d2b5beb5da94438565b82e50f36","score":88.889,"score_display":"88.89","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_287aa4bcb31b5b1ba26e562a","benchmark_version":"HLE · Qwen vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":79,"at":"2026-08-14","last_confirmed_at":"2026-11-01T03:42:36Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"72d839b6fa6a023ae351cb1baf4c4f51eacaddca4530e13b72c87e577729ad9e","measurement_key":"7e4792d774fbf4574820f60d889796d3826536dddf369e2125bcd16d8d7a85e1","metric":"accuracy","protocol_fingerprint":"c93a278e8ec3e88d3cf8590bc92e78109edbf3fa8907cc99906d802003896656","run_fingerprint":"382269a32ca84b946eb107db590b7b7c69df58670099d25d7d45c8bdf4a6fc21","score":30.8,"score_display":"30.8","source":{"id":"qwen3-8-27b-card","name":"Qwen3.8-27B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.8-27B"},"source_authority_tier":"B","split_or_window":"vendor-card-protocol-undisclosed","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f97c4e36649aacbbeb6c72f4","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5a9b232404a29412abfe265903fd8d2f948f747546ecf3eb2796c7fc2405b6a6","measurement_key":"10f2ad4bc7cff4cb9f54036daf6f6bd330c48462878ca6b351744e6aedaceaf8","metric":"accuracy","protocol_fingerprint":"9a73eba5f5692f957518717c74be4084fd8f4cf2bc7fcdaebba1a1bfd2c89625","run_fingerprint":"2fcb980ed31968835d39347a41d180077ceb43d9e77d08b793651995b379c3f9","score":33.920297,"score_display":"33.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fb1fd001743b5fb96397d2a9dd9b4f4dceadcb47f6b27ca0bd01e7b8f745cc6c","measurement_key":"e75c7e12878a5c47b85e32fe5e3e92550cc3188dde8d6a573d502c94fd483e4d","metric":"score","protocol_fingerprint":"ea360a73584f5f4a5b246ef6a7c00a9f4e4f74494a27db9d0261034e8d932adc","run_fingerprint":"5009aed8d0d2f38516102be5f589889eae77c8f4d71c48be75c0193d8547cddb","score":39.056,"score_display":"39.1","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c56677c8e3dde196226e7093139304d601864863bdab0dbf6703e4d4a3178b55","measurement_key":"c1655c3cc8a90be278e980e9aea8f0950b64c4f0eedd979461c61e933a0ffedd","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"42801f4217e7367fd6b36a9567f94cc358af5da961ef7f2875886dc8972476f8","score":75.26910714285714,"score_display":"75.27","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_da362f90a33ff4c7924ed94b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5202fd97b2169587ff1500d23bb14ef7bc92f78e4dec438d3b0f74d9678c910e","measurement_key":"25e9b1f382e8b06ba6527b614e0dddc1013f35e9910a6ba821b9082e6c4c2681","metric":"pass_at_1","protocol_fingerprint":"a2cb431b496c9aa1a029eeb370c180e487b7c8d28a7a912a0e1139865d25f7ff","run_fingerprint":"b8712f53448cfe12f112721318cc1c26fcfe7020ce9a8bc8c0f9864b55fbc6c3","score":83.996,"score_display":"84.0","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"344746e8221bd455f62b8d9bc9cec8a1dce2a761bd59221d570be9c0e580d9be","measurement_key":"c3854633f8b278308107fa00dbfae95463146bf67704d334aaf2583ebd86621a","metric":"accuracy","protocol_fingerprint":"78050e47b74a82aba0778659ae32272c9acd82d3dab9b593ad89321878825832","run_fingerprint":"c20ead303a9f543a5d2cd66a0f6c5370ebc04887472d0c4a3361e678176a2a20","score":84.337,"score_display":"84.3","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8e000021fbbab64cfb726102fa61961041147495c7433403d9b5e190ce05ab4e","measurement_key":"4129768a8cdd3d275d61d49469d7c13753d92e69f3cf3d6a43f6154c1c4da82a","metric":"accuracy","protocol_fingerprint":"385c6722c9bada8ddde7aeb4b35c9ed8084af42f46e15fc996b9b0663fc95c2f","run_fingerprint":"6707090f55c8c4004581d52edca44d8af3bcd65092983aa2931209ea3cec6b21","score":83.931,"score_display":"83.9","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9906b4e72b0681f54248c6df6a13d4f154c560a731c05fe0414eb5bf272df7b8","measurement_key":"bb4ea2be4d09ba9dab9cb7680e8e592cd188d0f80e811813b8863bc1d596d208","metric":"fully_resolved_rate","protocol_fingerprint":"4cc623a277251397a3befa2bcf969d4beaab4a51795e84ea349ae44b2049f75c","run_fingerprint":"912dbb982b92a0145758ed6939877d130bf4994bcd33c88c0f1b9185232251cc","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f7bb423e07bb7da9c4b2e0e34127dc9e6a56409b8574340f2059a9db721916eb","measurement_key":"a11620c100cf0469066c50d68aa5e67e3e917aa99db4d81f0e3694c96464f183","metric":"subproblem_accuracy","protocol_fingerprint":"205a143825c138c40e6c26c54493d4c89b2783025790ca500e5c5aedd2858b5d","run_fingerprint":"bfc9c905ba519e58232fd02dfd3bb83f7b60aad0c2c63f8862e6d01c9e6e9864","score":46.6435185185185,"score_display":"46.6","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2852314d9246a3f3ce7d11d26eac27ed7158c68d99f8713d573a1582d3083daa","measurement_key":"11a91855e5cb3de085d72797a21404ed7ad6737dc20be215e98587ddf869392e","metric":"resolved_rate","protocol_fingerprint":"0429901a09da1bb12ca4e339fa4e0d75ce501271a46e45422c8f87881a41a015","run_fingerprint":"29713d07699290cd220bc92b081085a132d7679888a9c75fd226e93f18161ba7","score":86.0,"score_display":"86.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2852314d9246a3f3ce7d11d26eac27ed7158c68d99f8713d573a1582d3083daa","measurement_key":"11a91855e5cb3de085d72797a21404ed7ad6737dc20be215e98587ddf869392e","metric":"resolved_rate","protocol_fingerprint":"0429901a09da1bb12ca4e339fa4e0d75ce501271a46e45422c8f87881a41a015","reporting_origin":"organizer","run_fingerprint":"29713d07699290cd220bc92b081085a132d7679888a9c75fd226e93f18161ba7","score":86.0,"score_display":"86.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ae5fede3d0ec3894df2d05e10e54646c5ce810ae113b6c2ae1b7f95457c502b1","measurement_key":"e423d7ee6c396c41037c89787b82caba8067f1f99f00877eed023f20ed3b3cc6","metric":"pass_at_1","protocol_fingerprint":"fbacfe912d91aa95f2879238c50bc964b4a9d604cedf68fb0d6ddd99dbe61233","run_fingerprint":"4336c68f3498ac9e23591a49224c9f441487704744ee30ccf75eee49ec37e51c","score":48.041237,"score_display":"48.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"890983ea53bc484f007550d98c54aa46a0e9010c4c5379dff7cff9953093fa5b","measurement_key":"57920e5ee4e4148efd440bbe322dcaf4fa03ff988cf02887759f1599592eb8ae","metric":"accuracy","protocol_fingerprint":"92a4752d2ba425ebfb7b606ec0e40266e013369a168f1ac90723b1505b3661c5","run_fingerprint":"beb4f589c93126ede7001cf547b15825b3333232fa790d6096a654fd0f3e71fd","score":58.427,"score_display":"58.4","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_b7d9ab744ffac0cb856e114d","benchmark_version":"Terminal-Bench 4.0 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:17Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"52cba7a5ab374e8635cda393e2251eea03cf2baa9749ac6cd2cf53235e01b59a","measurement_key":"71a36e08003f19423dc25bd3362a9928063de744cf0c8f06ab431f6d63386643","metric":"pass_at_1","protocol_fingerprint":"8c5e90a846f073fc49430001247dd9bc4b8be3e36d816862f9fd939f5f6685c9","run_fingerprint":"8144c97e658e0aaa8b7f8e635ef21f98c90eaf528bd0797ac57dc7290b9e031b","score":5.555556,"score_display":"5.6","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"mini-swe-agent-66-tasks-500-steps","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d4753383f36a785d89352040cd7cbc406262440211cf6801491cc0a70dba7f3b","measurement_key":"448bb4c1e0d786837a059ef22f9e48fb5a0575c1b8cd6162c7849934c1d44b66","metric":"accuracy","protocol_fingerprint":"381b4d985d09f53a654aa74d214a893d8c7961b171af26652e0ca59b4459f716","run_fingerprint":"0f33c9d613fbc7c7fa410c692198cae57d7bd18d4975ddceeb98eedffc455898","score":0.0,"score_display":"0.0","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8046efe303364e852245851e831d5a8107fe15ef3ec46340b830de5960ca1d56","measurement_key":"29d9861bfb29770587559bc8a65cff440b1ca6eab15acf9fbab8de030ad9c6d7","metric":"score","protocol_fingerprint":"a4cbec25a0618431f2bfa98de222cffef038f5a21fe946323775068084d5f73f","run_fingerprint":"74a318a31dd1cb81e67006157f874e064d897b953fdb005ec829df0be88583ad","score":64.85,"score_display":"64.8","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_6037c094ef27884dccac420c","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ed19049f9355143318a6f403247972b8e04bde770fc875601370d0b3c524c7cb","measurement_key":"bfdb191ce69e854fdbe4035ee8563ce8bfabe2344217a5ff034aa06d8c042203","metric":"arena_score","protocol_fingerprint":"6e42f3096498ca8ef0dc77728ec0ecb4a13898970445cc867abfd00cc8760b10","run_fingerprint":"d73e68d214e7268a8370abee08c343f087ceea7d50ee52f6ff0b76a4bd7df418","score":1589.782268834193,"score_display":"1590","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_457b335e7d9b4a78950ca289","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":true,"model_id":"alibaba/qwen3-8-27b","model_name":"Qwen 3.8 27B","parameter_count_active":null,"parameter_count_total":27000000000,"provider":"Alibaba","selection_rank":55,"weights_status":"open"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8cb0ba7725fa149c884dabd7728e97ec29fca0689e138f10c4d2fee4722dfe67","measurement_key":"57d63243ac58365987e7e4664f6cedfb4cfecff4121485094bfbb876c18ba8f9","metric":"performance_rating","protocol_fingerprint":"3703c854922fd87933ffac6a03927594645fb65bf266479163effe7a72cbc1cf","run_fingerprint":"f37117ca2f0b6dc5b72d57da3b2dcf9c43c67f072185dea5b7b7cf56a95d8af7","score":1092.67,"score_display":"1092.67","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b51293b6b43d208ca931a702","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"803c667c2a6bbc253cd8bb48b4150c13be27e0824d4590e63b5a426c1a2230b6","measurement_key":"71d9c027ebc17ec3398b659576dd64dce5117d3f12338b66ba40bc38e96e4d94","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"06b3e33bc702f9ab7e4223803f589608786aeaa871a86642ce11d14938672a52","score":1460.9562197110456,"score_display":"1461","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_efc5f41143198675a7b4f23e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T17:16:43.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5300f83b048cca3903efc3b3e1e4600844291eeadf32757593ca1ec49297c5b5","measurement_key":"6c4c86e2ddd7b31744eab01c500e4e1a82664e16914ea0625dbefcc26afc589b","metric":"mean_score","protocol_fingerprint":"6d9a0a62e0c88726d5c842123588d3d8d828316157ab166b6e89a2e305e5cf46","run_fingerprint":"4f624dcd885e0807fa4c819b5006da66fe93e1d768b676e3866668cb2247c8ac","score":20.0,"score_display":"20.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_5933a601e7c8c1587b769e58","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:41Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a4c0f43e613a6ba215b0e7918a9de8ce7698fb9469bf826e16ddcfbb96222a56","measurement_key":"6cfef82fd3308aab4aa3e24a25eeda92478817771a5bdc4c77b2c9e50456ccdb","metric":"accuracy","protocol_fingerprint":"1cfcaea211044e0eecdcb06ccec090730c95c6d8d8d3b891766987ecdb5a5c22","run_fingerprint":"0305db3acad9346562b82cfa7afc5b7cbd83279fdf5e7a4cafc32428e3cab639","score":8.0,"score_display":"8.0","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_272add6740d961e9d97d445b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8e27b69e1e1502b7ef1a024b5fc4c27eef46d55037b3341afdbbc3c70e27e287","measurement_key":"cb3d5e1331b5f35d9f3e05478269a61e5a5d4b46d528dcde3786dcfc30cfcc33","metric":"eci","protocol_fingerprint":"1a36a3e1a3920057423840e4e0f9acfc2f96262d9408f161902586823dc57d98","run_fingerprint":"0812f207d0657845cef15921a07f931e796e456730b6bc9302cb110c7cd04459","score":151.06,"score_display":"151.06","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b310499954e2e03883d1bab8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":143,"at":"2026-06-10T19:47:36.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a2be517f551835c2975f7376a4e6e9a7992011168bb71fc433cbea9a33cb1dc6","measurement_key":"45a55c26a11226830d0519c9a7417f5cc7a987410e91fac31496256d99053792","metric":"mean_score","protocol_fingerprint":"fd03000a890c14001f3d5c700ecc96f6eb91519f1ac9df62125290f68ae9c967","run_fingerprint":"d019c653de1d0c6eab0205d88eadb08c01e9f89665b550ee6dfd1dfa9d17eff6","score":57.19298245614035,"score_display":"57.2","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d1fab5b0d9cdb6adb08d2014","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":143,"at":"2026-06-10T19:47:36.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c19bf8cee8b68ca4ae85854a900e1fcdec4f80244e2b0ec86006f482949ffed5","measurement_key":"41885f414d2b227e896c93a1bd3f0686b99006c6a2be2cd3b79691c73ccf06fb","metric":"mean_score","protocol_fingerprint":"79753c91c17a8c32905f7dda5872e1340706d508f05b9928e1eb76a02c7431dd","run_fingerprint":"c330f739a1fa78daad33c3b1667c0e06d4ced91e2f2461d469fbaa0d8ae7a78e","score":25.64102564102564,"score_display":"25.6","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_20fdd50658cc979ced3365dc","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d099f0dc777ae3c19ae2c847a145b399a8ebccf01e6b6af35b143669151ab086","measurement_key":"5f5317b1341bf0461354bd2fb4ff349ab6ed668b0d077f386f8b47c95f12f253","metric":"elo","protocol_fingerprint":"75837e8a30ca4cc1a47fc90487485f460c44117608afb8622d6ddf8caa2b696a","run_fingerprint":"e3015ec484dc140f9f776ae6aeed69d17cdd95587657f9247fdc17d72fcf6f58","score":1046.53,"score_display":"1047","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_42ae63213d558eb4662e56b8","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6eb01a2b3b4153b382e044ae8d338e9bbe8953b3b736ec1402c439b21aac5a56","measurement_key":"d8b0f9486342d418a6302012f9b0679560de87d6070837db742d3e2a5dc2b599","metric":"accuracy","protocol_fingerprint":"5092b11a27bd8a1af615eb90534dec811fd0d5ef01774616ac09dc220634a8af","run_fingerprint":"9f42954e1082e7b108d9e5e1f1bd13274cdce9414f480947c199ddf336ed7eb2","score":89.142,"score_display":"89.14","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_34a077e25a13de6727203c0f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_5f3023448c2ae4632fe1a43b","benchmark_version":"reported-runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":195,"at":"2026-04-20","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"e4bcdb2641b42e6fbc95ff19da97b21a0b778ef140dfd99b395e50ea1c2efe66","measurement_key":"3e91c966b3cea8a0e314664615f9ec4a63568664fe687b82c3c34bc6ce08942b","metric":"accuracy","protocol_fingerprint":"fba5f6b10977c74d12a0a51f51615d7e5547d98b2fd12ae73799ca2e93a9ceeb","run_fingerprint":"ec8de890b40885f2460eb1bd33be7a7283c41031722853f16d9a9c4f9a491dc5","score":29.9,"score_display":"29.9","source":{"id":"evals-report-hle","name":"evals.report · Humanity's Last Exam","url":"https://evals.report/benchmarks/humanitys-last-exam?tab=scores"},"source_authority_tier":"B","split_or_window":"public-multimodal-mixed-run-configs","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_68921aa42095f28a6654781d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"evals-report-official","verified_status":"evals-report-official"},"unit":"percent","verification_status":"evals-report-official"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"79e1112c7deb5ec44228dacc38f068fa8e466cffe7ecc7e4fc6f424dca875251","measurement_key":"9ba0e1f764c5a01ee1f22eb26b5a7de4cc5d4a01f72f7adb5a587db59deca734","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"e84c89ce6cd8ed3ea2ad537f45ba14b7f031ddc3639fb3cc640b7d5efc27ffb4","score":70.53878571428572,"score_display":"70.54","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_42ae63213d558eb4662e56b8","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9a7a82ec9015d77a9ddc5f3dd005ecbb9ada3c69afb6b63026cf4383a1d7ca6c","measurement_key":"f6296da4f44f08f2f7838c28ef7564e7060388edec947cb3988c5572a51fe437","metric":"pass_at_1","protocol_fingerprint":"400290ab721be6142e63bccc9ecc1fc530128e950d27e10f7141441d8e14d025","run_fingerprint":"a34028f9b621a061f50d650e30b34a2a893436de3f1970af28305c47f56d8f1c","score":86.771,"score_display":"86.8","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0921b0a660bb2fa8eba5dd75","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b90e3ebaef417db40fd44f219c2f439e9a8f5d3e3511c2e0f20c894018add995","measurement_key":"ac8d69f90dca1a03f1e24952cecf60b24f462644e5a3c017f4729382e087e679","metric":"accuracy","protocol_fingerprint":"a91873dc75c6740e34aea668d484eb2471a53fe70cda740ea02501315a6b9962","run_fingerprint":"ade16b5f83e8e96ac3f2daec22784e00a6cebd3fe0b6acc0c343273db91aa273","score":87.572,"score_display":"87.6","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4b0cec355eeaeb214599a32e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:41Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8da7a219fdf10359d80df463e888bb6ad42ee8744afe5ba156a100a7484b66da","measurement_key":"b930e6b181b6d896b13e52db6453eb6a6f530ed2cce2d04039098c9043b06f0d","metric":"accuracy","protocol_fingerprint":"67120e7fab38a96fcd406c42dac9466fa1d2b08f0b04664f3b763bf476380dec","run_fingerprint":"cab689ea84ad923ebd18cb1a73138c40d1562ca98728e139fe587c3f524da377","score":86.301,"score_display":"86.3","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f9ebb9b70f07c7fd44aa7c3f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"osworld-2":{"benchmark_release_id":"release_15c5525fe39f33bc181dfb69","benchmark_version":"OSWorld 2.0 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:06Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0789f4f5a281cb92dce84cdb14045ab781dcb6b7841caca0231828ee82464a2f","measurement_key":"cec24f902ade38ea51513a015b0ddf9e27d187243ee06d69544609ec03df21e7","metric":"binary_accuracy","protocol_fingerprint":"0d8f505dbc71ac537e0aa87c689661ebe93d7810bf90905213a1f0cdaccf5283","run_fingerprint":"90d37ac22d9518349fa113c8b00c896c0af070cd2e0b37665b9bf8ab1fc7631f","score":4.6,"score_display":"4.6","source":{"id":"epoch-osworld-2","name":"Epoch AI mirror · OSWorld 2.0","url":"https://epoch.ai/benchmarks/osworld-2"},"source_authority_tier":"B","split_or_window":"binary-accuracy-500-step-budget","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7a58f8d92e38556c6d31424b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":183,"at":"2026-05-02T09:08:49.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a9ff6be6f8ebe3935cece7b53082635b9affa1690e1bb3fc8e0f70e0fa5ba287","measurement_key":"96c112b0bc57dea4223188011de97cec6f16eb98bf3a5ea5340bb14aea75cf4a","metric":"mean_score","protocol_fingerprint":"eee7ad52081a22a866018fdb36a96a8d45cf0b2c81142142245a800fbef0f45f","run_fingerprint":"42bca31c9830028edc40d13ef2d2b0a0b2be219cfbb1a5b411274cecaee6fddd","score":96.11111111111111,"score_display":"96.1","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_13dc2af2a60f2cc07172f0f7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"04c46149ee98c54afd91cb4ea0cb8b7fcb26eca64caa20719a68aa5b76fbd1b5","measurement_key":"ecf6b8a48b34658298c37386c4a7c366f24f7e6ad782df2ab65e22e316fa9997","metric":"fully_resolved_rate","protocol_fingerprint":"3f08659201588c1d8eae9bbe331be789d3372e8a2660ab9476713731388c0192","run_fingerprint":"f221e1218b84ae441a54724172973ac40c587f052108183b9a341e19c462ba13","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_cf9e248427b06c9503d322c2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:47:54Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5c89ffa04a95b2825a4df9758c78bdb5ac69f2a8b82267c049650d5dbf23d842","measurement_key":"a7e155c1f6d61962bf04c9e425517b70f49947f6006761457e1d0e7726f38c0b","metric":"subproblem_accuracy","protocol_fingerprint":"c96e38cd745c305f2097b7074864adf7246c8a809c41b1eedb41bdabcef11817","run_fingerprint":"ce1ef162587cf6f237585ec94974062714093a54057e3916b560a16492fcff1b","score":53.4722222222222,"score_display":"53.5","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_96286f612a6bc490a7c6da8c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":82,"at":"2026-08-10T21:35:30.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7cd9a373305ea666cc786f7743848a194492487316e10ac3b4a8dd7aba67e91b","measurement_key":"52ae7deb6cd9723e3d8b573b665ef06a0e0eb5ab76354ca6e2b359054b1417f3","metric":"accuracy","protocol_fingerprint":"09143fdf56d84fdffc3344df3475d5a69d20be0048770624622b4be3711fda75","run_fingerprint":"b68e02849ecf09e56443eb3ec156b0c5cdf69a24b0426a037ba2ab9f465696d2","score":34.9,"score_display":"34.9","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_97380cea8f577d9e27da9479","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"skillsbench":{"benchmark_release_id":"release_093b45b8b752b3f08534f6ee","benchmark_version":"v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":138,"at":"2026-06-16","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e5407904f4372dbe8c907a5b04afcd16ae258be8fe44092098eec21c49a3c844","measurement_key":"68e82adf3b0db4f2b502cbff885bc156a7ac41711f22a5b136ef07fc4ebd9d44","metric":"pass_rate","protocol_fingerprint":"c2ed2025e534826e5e627446f4493a128269710491b35eb2122abbaf19d56304","run_fingerprint":"398a6046fe0df64a1b6805979de434544381eb78c043bc13dfe324816a282ce6","score":54.0,"score_display":"54.0","source":{"id":"skillsbench","name":"SkillsBench v1.1","url":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json"},"source_authority_tier":"A","split_or_window":"official-87-tasks-with-skills","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c8716685b104fcbca109c687","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"88c432b7518a7b204ef8e8757846e901f39ee473f968b2b856dda225cb723e1c","measurement_key":"f2b95a70b1441ad92522789699331a07df881e860424d1f401f423af331ac16e","metric":"resolved_rate","protocol_fingerprint":"88f8440a9094f80a17fd6eb95f51ec4399a09a41c92056772c872a6dcc15adcc","run_fingerprint":"175c3aeb6498201a97e0c74e949527fbc3811560a4e1a2923112fcad1e6c952a","score":76.2,"score_display":"76.2","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_55a0f6cd9901fb49f5645d5d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"88c432b7518a7b204ef8e8757846e901f39ee473f968b2b856dda225cb723e1c","measurement_key":"f2b95a70b1441ad92522789699331a07df881e860424d1f401f423af331ac16e","metric":"resolved_rate","protocol_fingerprint":"88f8440a9094f80a17fd6eb95f51ec4399a09a41c92056772c872a6dcc15adcc","reporting_origin":"organizer","run_fingerprint":"175c3aeb6498201a97e0c74e949527fbc3811560a4e1a2923112fcad1e6c952a","score":76.2,"score_display":"76.2","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_55a0f6cd9901fb49f5645d5d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_72d764965dd7baf34f983249","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b21ad5872a6e89f68f9d0b98ad4b8b4d9720f2264d892a74b71629c9ab867ec3","measurement_key":"02bcc7a0afc7ea94e20a6d7f299b7239946012425102d421b50bb90e47500b52","metric":"resolved_rate","protocol_fingerprint":"4d1be04b07e6b95bf0f76baf433081fb6639c9fb4e627252e3d479715ccbfbaa","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-03-01/2026-05-15":{"benchmark_release_id":"release_72d764965dd7baf34f983249","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b21ad5872a6e89f68f9d0b98ad4b8b4d9720f2264d892a74b71629c9ab867ec3","measurement_key":"02bcc7a0afc7ea94e20a6d7f299b7239946012425102d421b50bb90e47500b52","metric":"resolved_rate","protocol_fingerprint":"4d1be04b07e6b95bf0f76baf433081fb6639c9fb4e627252e3d479715ccbfbaa","run_fingerprint":"be694bdefd40775a51817ae697c4f62023561dcb56ef9ada9173e1300a3291b2","score":46.54545454545455,"score_display":"46.55","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-03-01/2026-05-15","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_85d245e50cf88f18729906fb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"be694bdefd40775a51817ae697c4f62023561dcb56ef9ada9173e1300a3291b2","score":46.54545454545455,"score_display":"46.55","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-03-01/2026-05-15","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_85d245e50cf88f18729906fb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"641da7027ee22f84829c09b95c4971f4017e1dad331f649ec6427dfe891736a1","measurement_key":"4578dd351ccbd3df9df86655447d732af2c3cf26d1a9c4140600a182fd02b830","metric":"accuracy","protocol_fingerprint":"1eabcaa1cbc163be53205bae4888d46be72fc4139789f749e9ccfe9687560429","run_fingerprint":"fcc4f8557538032a74a2e1b3fdab2ae50d289a0f2c4d79e49b4250c763aa69df","score":53.558,"score_display":"53.6","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_807bb82ee74af1856495dc68","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6d3e24c267eff6f5cc605113a1ad8412c3406b828f8ba8fb7d3048893219ac33","measurement_key":"eb6039ada8ef3ee7fcffb6ecac0637e0a636c8ff14ec55e1cbcaa3702598a2d6","metric":"mean_final_balance_usd","protocol_fingerprint":"7a300a06689c1bfa973d94d09dc598138039797d33b8ab97c0f89de019eee6bf","run_fingerprint":"f097194891f7968099a9b36ce782725720db3f55a6cb7a52650f2067b65dd89c","score":6204.570000000001,"score_display":"6204.57","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8c49ed901c348b23f62acd44","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e7ad1babb6553c01885c7a844189729153986852b18c57d54b5a5dee9d5d6645","measurement_key":"27ec5c6d7134ca4de84d2d55ab5d0ba8c222dcc6d538cece7e4d8e36b10221dc","metric":"score","protocol_fingerprint":"0577014ef287237c351705ec687359bc66a5fff7e5a98f55a202dfce4652778b","run_fingerprint":"7aea0b474b876075e91cfe70e19acbc3e6a397cbf592240bc8ddfd9b5c05a2a3","score":37.891,"score_display":"37.9","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9eeb07a0de769530f935f98c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"34683c305fcfd0e020f8d530154bcedcafbf2f323335dfdccf72acca1d36f4d8","measurement_key":"8a15871567a6eabd0207b7cdec0684bbdf637c3927633eea41f2d87352164ea7","metric":"arena_score","protocol_fingerprint":"b6d68f0e330c4c42ff79ec43a679019070fc63ec56d11461a675d60183ea159a","run_fingerprint":"f1cd5e27dc2fb17e6d635760520d7414a798fe5b9f0263a35e9734a351562032","score":1509.2234110707893,"score_display":"1509","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_768253bf922f44c1efe3bf53","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9a7e46250ada3964ac8065fd0e4359604a65af626f10252c7f5c34ee74bc0baa","measurement_key":"09c23513ad9ef0a5a9ee38c5a0eafc959e93b9b8f445c9b83699e53a5a42df8e","metric":"accuracy","protocol_fingerprint":"7c243afe23aa63e3900363e414753a05d10990b90cc42da92099149355363aea","run_fingerprint":"dd4c5ea3f1f229b96a86a3158de4a8955ab8e8f9cd1dfc4914835786d3e4c3b2","score":55.86,"score_display":"55.9","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3011d20cf3046664a1d12e36","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"moonshot/kimi-k2-6","model_name":"Kimi K2.6","parameter_count_active":32000000000,"parameter_count_total":1000000000000,"provider":"Moonshot AI","selection_rank":56,"weights_status":"open"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"95541d797511b058a4c245b11f814593ccb2f138ababfbcad40c22a92db46b37","measurement_key":"2069e54b525746b59d476ddc29ef54c6daf9391cf7d171528eeb1e45093a671c","metric":"index_score","protocol_fingerprint":"c4d84d2dadbc521200297ea3702054b3edbfcafc1ba3a24f49b1f0a088f2c719","run_fingerprint":"ec6156b3b739e5da81da96fd4f0d554d4b3d9e9ef302efa8d1180910a7bc7283","score":59.425739,"score_display":"59.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_ef2e61bb3d248820901f479e","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0e34caf709604edafe701c970aafd9e2ca36f30352d56f3a6a7ee527cd367cb9","measurement_key":"39db517b2bb4b72c30513da574364aca37449e9bbd7f32c8308d3feb311e33c5","metric":"ips_score","protocol_fingerprint":"14da946bb1ef3a2a6d55f565b4355605f01cfef3a52d4f2f4592720af7e54015","run_fingerprint":"2f5d752bcb748afa36bee16bb9a6fe192f6b99dc289e60e5b47668b79ca342e5","score":0.16038738558073073,"score_display":"0.1604","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_ef2e61bb3d248820901f479e","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4b1c6c03f4adb14c065a60d6ec174f4e01d7d642cf7ee6f7a786ffe5d14b1ab0","measurement_key":"d186043ef129e984967f81e62b325fb17591b4816769c3ab91b8adc96267046b","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"f003e202d7653e285697b4265cbe660a705b73d4926a3b02004cea6ceb81b4c5","score":1527.5065447464403,"score_display":"1528","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_ef2e61bb3d248820901f479e","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-10-30T01:41:14Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cc925272539e66ddec5973740f4025989ff4331be1b31ce3d17602ca7b7384b1","measurement_key":"3eb8df93d206b98c53b48b08e4131105a640b830b2ca58dd7c48a4976660724c","metric":"accuracy","protocol_fingerprint":"34338c9b2fadeadb5295df7ba4be76e2c32f720f04e4fcd0f463dd86137201c2","run_fingerprint":"b0d64fdc0c57326c81464cefab90896e42e00fc7836d73ec7264537482a47949","score":36.0,"score_display":"36.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_ef2e61bb3d248820901f479e","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T01:23:12Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"be4ec243000874f8ab9eb312e6d4f49b269108308039c6d26bfbeb35b8339325","measurement_key":"bf0b71e358ea853355c8e3b765acdd3e53a36229c56d63a2360db857906bfe72","metric":"elo","protocol_fingerprint":"1a5f92827d69d1b1f5cbbd17a7908fca6238ba6a200f877c4a06ca8026a1d323","run_fingerprint":"42eb629c537fddffae93927b72831e39380fc8cfb3c9560c644fa3adffedca13","score":1732.68,"score_display":"1733","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_ef2e61bb3d248820901f479e","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-10-30T01:41:14Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6ee11512e17238dc2ca98049796b5dd1d18c67629e258faab9c6c80bb17c1672","measurement_key":"6ed04592720d4ac4c6331fff0e0b3fa83bd23394eaab58aede7f907a81e2919e","metric":"accuracy","protocol_fingerprint":"c5e5d47080878b2de6edb10dbd025dd5e5c4c534dc4eec492f17bd3cceefe25e","run_fingerprint":"5d9a72461a39864d9a07cb6359908eb60c795ebf54fd7c069b08f88f27b5fcab","score":60.379981,"score_display":"60.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_ef2e61bb3d248820901f479e","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:02Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"142104358a3d37bf12cb0822baa88d7c1fe9f66ec39172c2b6e4e9114b6362ed","measurement_key":"a4cb272333930a76e4c05a418e3041b57b68d509de7a7c6ab40f693f301b9a77","metric":"subproblem_accuracy","protocol_fingerprint":"455dd738b5e3c71e92887fdffc46310d86b2b175c73b14ec36f5a5ac941d636d","run_fingerprint":"3a716e98a9576165ec5939f1734453c6785e3a19d7d8879e5fbc17a574450456","score":64.2361111111111,"score_display":"64.2","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_ef2e61bb3d248820901f479e","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":3,"at":"2026-10-28T17:21:40Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fb5f2c55f8e81aa18b5823c39127d5ea04008b3bf8fbd1d529eee1beb7aef469","measurement_key":"09c0f52660ae1b06441beafe66ff83cf788f1581c38abe611f8f5e9f5f35fbf9","metric":"accuracy","protocol_fingerprint":"6a086a197e82461d0c102a47469a3d683aa35b33bfd3b9a55cd8979eb5397fb4","run_fingerprint":"3a1054edbae3b889fae3871c001fc12b8bd4b23d556510c4915c0b0d06e31a11","score":63.131,"score_display":"63.1","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_ef2e61bb3d248820901f479e","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:04Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"91da289e27fbd14fba0c714f19a2d156ea94cd687928a8582627cff0fec10ca9","measurement_key":"790ee7bf70c9c7094e061bcbf5c7b647b468b14328d509c049b36099dcc025d0","metric":"mean_final_balance_usd","protocol_fingerprint":"d407ee77c4124e37711dd76fa884be59b9032e743580984a40b671e739b0b306","run_fingerprint":"7af1c291543cea1ba9213fe641b804733fbfa63b0002d20672fc013c941395a7","score":16484.20666666667,"score_display":"16484.21","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_679b802baec2b647dedb9379","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":3,"at":"2026-10-28T17:21:40Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"272ff4ab2477cc7cd2697adc6ba167e03855d318086bd38541f92ef2c36414b3","measurement_key":"bacd86396f95e227d8dec861cc48cdc70a1c9d8bd84805dd52259154f1ed69f6","metric":"score","protocol_fingerprint":"04e5aaf4f23019399011589f9c7a66735773fe5e181b0e9df63f715bbdaaa447","run_fingerprint":"5f3304ae158f46f8ade7c6995684a8df7ab353eea5b91a617eebce55551faed0","score":89.06,"score_display":"89.1","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_ef2e61bb3d248820901f479e","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"163c196997bd7ce97f9a7c2d6025282f4112bfe4dafad8c0c43c044bb582db16","measurement_key":"457a0df432b54739db9dde4518dcc77b3225e332767ebc0fb12192f9bc583f80","metric":"arena_score","protocol_fingerprint":"39e78e0869e437de68dc1b47580a9be86c44e4a6e51d73a262c872e2e1fce40d","run_fingerprint":"5c3ae235f579c38ad087ab27f6951386c2762e266d2fdaf08ad594180aeaf15c","score":1768.1522310766236,"score_display":"1768","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_ef2e61bb3d248820901f479e","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"google/gemini-4-carbon","model_name":"Gemini 4 carbon","parameter_count_active":null,"parameter_count_total":null,"provider":"Google","selection_rank":57,"weights_status":"closed"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7f52ec3982ee0a999a9b8f433b643cf525623a7b3abd210a63fce94258e43e16","measurement_key":"05dd530ce9cfc43acd7f687b62ad2679d8383bbf2e6b4bbde11063254e33f465","metric":"index_score","protocol_fingerprint":"63bf02113ce453ed20f8747588b2013ddbf4707d2cb68bb4e7a10a6436327d0f","run_fingerprint":"064d3a423182585065566307fdf86b48f70f1e859cd2ab02b813085610f4fda4","score":12.47817,"score_display":"12.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d7ea10543bcfd3f2dca6a744","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c7b80936d21e5e777731ffb7a6b34ab555fea4b2ff2060205331d0b39d0720e9","measurement_key":"33b30fc9825156c77a4eb21d8c5572656c4f679d3db4bc2cffaff5cd5d5f507d","metric":"performance_rating","protocol_fingerprint":"15a3f86976f978661efbb94596401133b13178dd3ffac3599cb852845d2f49c8","run_fingerprint":"72d0f368e6476abe55f21c62000860db5b1c2d6f27fb52a47e8697949b9ef2d8","score":946.0,"score_display":"946.00","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5b46a048212c2bd56946fe13","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c7a4041776299f234e22e6962c6194921b57fed0b9b14cc7f6cf9d12781e3bef","measurement_key":"1db51bef20ac0a4229e96c7559c5df05bd87a0c6e6371728f1a17de065bb3f4f","metric":"pass_at_1","protocol_fingerprint":"271aff4c2e1b143be813fde8fd1c641c2f10f92b540154a47c713fef5707ea2a","run_fingerprint":"c48f2a911700e701512bd5964b955c0dc24a591485f897276715f9386be2f1ba","score":33.8,"score_display":"33.8","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2c3ca31d2106579e73b85c2c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7697b7a2b2b14db76174547bbf9c821110e4ab35fff84baaa1ee939f8b5c9551","measurement_key":"95f47a6e88925cd9875eab7985e2514f73c0c944e50717a6cbaac2ae4fbe6804","metric":"pass_at_2_accuracy","protocol_fingerprint":"293efacf877896e53be0b51a4aef786c41496191bf99b1897934d470ed42dd8a","run_fingerprint":"90d7d869c6e1c6d4e29e70c66803fd6041b56287a7f7d6777498721d9113a584","score":79.5,"score_display":"79.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_84441dcf4ff9d3a7ebb4f5f3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fa687947c022d0f1e6d436c7c2ac02664df3fefa634739de73390bdb9d592a45","measurement_key":"da80ee9119094ca4ad4165cf20116662d660dfe5b52284a263df0f1c141ceea6","metric":"accuracy","protocol_fingerprint":"84ab3445a8f1e639d5912777a39d57baa63d5da37edee2657435ca577434367b","run_fingerprint":"f867d506fc1010a5fd4e433e6a3ff5dac2af9a165114f2b971e8c92c917beeb0","score":36.52777777777778,"score_display":"37","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9f4576349b0b9a1dcba8e325","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"35fa3f469523b52e17feb29cb0f5472051fbf25630323ea90599ed2941cfe49c","measurement_key":"7f6d24742211be093f4a7181fda13de4305588c8ab901f62278128eb5b95660f","metric":"ips_score","protocol_fingerprint":"0f592ab5858e3b737b1549d2b862d547e292e081524561154d721017c725443e","run_fingerprint":"54ee42be05bb2a35f076b81a2ed096aa6b9cc39767a89ea3c5e58f472a8102e5","score":-0.15799537295041588,"score_display":"-0.1580","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_868910b5371c3f0911dd2a6d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dcbeab653adb2d0a9ce0b5c7d8de453f1ec00f3add5607e2c86c0b016b6aa5d6","measurement_key":"07187618ad31793054d52763f5bebbf8addfe7848172dfa3165546fdaa061ab0","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"0b6602182eb8858b634d7c475a32ff07426bbbfe4158648c2ef6c7e5876fddf8","score":1442.201111233133,"score_display":"1442","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b73fb4763ea0cafd73adca99","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T12:49:23.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b5f0d154bc8448d87c6c94146385a4c7071acff056007d85e6e904b70f1f7599","measurement_key":"e083c7cfc7b08e08b9ab872b4b15b118cf393f83a040b348cb676db824c76f91","metric":"mean_score","protocol_fingerprint":"d18b2698e7fc230e2af92daabb030998e3f0f1722bf5cff30628c76c41c44052","run_fingerprint":"2efd8dac71f20bf5948956165734fbe3504f8ed5ad47b541753bbb0b8bcd00cc","score":21.0,"score_display":"21.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d7ea10543bcfd3f2dca6a744","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b0497db5e1a0b577740335178835abb025978faea8d5566bff669e8cc15b3fda","measurement_key":"70b0e0d2a3d3aa7c95f7c4d62d184c2f5d31a5d94ea4717e1d05676fa96a4151","metric":"accuracy","protocol_fingerprint":"ecbbe008614a3c58bf3e0adcc54d3a3d232f589b2a949eafc83f1644549d9f14","run_fingerprint":"dfbcd9697cedab6d1c5a87110e99855fc5ca34bf2f28fe272cba3b646692a028","score":5.42857142857143,"score_display":"5.4","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d7ea10543bcfd3f2dca6a744","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"209b86c655c23bd29b378340c78ff4c30aa4e94f6bc05548d72e7d09fe3baca5","measurement_key":"0135995ac2894f9d813b5d847aa9e78a3a761eae995d23d5ad8e56ea4b829409","metric":"eci","protocol_fingerprint":"b8b550d08d364703b48b080e40c5e90d183330c9191a02fba5a517ddf77c8534","run_fingerprint":"a3fefcf87937193a7e06eaf15a749ee21aa97a69dd9fc9f9261d8c3d086a995c","score":148.51,"score_display":"148.51","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_57fc6d9a28dcfc60bef75504","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"31b8c188c5b2e3c1f0486616f4f5be6a0d8270c5cc9cca4e3ddad256a30024a6","measurement_key":"010546a525e21db54b5348593f432894b89a527e609ab29833664e61316ce1f3","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"4f671b8d19afc203b8b3147d4f5f2816d40402fbcd2c142155ec201ac578736f","run_fingerprint":"a0263a3ed5e167984b1ad5baa78aa3e8abe61902934e44bc3d403333981b2ddb","score":14.000000000000002,"score_display":"14.0","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b8c36c61e899913b2bb3beed","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-06T20:14:32.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"813407a7c4d8e82989ae0ae7805d5ffeb9ae752f9781dce82953aba9a138c151","measurement_key":"f66a0691dcc209b83f541a67e51088abba2c11829cac52b7e38b8453372b0b01","metric":"mean_score","protocol_fingerprint":"71b356cdd9bc989e02c5e1c7ada49f7370ae5ef3e39de146b938b0bd88eb988f","run_fingerprint":"e4e24b73639de33451ed6ce5179ebf4a73b6498fb08e3ca6b62ae7758c26fec3","score":33.33333333333333,"score_display":"33.3","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d7ea10543bcfd3f2dca6a744","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-06T20:14:32.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6bf6196ff5b35f17817d5e5fe674717a42bb5ade51797f2d565e6cd2e06981da","measurement_key":"2ddf0ec8515fff2c3395bf8df642503815a8fc679ea27fae5899db39e82819a8","metric":"mean_score","protocol_fingerprint":"5d06392ee872e180a995f19d965db004f09484e9081d09704fbcf92473a6e0a0","run_fingerprint":"0cfdec21e3fb756793e7f86c2f7966f80fe267b47318badaa7126de325d8e4b9","score":4.878048780487805,"score_display":"4.9","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d7ea10543bcfd3f2dca6a744","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1927787518250ad46bb54d258515d9280773330259123b85284bf44c0639d264","measurement_key":"5a5015e105b8e48111e706e1db535f0133872fac3037211ff9477ae27f9b695c","metric":"elo","protocol_fingerprint":"28115deb8d5a4ceb421a7ac3621b3893a92e169718e0a321a68cb61a2206e9ff","run_fingerprint":"debc15d4ce52e7375f97ea991eec24138b0739727f33409d3edfb6cac1d470f0","score":1080.22,"score_display":"1080","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d7ea10543bcfd3f2dca6a744","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6bb8ca8d57c2a563c1ebab41e832badcc4a107cd7f707892715face7abe7549b","measurement_key":"0eb6ea9c09b80fd767707a48fdb2d7f046325ca8465a9bb0b9e4222606a30c81","metric":"accuracy","protocol_fingerprint":"eab2240a7ea2afea2366cddd07324c0c3addb6191e64983fa6e9ea882744a579","run_fingerprint":"0f1dc49728933183dff43a65eaba790b1886dce37e6c837c3a731e0194b1caca","score":87.122,"score_display":"87.12","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7279a3f7a28bd9930d9b03cc","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_fa9e908ac04b067eb00182d4","benchmark_version":"HLE official leaderboard","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":63,"at":"2026-08-29T23:52:43Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"25bbc941cc962f4b506ba064e1cf5148c1ab07a6707d22e75e7481fa545ee313","measurement_key":"d75a4cc3f1f19bb0aea71030245c3a10f1a849a61cf3671139f6da6e1268b49a","metric":"accuracy","protocol_fingerprint":"e1f956386a97e6ba42a3c396757902d19f19cdabb10fcc91e345af5c771a2890","run_fingerprint":"28ace341855c8c473f37c6cf975f82b24ae926710c03500428512cf5d1c2574a","score":46.0,"score_display":"46","source":{"id":"hle","name":"Humanity's Last Exam","url":"https://huggingface.co/api/datasets/cais/hle/leaderboard?limit=200"},"source_authority_tier":"A","split_or_window":"published-leaderboard","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9917693906cdf9a9f6c99327","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"C","evidence_rank":5,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"self-reported","verified_status":"self-reported"},"unit":"percent","verification_status":"self-reported"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"53c786ce63f4dd0da8e801dc71006cb2ac13cb59eac11086802f66c87b2aebc5","measurement_key":"0a1f1831cf7b93bd08c913de171948d93c255a1da487815aa6f814926de30de5","metric":"accuracy","protocol_fingerprint":"7f0862a25debfb669368622a3fddefcebe68ea6f18f784f8cd24602814d640c7","run_fingerprint":"39fe55615877fe5d90f9380450c5a3be173813f0bcf19708bdcad4f901723784","score":31.881372,"score_display":"31.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d7ea10543bcfd3f2dca6a744","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6f2d2fd8bc922eb43ef1f1c5f7e341383c52289674cc475839d8c9f493106acb","measurement_key":"a67f6ce3ec4bfd44e467beddde1a449ea6eb519d49ef2bbf948322d8e379e2c5","metric":"score","protocol_fingerprint":"a1e509f0f8519979ad82270626dfca0ae9e6c4c815f28e97f036df46eb00c637","run_fingerprint":"92165c11c71cfc7a4be9e5eaa1ff7fa4d1bf90a47bfe9ef480ab0e288e459a09","score":14.944,"score_display":"14.9","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_aa19ff77759412701a03b4d0","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5a68deb6e085d52ef45610156f2b52f9caca19bf2112b201a42dfbf6642ddf57","measurement_key":"2c9c265d18fb7224509c06456861017ffd04b99fdb73ff998d7dbd34692381b8","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"373a470e46dac02c078d8990dc62555990c41d8bcb2c2809e0b9e922184f888e","score":71.92241666666668,"score_display":"71.92","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d7ea10543bcfd3f2dca6a744","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4500f560f441a70a909a984f5a1b5a658e3a3d5de1708b0b0fa25cda28f40100","measurement_key":"6136361ed4beefee947fa1e37005201593c75abf98d01b2afd78100ce96adea2","metric":"pass_at_1","protocol_fingerprint":"2fc824df4fb3315c29a1859123eadc86dac59417f8b7b09bb4fd7e9f2d3634bc","run_fingerprint":"393f218809d3b79e7e88cee07993e04d02408293290c5bea7ea851625ae76a08","score":85.517,"score_display":"85.5","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d9ea177d067409c4e24792fd","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":108,"at":"2026-07-15T18:19:13Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f71438e4aafaccfa1215fd51e96401d544f30f6248a3a78a64d8659d7aba1bc5","measurement_key":"539d4e41bcfe2a3bb2f1b62845aaab7c44672314ea8c7baf43d8ff927542e200","metric":"pass_rate","protocol_fingerprint":"d8e050659dae30b1689b8d802e922805001c6f77a4e3ce69895de8284fda4a12","run_fingerprint":"cca823b5ff2d765a8315479f2dbbb771a94036aca675b724afca047149a64b47","score":76.0,"score_display":"76.0","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d7ea10543bcfd3f2dca6a744","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"580c61f205eab92cc0bd1e0979e6960c1d5239018d8cd91250411adc1746d5cd","measurement_key":"4c79f93f816302f35941429e93562a57e0e3c847c6fad8e3ee701b3574e7f726","metric":"accuracy","protocol_fingerprint":"7f37d3be152bbb7073099c5a5d7650b6b70a0e912c3c111ae743a63ad5fa0955","run_fingerprint":"dc7db2cc9ce053eba8b01ab8f2caae0ea4ab154bc1ca8c48bc4b447c9646a5fe","score":86.295,"score_display":"86.3","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c8d9902582e198f49805a576","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8878841f72f67ebbfb49be1f59d9e8344b3bf26122cb62122c814743c2f1b1d3","measurement_key":"4d101ac615078d661a4d2af288ef36c5a7d8bf965e6a5e6675a8af58fcab5500","metric":"accuracy","protocol_fingerprint":"5d10cabb7b749a985b6e91c0c5a8ccca1a2efc80b4461f90ec7b42da9d0ca1ee","run_fingerprint":"fd162a4198db280d04c4ff3231d51faad58c18d2c628983a5614f26e78d45b22","score":78.497,"score_display":"78.5","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fa698e6a574cf4d42e206b07","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":87,"at":"2026-08-05T18:55:39.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"11810ddf46ca924536300ea312ffde64c4cdbba0e4bbe98539aeb020db8a3ee8","measurement_key":"dbde7487143792819933cf58c9fcc0b4b4df5d3f5d99ff5fbe96ebfdd3a6679c","metric":"mean_score","protocol_fingerprint":"d7ccddb87a309ce5d6c745f39bb12910ef2327bf966e1c993a0a4c524bce446f","run_fingerprint":"12b91534e2bde8e1dfe2cf67601c1018c074ccabc4ecfba514ac966908b6e07c","score":88.88888888888889,"score_display":"88.9","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d7ea10543bcfd3f2dca6a744","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"197ccd8905f941d98d13c5d1cea099801d0d2180bf94155b484789ca391cfee1","measurement_key":"76a8541733afc9057f6773f40b884a6920c41f223a377f62f41fd56b1c0bb523","metric":"fully_resolved_rate","protocol_fingerprint":"f5cfc600a9accec5d0ff8f3059124bd2410a94efb6d16aad80dfea4bffb92069","run_fingerprint":"36475da28262580a0233d90d43cebafb1fba39c5bc484b04b14e6e514f7c83f2","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9fb27134891c2a3b66e9b8de","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"795ba6fa840cc52c51ffef54c95e1759630ad0e56f451716c8af937d31fc9d9f","measurement_key":"4c8ec79304a3daa3c198b8f267be2a6966da3623e37ce6d60a73a9b30875ded1","metric":"subproblem_accuracy","protocol_fingerprint":"e70a081ece68126afcf14695488ee1d26d6ce32b85c428cf6263689eb284c447","run_fingerprint":"2415f6ecfb637e7d451eb58c52ee18e30f06d9d0839e81675054c10d1055751c","score":46.9907407407407,"score_display":"47.0","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d7ea10543bcfd3f2dca6a744","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"47cd03116df620a196306cf8465da660397a86c06d712b12fba071589546b694","measurement_key":"c3787c08ff74806584192c23b5d254881d9033aa9bfd5d428dda91430b2d207a","metric":"accuracy_avg_at_5","protocol_fingerprint":"f6b61380000b7f489f75162e5da21a7d50a80ee616f5a65ccd9f104704b53447","run_fingerprint":"daeeed7a5aa5aa90073ff9d6ace6aa7164dd65eced31aae9aa0a3b2dd7bb3b14","score":50.0,"score_display":"50.0","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_323430f8d70d985199accebe","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:36:45.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"45f5a3fb5e23060d78b5f26f6b81804a2b7623ce3744e57cbebc2f874be5977f","measurement_key":"7eb4abcc2235e8787876cb4b149e62f0d1fc712265683737bc55c5811fe937e3","metric":"accuracy","protocol_fingerprint":"20eb758f84971175d825a75c364c42137740841325eaf7993f5a8ad3ae1df78e","run_fingerprint":"9b609315dae0e488c10d46c22e58bcdc762932e9b134c127d3c6c5cfe630c13e","score":40.300000000000004,"score_display":"40.3","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d7ea10543bcfd3f2dca6a744","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"98446077fa6a51c0768fc10badcfb16562e7faab6a5077250a18e3c1018c044a","measurement_key":"231b9859d9bbeb435467b4b50118fe7977201db1ff0ecf7917786680d3fadf17","metric":"fully_solved_rate","protocol_fingerprint":"91c5039acc22e714d75ba3a69cce7c81c4de69debad4c2fb6d51da9496d825d7","run_fingerprint":"70786ee90a103dfca3d7335f3ddff1c4b978c4495406f9968e0853ae12ae5c4a","score":0.0,"score_display":"0.0","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8d3b7dba49e2253ccabbab53","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-pro-v2":{"benchmark_release_id":"release_d9b58bd286ce316ccf0ed891","benchmark_version":"Scale SWE-Bench Pro V2 public leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":25,"at":"2026-10-07T01:44:58Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8e8363c46aa63b1578b0535a68ed529d385d6fae8b1afa7e14cdba91bbc3b52d","measurement_key":"44cdec64955be75b329d9a9471bd553ba6effc77dd12675ffc1367c74de51f77","metric":"resolved_rate","protocol_fingerprint":"7e39bcaca5be9845b3f398aab817035aed9193cd7acb296c9ad29e0c5dbb4825","run_fingerprint":"cb848eff8fc388dcff2dbe056a2bed85ccc6326f8f017535d0cef4af3d3be053","score":89.88,"score_display":"89.9","source":{"id":"scale-swe-bench-pro-v2","name":"Scale AI Labs · SWE-bench Pro V2","url":"https://labs.scale.com/leaderboard/swe_bench_pro_public_v2"},"source_authority_tier":"A+","split_or_window":"public-v2-642","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d7ea10543bcfd3f2dca6a744","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0d2105fc8657e6e7a3e7934facbc566e62a1f299bd9724038f19b12b728f0733","measurement_key":"4fe5a3a4532b44b6361fc1d7526297093093a0dd76ca5bb3165ce4a7af8f51bc","metric":"resolved_rate","protocol_fingerprint":"178ad2c09e2fef8871c623dd837f4ee2979644bd9a7f685a6c5a2a34dda2a40c","run_fingerprint":"4292f39bcdb31e7a53feffa5304dab99f532a1e995079a5830ee695a17d9de4e","score":77.6,"score_display":"77.6","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_20afbe6979e993a50873f13e","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0d2105fc8657e6e7a3e7934facbc566e62a1f299bd9724038f19b12b728f0733","measurement_key":"4fe5a3a4532b44b6361fc1d7526297093093a0dd76ca5bb3165ce4a7af8f51bc","metric":"resolved_rate","protocol_fingerprint":"178ad2c09e2fef8871c623dd837f4ee2979644bd9a7f685a6c5a2a34dda2a40c","reporting_origin":"organizer","run_fingerprint":"4292f39bcdb31e7a53feffa5304dab99f532a1e995079a5830ee695a17d9de4e","score":77.6,"score_display":"77.6","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_20afbe6979e993a50873f13e","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":100,"at":"2026-07-24","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"48920c5e32ad3ac8b385acf9fe909cd110d596fa99a69006de811b8f925af3f4","measurement_key":"bda68d004c120f9ad748ed11ac2f805a9fc3b88d9ab799db0179c552f18dde4e","metric":"pass_1","protocol_fingerprint":"9b3a9ea0b94586db52813b863262b4d8c3a015bf4bc6452b53ac000c57e1562f","run_fingerprint":"44c4233e11067047bc9a5d2057a2bf9e49db4a79b9bafdd5da2559d705774126","score":25.0,"score_display":"25.0","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_5b46a048212c2bd56946fe13","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-10-01T02:30:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"04f6027383f49c73024c3596e432d1216593bbbb81d1886df5a23bebfb211ea8","measurement_key":"e59a351bfee73dc7805c70708582bd271c7f1a0dd5daf6944c742a05a2154d0b","metric":"pass_at_1","protocol_fingerprint":"b9dc6ce08f2944cacf598c9e72bd288a7a4376e850c70ac6cb563f0fdc531934","run_fingerprint":"47f990a214a5b191c5c73aa41d0a15033cf53df42974d481842ed6be4c0ec496","score":29.072165,"score_display":"29.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d7ea10543bcfd3f2dca6a744","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9d346d00f9e78d8a468a3b3f224957cbf381e83b0e4ad99c27a8e143a6167b12","measurement_key":"c82990b5bb92b6ac57988022fc09796af888d96a7f5434500f2d9dcf8eed0a8b","metric":"accuracy","protocol_fingerprint":"cece4b3d8227515c03aa4c5d4bcaee43541264ad81315bc7fa0a5d945676a184","run_fingerprint":"63da7f5dd10c6a8ef2c71b8a7ee4d3c85600ebc3f6bb6a0ba2d1a5589f05dc2b","score":47.566,"score_display":"47.6","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_551396cfb7201bd63ba1e871","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4e9cfdacae80678b9ce1d8904b5c3701abfb838806c210d9116c708e9a272984","measurement_key":"ea247be3b6e6294f8a5b77bfb31342dc24799ae022de0e8d8fc77ec556fd4cf0","metric":"accuracy","protocol_fingerprint":"ac8ae1b27815c194fedd262d4630054bce0548b3bd7b11dc4bd5079d7fe081e0","run_fingerprint":"466c0140146a637ac9e56034821f1fe9d37e79d0991abcd6e1977ff22915a941","score":0.505,"score_display":"0.5","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f608f4723bcb538ddab99191","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b7649608d2b6ff7102066d6dc7c6073eda33efd7987a3b9b891ab7f7ed9aebec","measurement_key":"d648c7940da0b380c5a4a1b1345d6424f9cb4fbe0de77bc4b51268cf508cbb54","metric":"score","protocol_fingerprint":"976d585baec8bdadde672f17193cc6586f99100d0e4cbf61345ac0a9c1132a8e","run_fingerprint":"3adbc321cc829be29be99496fb6bfeb4ddcfd90705ed7a7f571a6b4b4bccc003","score":19.214,"score_display":"19.2","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_777456089accb2a956038d7c","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6f4f36b1b98c760c062e205d1c0b1a8d04eabe2784d5f4abed7f3e17b8bba505","measurement_key":"b651f885ddcd13d7416f6cce3776e5df23e9b6b56d2e05ff990eebade0b53e60","metric":"arena_score","protocol_fingerprint":"ea835c5aec7baa48af8ad688ce932d00eff614eb4a4fd9478b4b556bfcd4ccb0","run_fingerprint":"597952b03529a149f8fed6cf88228499402ff9d6bc3b5ddbf4603f0d7d79b0dc","score":1415.192007852744,"score_display":"1415","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_75b2751fe3dec6d639534bf1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0378fe919d6a2ca882b55755d176cc48ecda9d47b9e82fc5a170077374b5edf4","measurement_key":"52f68ef617792ea1e49c6f882a9ae5a271ca80462695d6da4eab915815f8693e","metric":"accuracy","protocol_fingerprint":"4640d6de029d479249606816cda2c2b788d7aee89ef4aed6716d30abc6d774f9","run_fingerprint":"f029aec3d1ffc183f6279a649e177c101bfe16668abb5dea859a02ab76649902","score":32.29,"score_display":"32.3","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_a026da84feee358d3fb40d36","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"897c8e6468e6d583cd3ae772299dda9a4067dda8505a6876a593c4fd11907dbc","measurement_key":"d82d3f39e8a2e8f0b196257dcaf276185d3fda15d833460e22807b6e55a95745","metric":"token_efficiency_weighted_score","protocol_fingerprint":"13c017b8386b2cc196d73c6646ef6de9eed9441b45c56254cb57f018bd2b43c3","run_fingerprint":"1d96b2dd541c5cccc370af077cfd9a9c1a4802cfecfc41c171ff6f58ff0ea610","score":3.9029836363636363,"score_display":"3.9","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_d7ea10543bcfd3f2dca6a744","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"thinking-machines/inkling","model_name":"Inkling","parameter_count_active":41000000000,"parameter_count_total":975000000000,"provider":"Thinking Machines Lab","selection_rank":58,"weights_status":"open"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"675a5693b0cb124c119dfdda61825d6851377f99127a2c69bee745aa978676b4","measurement_key":"a3e16f32e1837b379d8b52f97aedc78ecd33817990a526bbb755af758cf3a811","metric":"performance_rating","protocol_fingerprint":"d65099c81612af988ffb7a0b93a5544a9a82eb2b87403f6854871af4995567ad","run_fingerprint":"c3cdda862cbce0c13ac6aab613eacb4d41485b1ebbfbd304a7a0acce3b74b930","score":1006.08,"score_display":"1006.08","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_c5963039dee3d753db6b264c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"da8b49ae999da132ea7181cec054cc839593ee172bf39e0faaf701c6486ab10b","measurement_key":"89a80b73994fc7e8fafb6b2ffb2cef53685684f3a39ae7eb54e654bea835ef94","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"1f53a396e6ae0dcce249d880ce6310365f8359affd8a40c6ddbfbcb808c84ca5","score":1454.894064898029,"score_display":"1455","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_c5963039dee3d753db6b264c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:38:19.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3fd24f816c6e8d82f8ed91e92ec62474560ae624b28c7ba70284e33f7ec39bab","measurement_key":"aaa940a7f8244e7410e8720395ccfa8308c3c18dfd077dcfbc8b3164004393ef","metric":"mean_score","protocol_fingerprint":"bbd6f6993516ba2f74604dff73de67057cec18449049bd2a9647e0a7681b6f0c","run_fingerprint":"19393e2990b77f0aa8b8ce7ecfda7e7c400c39839040f007c3999869ccdd66ef","score":19.0,"score_display":"19.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9328fedbf3d1191ecb6de30d6b23d1323f78a3b68b8cdd5ec77f804d1c11f05f","measurement_key":"80b82c113940c30dc3f7dd95713c26701c4585cbb71172a2908130dc1fd8d00d","metric":"accuracy","protocol_fingerprint":"54c0a3462b0354586e63990949d9c5451c781ef12ee6b0a0886548f23f1aaee3","run_fingerprint":"02f37bee68b6ef7bace6be03e07d46d8ac594841ffa32ead246cfa6bab99bd63","score":12.857143,"score_display":"12.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"48089981dc59f3219a5def5e0e003fb716641159e16673c18a65d380ed13a1dc","measurement_key":"816f33c420032d2967c3027a9be16ffd4720ddbeb8fa373c0b25da55898a8e86","metric":"pass_at_1","protocol_fingerprint":"88739783113936c77f12a3e2bfdf8872eca3d657a584a15474bdca234b72bff8","run_fingerprint":"63044f08c99197f6025bf056ef5ab64da147a305b01361e7b0c1a5e2e3dab604","score":62.83185840707964,"score_display":"62.8","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5a8282eec75722526b8f88b92d54db3b91804ec0c2a84bee80fe2397ae867a4b","measurement_key":"af882e505363189266c519c8c879b60786f691fcd7553c68adf7f66a4023ed33","metric":"eci","protocol_fingerprint":"7f7ab96d5526b92002f36322aede653e346e0b9d51045f17b1fbfae1df555c48","run_fingerprint":"2204878ed8cb929916dec849b11de5ed6890fac2ba6eda774be7634af95f294c","score":149.13,"score_display":"149.13","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2f74bd93cdb08957659a5334","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4b23cbf459c122afd40525b98e7f1950be50197fe4ef2d8ac08e4f5b044e2fbb","measurement_key":"040756cc56cb20b2767e31ce78162ad4c505f693ce514cdc6820c241cba50124","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"b672ef2a03c8dd178ee749c191c14cd37184eebdde01297553288af327cf08c1","run_fingerprint":"e70e185b893bb67012e94055968e529b2f4d8fe4fcbcdf5824fe57a18cac0a86","score":17.64,"score_display":"17.6","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_aa69f796458792e2a6955243","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":137,"at":"2026-06-17T02:30:14.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5d498c76d15ee9dfd9a68b1ba7bcfe05ab156764bdf321fb6ebfe746b9723ff1","measurement_key":"e6df6cc2611e70b4804a1729f41b68e72dacb858472c70a1994cb48a6dc563b1","metric":"mean_score","protocol_fingerprint":"95bf319888c76b6e404d381ba4159ef1791db4120bdc0eaeef0f05a4a760f22e","run_fingerprint":"7267468b261301d8d37e7a26718b5abf46d372f73493c66ac7891cfa0e813f9e","score":45.26315789473684,"score_display":"45.3","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":137,"at":"2026-06-17T02:30:14.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5ee40aae447f0fa895b37da6bcf28d7685bbfbe8960f8f129bf79dd270a02507","measurement_key":"6bd4f5cc67f3070a5bbb7889892b02c6bd1a2eb8c85d9ec5cd0f16acc2531a2b","metric":"mean_score","protocol_fingerprint":"3b144d21098efd3c14d0a87584ce1cda445178f5d3330ba826845d01323ddc6c","run_fingerprint":"d6ad453ea1bcc4e8f6a8b755ff7e9c4b110f13a7a6ca2cc9757034eee77a3fb5","score":2.4390243902439024,"score_display":"2.4","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9031b229e2aa568fe6fd792d63c44854e5e6edc9ec1c151ef7ab34ec52f3f70d","measurement_key":"b79d38e09219518233e36a85600b38da6e32a5c799131b802f33766eee6a98fb","metric":"elo","protocol_fingerprint":"435b584b368291ac8d9559b181f365b1ddac7c2e48ed24d78572ecc97340d4d7","run_fingerprint":"cf14937be22d717009930a8acf9d76e28aec0c1d16939dd123b5ab7a90008d43","score":1166.24,"score_display":"1166","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ce32f7ef3f87be6f6a41aae76001f65637752dda876d45f05fcbfbbc77321faf","measurement_key":"9953e0dc24f5ef7dfcb800654b06c8fc0cfa66289ec088dda248d3959c3af59e","metric":"accuracy","protocol_fingerprint":"f751a91ecd23c5b2b2c3c92dca8a7ba18c596d90a35bd4cad13511de7cb85717","run_fingerprint":"ed6f73b9fa1d0dc004528677f833537c0ba71ab75fd7baff0293d654d5065418","score":89.394,"score_display":"89.39","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_1f4bfa5486eb4deec4942449","benchmark_version":"HLE original","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":191,"at":"2026-04-24","last_confirmed_at":"2026-11-01T07:28:22Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"6092406147b9796ef0065ae304dd37ef4fedaed10752880958e00c544e23de4c","measurement_key":"042669cac8b20dcc1a9d335f3d371b690c57f8d36067176f887c6e8b2a57d56d","metric":"accuracy","protocol_fingerprint":"9d79f00315c23bc47d2293c9003ea42de6ca857854c04113ff97996ca36b3878","run_fingerprint":"b4dd9bd2014479d5ebb7c2aebb554c42f342c22bb4d5ff2ba7cc81440ae450b6","score":37.7,"score_display":"37.7","source":{"id":"deepseek-v4-pro-card","name":"DeepSeek · V4 Pro 0813 Model Card","url":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"},"source_authority_tier":"B","split_or_window":"provider-report-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_79ec886ae22fa1df9c9fd7c2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7529945ab9a2a65c59708ee287cf3de7837623d69677a1b92450bbbbfb67250e","measurement_key":"aedf0b0500d04c4f388bae78ef10802b39ac6a53c96c5df8dc677d076ba89673","metric":"accuracy","protocol_fingerprint":"a174714c0c02664b3978f4ef91c041cb4ccea658046754a3e785e15abc4b8e91","run_fingerprint":"4e434f129c7bab7dd1ca8b5bd1679b936f5c34d5ec7514bf0c3117b0d1a2cea4","score":37.534754,"score_display":"37.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1d5a6736128d08d1295fb397e9ebb37ee57cb0c83f9f4ab94d697914c6add77c","measurement_key":"a0222f71820a72bbe7dc8f03ef1fe817dbc522051732192e9cc6beee19d26b2d","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"e6055b2b9693f472f3627928d741fa26ac948235ffbf4780f370302dbd283d58","score":71.57225000000001,"score_display":"71.57","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_192f474c0dccc604e621ccf3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"45959b6255b787685f29e2cf4f0cf7e8ea027eaa402a12f7a756d1d3bc568072","measurement_key":"e9bf123e08db47586874aaf37d25036c98d29829aa7654b48ad89afc449052a4","metric":"pass_at_1","protocol_fingerprint":"99a7e6922848de92555c58cd110fa72d016709410b5154ee4f0a5791f27c684e","run_fingerprint":"29fb92e122606de2bbf54784464c16f3ebefe5853c47356d9bc5506b616d1e61","score":87.484,"score_display":"87.5","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"73044192c7015368816827af04b1a20abb5e4848ad16c047ad9335d3565123a6","measurement_key":"3159066434ecd8e9a223614c1f16a3e183b2427ecd6372ceb164427462056823","metric":"accuracy","protocol_fingerprint":"38d09e0ec2ce46b7cbfd13c64d55be7fed3197482a5e4956d986d206031288cd","run_fingerprint":"59059c456fbb5cd9409a98bf884b69f291c50e88fe30505f385cf84c3bc070ad","score":87.249,"score_display":"87.2","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":137,"at":"2026-06-17T00:34:52.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e5928266f7852511312d473b0809883fa143bb415f2201e3d8a3265542756aae","measurement_key":"12d1e4ac9b4fd7d72b91506bc50743779372b3e8748fec30223f31e3b161ae6e","metric":"mean_score","protocol_fingerprint":"de87d7ac7927a21c72e918946bc37f3a2db2ead14e8fdf928a8d6809fe55339e","run_fingerprint":"04c1162edd8bed35b4e2ca363e830ff8cc6a1e54b7e79a0991d8428307d7a1bd","score":96.66666666666667,"score_display":"96.7","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"19a9f8c9c6afa70310be080bc6c8253cf3d2fb027a04ff520305256e2e139222","measurement_key":"bcfd6840cb31a18b3562517b3f7da2c48fc035ecb16736d135c6256f9b16c9b6","metric":"fully_resolved_rate","protocol_fingerprint":"fa377c070d5b851d90b06fc661f87949b0c8129e7750e2f1b2aafe78dfd9e7b8","run_fingerprint":"f266f6c8bef5cf1115f981b504d0c25513cf13581a1683df1188f795281acf54","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:47:54Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"966ea5cc387ba7722e42b7bbfc6d1f197d52c5d351d87d74f9287d584bc0364b","measurement_key":"2757c8779645ac56cb83c203ba2aae546f17f19918d15bc9a88b82513ae6d1e9","metric":"subproblem_accuracy","protocol_fingerprint":"0746c2a76e3dea8e9a4ba6d60699960731fdae218c6d5df46786a9a55f76fb04","run_fingerprint":"70ed966d0b47868295d781f38ab1385f0453472a57cc2e6e1dec129e40222ae8","score":50.0,"score_display":"50.0","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:30:29.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7e1baf3bd6de10d7bb7953a2301e50eae6c74fb7602e3eb090aefeb04067a182","measurement_key":"84b5dcc8233b70efd301ce861fa13a6efc5cc3a6ecb6ce03dbf892e4eaf1b95f","metric":"accuracy","protocol_fingerprint":"e6b53f7246e0f1d6038e6ea750f2d839e2dc7c2c8caaff3af680b5977c371cec","run_fingerprint":"2f1b468b12ae6f27ab66888d88e25a81821f70618efbd4cdd32aadafdd3c025e","score":46.9939879759519,"score_display":"47.0","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"skillsbench":{"benchmark_release_id":"release_093b45b8b752b3f08534f6ee","benchmark_version":"v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":138,"at":"2026-06-16","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6d93ddb784e357cd7fa697985209bd1de059491dc5861e01d620343c9675031b","measurement_key":"e3440dc7b7f60fbb0739790836a55f93980b41b8d10238a6727b4cc74742b4c7","metric":"pass_rate","protocol_fingerprint":"c2ed2025e534826e5e627446f4493a128269710491b35eb2122abbaf19d56304","run_fingerprint":"4602c43769bc08a8edefac7db918794494f31dc3f20c90be2c2a4a57ef633c97","score":50.1,"score_display":"50.1","source":{"id":"skillsbench","name":"SkillsBench v1.1","url":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json"},"source_authority_tier":"A","split_or_window":"official-87-tasks-with-skills","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1710bb809c3113ebff53f7d3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b3c879f19b1e2f8edf6ba0ce601052bdcc55d5aa10a592c16512aed2786e98af","measurement_key":"ee73f25dc1a460de1ba2df42d1eb165e79b17987279ef8d2da7cf34068e2b744","metric":"resolved_rate","protocol_fingerprint":"14260fb5f15d155695a133e4901b2b4c82e4066f6fe3ef5402847374213ea6f1","run_fingerprint":"e0a1f5d3fc83df22efcfc6d56efb48f70cc5b118ac32e938f6708d223fad31b2","score":77.4,"score_display":"77.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b3c879f19b1e2f8edf6ba0ce601052bdcc55d5aa10a592c16512aed2786e98af","measurement_key":"ee73f25dc1a460de1ba2df42d1eb165e79b17987279ef8d2da7cf34068e2b744","metric":"resolved_rate","protocol_fingerprint":"14260fb5f15d155695a133e4901b2b4c82e4066f6fe3ef5402847374213ea6f1","reporting_origin":"organizer","run_fingerprint":"e0a1f5d3fc83df22efcfc6d56efb48f70cc5b118ac32e938f6708d223fad31b2","score":77.4,"score_display":"77.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2a386f936fb7e907b8d80ef4a5670300edfd682c732d9ce28fc756773e7bf775","measurement_key":"2fc6762f386397ba4f96b9a2284bcbad7b3c909722e25a4ad092e7143ba3b4a6","metric":"resolved_rate","protocol_fingerprint":"7e4a46183c41dd422edc5787a41225794e91e14e6c1831d24d9ddfe3a73ac2e3","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-05-15/2026-07-01":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2a386f936fb7e907b8d80ef4a5670300edfd682c732d9ce28fc756773e7bf775","measurement_key":"2fc6762f386397ba4f96b9a2284bcbad7b3c909722e25a4ad092e7143ba3b4a6","metric":"resolved_rate","protocol_fingerprint":"7e4a46183c41dd422edc5787a41225794e91e14e6c1831d24d9ddfe3a73ac2e3","run_fingerprint":"f70282efdf208348c11971aac7b8650fa97d785918364c8b52db641895467dc0","score":40.18018018018018,"score_display":"40.18","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_c5963039dee3d753db6b264c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"f70282efdf208348c11971aac7b8650fa97d785918364c8b52db641895467dc0","score":40.18018018018018,"score_display":"40.18","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_c5963039dee3d753db6b264c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"98f9968940241b55f8eedd4754d045445fbfc60e4d58af80570946cf8aa9dfa0","measurement_key":"45ecec60bf27e537f9bf426a799ac738eea7ddcf93ee2812e22ffef762f2121e","metric":"pass_at_1","protocol_fingerprint":"7fd2ad946ee97973206f8f5078309493d26dbf48bc1a656bfe529d9b14c6ecec","run_fingerprint":"a82b480f9072654d60a7ab5212f556a571f4db61cebef3d5eed163a646c6eaa3","score":30.103093,"score_display":"30.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0011f83722e8b526bb4285b89e0afb0134834b308c1610e18b622ba1de94a7f0","measurement_key":"4b4f2321145f8451ce21040b137af62d450ce51b7a9cb496aafb3bf13352c8ec","metric":"accuracy","protocol_fingerprint":"fd9857580e7684a852b9c4cd51d7cf1024c6324c5ed457af01e971c180aad987","run_fingerprint":"0a3402a0f6af39ceb131ef763d91a8e4fa15ca942b548a40b22aaeda2a5cfde1","score":50.187,"score_display":"50.2","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_085955b3c249b60f983db38c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8b0222c8bc7b81d438625a919333990cd7b5a545dbe21f96bf618f06bcb75ac1","measurement_key":"77fb90b5a38b15f0636581d01dc6c1acd68f8304d1dbc13dd350f783e19ddc3d","metric":"accuracy","protocol_fingerprint":"fc6138e4c585334d03cfb04ee059f981bbc0467a0884a073890c9de7f15f32b6","run_fingerprint":"c9b25b7071fb69fb1a5e589154365b2c294006149e72477019670b6f7ebcad6f","score":11.111,"score_display":"11.1","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3bd11c7987f61d18e5ed6fd57891ccf438c443e60af1edaab578a748646f7c3d","measurement_key":"e8b5b91fd278009560ec1d066251e4d224c890d7c4ac8e639f1abe5bd82c713b","metric":"mean_final_balance_usd","protocol_fingerprint":"be87d9ad247a6773fa090746ce641b5caf524039d2caa36fb2af7b17aa7b965b","run_fingerprint":"2932defaf40c34eef689e18801fcb5ca16646cdfae5054b7744f9e9181678b85","score":3284.519999999999,"score_display":"3284.52","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1408cbe9e98576abb4a0f36e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"63416ed09fa4a0b3d63623c9d1d8dfb362fd429b971810107ea35ee429b26ec9","measurement_key":"bc909c8e55745f18008d7bb0f97216cb01e33283c39d156dd20db108e0f0096f","metric":"score","protocol_fingerprint":"942c7679ebe94cd311c86e129f5045cb9879022d3505ad0ae74d6cd0fa6519f8","run_fingerprint":"6e95e1cfe0df0e5b2b1f971fb37f98356ef4c480f00cf5fb312bbdebc9c47d79","score":49.931,"score_display":"49.9","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8a97a60584d9e099541d1c21dced8c851ee8e62a20456c77a93970228b8dab3b","measurement_key":"2da45cbe02e9b0e43f439d210b339f561478e4b9bc7defafdfed7a4372064072","metric":"arena_score","protocol_fingerprint":"c555068f83103a9aaf1a353989816e340d859d20148171139425022f65c86c30","run_fingerprint":"59932cb9d4bef9a4bf8f1a63177b8db5e64a9fec4ded54261c058a6263eb1fc6","score":1464.190999873057,"score_display":"1464","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_c5963039dee3d753db6b264c","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"41e02799184ddbdcce60f6068ce4130a9aa9b4fbfb8c3fe6e626cdf408a971d3","measurement_key":"b75f97d76b2e6965cafb1daaa0dbd0c331eaa649bf507e4adf3d3d1b324dd2d2","metric":"accuracy","protocol_fingerprint":"db710865a7051263576e4aa65d3c94cd9cd42c3f47757dfe56df0f4fd5301319","run_fingerprint":"d69ed27d90c386a632d3811ca87a57a82a4a683d2b69409b614657b008ed06e8","score":48.9,"score_display":"48.9","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_27a543e4d8b8c6f237f312c1","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"deepseek/deepseek-v4-pro","model_name":"DeepSeek V4 Pro (2026-04-22)","parameter_count_active":49000000000,"parameter_count_total":1600000000000,"provider":"DeepSeek","selection_rank":59,"weights_status":"open"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f6e807753d0c38cbce9c0c2e475396c4141ec089bc3ed4aae1cb4be42039b635","measurement_key":"6ae113e76a8db6a5952695e501e7026729f0e6771da459f9b32316a4fa96ea5c","metric":"index_score","protocol_fingerprint":"763dc2c67f30ae1fb4f6c1d6563d0879ee56ae53b6b28a9d8f46dbd865868fea","run_fingerprint":"a77d97ae423dd92b8ce3b8fae56271439d651eb6e692e68b37e856e05d6eb68a","score":29.889783,"score_display":"29.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ad5c4858e74f428a0183b9f8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:15Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"df1260bfe99cdbf3f116d236deb5ebae08add0a5baa611204b12bef6848c9ac6","measurement_key":"355e94625c0b49388fd75841e5d236f90d85b274acf9790cb04f05e2a4df5236","metric":"performance_rating","protocol_fingerprint":"a2b4cf473ec5223f4c0d0825b827ef697896485033d1a8d5ca4ade9bdb96770e","run_fingerprint":"0f2fbbdf3694d6dfa734632063b5b39d7dd6ed5b4e78f700b9ef6dc6ce620afd","score":1158.1,"score_display":"1158.10","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e0935f7f898ad2b33c5be391","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":12,"at":"2026-10-19T22:24:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f31f22c684091971402ba31bd9d4a0b19ab4347490541c5e8b5600d492df96f6","measurement_key":"0e2410f435cd29e55a6891bb9799c81047800c6698183ae8e1bd1e39b576f405","metric":"pass_at_1","protocol_fingerprint":"a467ee58ec0fb95e7179d89e476f72b01cd22c60b3880acf04ff963bff40cef1","run_fingerprint":"267297a74c1db7d07e589fada82c1eec492ba30767387c0d733a6c83e96fcfd9","score":54.400000000000006,"score_display":"54.4","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3d1d8a68b3013e79d3d50a58","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ef434dcdbf7d9a19ec238641f8092b607a9b029296324b8978d75fe71dfe2750","measurement_key":"4e15c3d3d939835102bf532e773185b87e8c293d9322c399f36fbe85e9a1ceee","metric":"ips_score","protocol_fingerprint":"08cc136206cb6cb8a231ee320a7bdc747e451bc1013f7a33ccdb1b2a5626b343","run_fingerprint":"34b097b5f9b54228a8d53780f73a7bc7fcc56ef78c39b794a3a152cef7b628d6","score":0.027705996772957868,"score_display":"0.0277","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fa699564a69ec0aaebf7c223","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4fa1bcfd69d69cb9a1e51325a9a2ceb5bd4204f478c076342a695208c799427d","measurement_key":"39771b9afe460b90fa081eab0e6a49d4546956e3108218c1996c2fbabb271cca","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"3d0e798658e463ac5e83af7354c74e81c1b4da446babe17992b887e0100cf5dc","score":1479.6978910104858,"score_display":"1480","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_95f69c97aa4a1cec75c671d7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"faa6312d3ef1b6699ef3c0fb8ca44dda523f2c3183b46d677ae0e86d137a3538","measurement_key":"7e77f6c7f4b69e8ca19f32529ecb041d124d8d42694030598674256546f259d8","metric":"accuracy","protocol_fingerprint":"d9e8f6e4576dcbcd1b00c9e181cea4a25fc15c1618e0a9dcd4d2a309a854c86e","run_fingerprint":"91f3d77004647978016516f20645f485f73ae85284256881ce74df625f230525","score":26.5714285714286,"score_display":"26.6","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a6d859a7de2c648262173a51","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2b5a2b7e76f9d6a28feee5762bd6007c7253920ea380e8459df6b6f628e98967","measurement_key":"e5d6473d6b796e97102bbfd2a698e5fa096f69c2dd5c230bf2c081f6f8fa3b13","metric":"elo","protocol_fingerprint":"9fc9b7c83607a970df00b9e96439369804698984fe008f5d709cdbeb984709a9","run_fingerprint":"760f3e57e4ab04d90cabcd308237af9162251cee2e15f52bcf64d61582a12525","score":1689.4,"score_display":"1689","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ad5c4858e74f428a0183b9f8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-09-30T18:53:23Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a8db1e011bf77aa7528ad65873cf479626d03cca881be29586c42b397ca0bc49","measurement_key":"81dd2909638b79683ad9902b9db2a73a42ff9622ec0db17f441e8fd09f09d13d","metric":"accuracy","protocol_fingerprint":"117ce075587de96ffde64dcc0c76c0833d042aa82584ba6a8126b118e3d66729","run_fingerprint":"1bd7f678e402064210c5db38ed83757f90fb994c45025a7e0f1cd9b087bb3e48","score":49.351251,"score_display":"49.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ad5c4858e74f428a0183b9f8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"38d89956aa04b38b95ac91c4e3c71e06000ec2b915589a80ef7e64ce1fbcd130","measurement_key":"1520510d0bc5691e96ae4ebc7b640ebf18a9ae391d9a8563f2ad2089803808bb","metric":"score","protocol_fingerprint":"02bdf6e671f2215b6850a4bd42453f8262c954b2b71ffd01dfcd81344c0fc538","run_fingerprint":"d334ad93d4e46a5c70fd5a80ff69aeac6d021db6069e4a475488050502cdfb8f","score":39.333,"score_display":"39.3","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9371c32d8313eb1b572415d4","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"912387123238d36eba8113367fcdb3b2d4f2d9278fdcef4157ca57b1547c79de","measurement_key":"7b7b8c8b2139cf0652b349a2fa961815b8072bb3aee7f635ca5930757c43f261","metric":"fully_resolved_rate","protocol_fingerprint":"4963cfa30d7a2b41636db35e8b58dbe7462166ab617ee219f9baa95b3752f571","run_fingerprint":"5921ca50ad5bffa49dc437426d41de92d8fa9666cdfdb46306dcdc47caf096ba","score":0.5,"score_display":"0.5","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a4af681ed9f15751db717d43","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d05316dc1f55a472eab87bf527cee060c4ba853ff62c5f33e16b3dd3ba33dcc1","measurement_key":"ea28cd4ebf00ba8336984770558ca23c4dcec68fed9957ffcaa91789bf8868c4","metric":"subproblem_accuracy","protocol_fingerprint":"1f06c1b7534c2fb7fccc428717b63eef3e18954e9a35b0f1a1ba9305a2e9434b","run_fingerprint":"72765083df296b6b5fa7bc26e4b995b976e9ab9a462d8a33fe47bdf848939df2","score":60.8796296296296,"score_display":"60.9","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6130f112650f283957c33de0","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4e7fa7412a8038632d762711da90f627da26278faec9ac2add3078ffd04134b3","measurement_key":"9acfbff0a97781c9b19baba4e31159399ea17ceb65486e100a5bddca21950b74","metric":"fully_solved_rate","protocol_fingerprint":"5932620a3562e6c15642c8cd0631f76dc739a777aee0cd6f8a3a473b4f5db66e","run_fingerprint":"1ce16da4a13f5017153d0fb9580ef23f500b602218669d9cb734c58951dc8754","score":3.053,"score_display":"3.1","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ddb840c99baf1533c559c1ff","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2bfd61316c3571c1465fd73c474ead0526521f32168e9810f12e95e0ebe8f746","measurement_key":"4f659f16577d94f2a4d9d93755633d99d2c25ce6ae4f82a6bc3de2febfd21c52","metric":"accuracy","protocol_fingerprint":"209c2dec022ebd3237bcf27b87aa0e21c2a2734c519a2693164ca1994e3f1e3a","run_fingerprint":"a535fdefa8dbce5dbdbae78ec0d731c1c80f27fb31ae24c2d035936ee60657da","score":67.79,"score_display":"67.8","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_83ef76f94df553775bdb50c2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3e31e08e5a78ec4e54eb38d2c34c039ac0ad66832e3cb28a03dbad7ed650ab43","measurement_key":"a7dac2c7c8eb0d54cba76eb5fca2af0bc5ef85cd1d5f77b5f2d78dddd69048c4","metric":"accuracy","protocol_fingerprint":"8d0311088fc5cfb8bdeb11e0132152946e19626dc01e66af42f6fb613a220a97","run_fingerprint":"e8ea449e622f01116eb55995fedff35f2fa052bbb6365a90accc9029b7fdc0fc","score":31.313,"score_display":"31.3","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_cf49abb6dc20240b5e194172","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2324bbf56bf5f5ed764c8d52ad3bb18defaa2ac03abbe1a68150d60b2cb4844d","measurement_key":"c475566b94fc1520612a82ec343cf1cf96c309aa6172c6870c1df36854482424","metric":"accuracy","protocol_fingerprint":"986b2f8ce1ae7e2e588355a186edbae80339671019098dd79eb65d244ca707ec","run_fingerprint":"68a1426a1962b935654dc641b44caa05687b5db853530d156c990836546aff80","score":2.857,"score_display":"2.9","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_456c16d235a741750dce26b6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1d4b85595546420fe29f1cd7feee1746b14417dc47167226df7a7a7297edc9d9","measurement_key":"3ee10a142e66cb281461b8321a5060dcf6156569dce6aa8e52b3ad00753af55f","metric":"score","protocol_fingerprint":"7ecc126394a88bb0d462beb53f3a33dd51f9e121920c738b67cd8db108dbdbb8","run_fingerprint":"4b6160935bd56912bbfb9ca408dfc259ae5e363e709089f69933111ff451549b","score":85.223,"score_display":"85.2","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7c73c8831eb69ca88b4cc5e8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f6b2784520c40a28801846d80f67bcd087a712659582293aea8356ce37340137","measurement_key":"5eed57216b298ed3f5954aaefd5c9dc90ad67b0cb7bb6bb0ba5bfc7f19b3e75d","metric":"arena_score","protocol_fingerprint":"a346f712942c25f31078e2be54957a4c00fe8b0835f63f7b22147453f63d5428","run_fingerprint":"035c38ce4db4e292125845ffed1760a256f872e5dfde732d31380f5f0ca81a51","score":1625.417548626546,"score_display":"1625","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_aeabb9ac695c1ca1e41af8b9","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"xiaomi/mimo-v2-6-pro","model_name":"MiMo V2.6 Pro","parameter_count_active":null,"parameter_count_total":null,"provider":"Xiaomi","selection_rank":60,"weights_status":"open"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3c52bce955573f887851e9b72cb2a5a2e651336fa8e07c2ae07d3025344c7610","measurement_key":"50b5ab68c7806eebcb9765bd1038ece34d6417150385134012e9a2a57fef204a","metric":"index_score","protocol_fingerprint":"94615ddece2f787acdf0a8cf1e4adca2824db332a896625bd695b6c8497dff37","run_fingerprint":"03f3992a23a8baf2a82b49b6fef371f93ae0061dd4404ff523c541f8adfa8645","score":18.728908,"score_display":"18.7","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_18bf23dd51a56ac5e133a7c1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"67c15862877cc04e1b5cbe8acdda3a9c352f7cc04c68a2edd1355a92f74c0f1b","measurement_key":"15abae20ed6df5f3a98125da927ceac2ac352043148ced0000da2107626f6a23","metric":"performance_rating","protocol_fingerprint":"8b1229a65e9d84d7833714acd10b9efea2d02da2e4034328743cfdc9dbfc1d64","run_fingerprint":"d26a00ca5590786437bfdf24453df124e479a92f836fe8a85a9d44ef494d95dc","score":640.02,"score_display":"640.02","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_bb51e947973ce8b8932407ec","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"303fd0f4d930e6a70da71875a708a3c9039d231c30e37451ac0e0830bb3a498f","measurement_key":"1ec3852b6e5d9c61d3e4791ae813112665764ad833569701efacfc1048afbec6","metric":"pass_at_1","protocol_fingerprint":"d47ccfdf0d6ac215be0ca50fcd3c33ad4faefaa3c8de942ecc63915ed8ffd39e","run_fingerprint":"e13272da54a4d290673b0ea40a7a0301d89d171a187ae71d42fce271e1142936","score":37.7,"score_display":"37.7","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_53416c63888b302d0224ceb0","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"018e01bc73fc3787b08f7601fd500872a6d36067abaf3f173bbda841c96dd8a3","measurement_key":"471eede1171dd92e898a2f34a768702870291faa93ecf04dbba832ecc075202a","metric":"ips_score","protocol_fingerprint":"3f170e27244e2f1ca1729f0584582ba73dee3add65a2555309ff41f8c60edc56","run_fingerprint":"8e76dfc0a51a83e98f6f9555077b683c81debc5c1cb7fcdee0bc0abd233d8676","score":-0.10161684431257027,"score_display":"-0.1016","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b5748244f086cfcc6a37e5d2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"71a16bb10468300259049c51fd615f9a1cbd727be37b79d5e458f386336bea42","measurement_key":"0c0094781642925c1238aca5bd445dbcc492ffaf06b177497c1ee39b77410632","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"c8f535b37f5f30c3deb24d1217e50645a5205c67c092859c0139bd6becffa0bc","score":1439.2396535610842,"score_display":"1439","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ab1b92201926a7b0c5c81541","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:44:41.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2303aa1ff0dd43ee4b1fdb30e4fa5564410c9befc0d489f184f3c118f95418ed","measurement_key":"1c1039fd0f961ad53ef56f6f9dce3620fe6b10353f4a51df04746b5533b2626c","metric":"mean_score","protocol_fingerprint":"074464460b8ed4ba876fa15519cf3ef09d6b8fd3c599c005f425e28ec58a3145","run_fingerprint":"817f69e16a1d5d62146b719e6e4eb080f0ef1f82123d9be930c6846747f558cf","score":7.000000000000001,"score_display":"7.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_e15386937757ec3e2088b88f","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"26ebfc4a0293e189cb421c54edc42a220dfacd547ba8af7a8fe74050c33e84e0","measurement_key":"fc4602af3d27c6a389cbb44885fd91d2fd1a524cc39a7171d39c8ee31afca228","metric":"accuracy","protocol_fingerprint":"acd39e2ee82d0f5134f524acd25abcad1cb1d2e4980790f737057dc3f6759f54","run_fingerprint":"61cf861e03d3e4312e23ef492721a287b1513d7ef31c00d252fe09c4a0dd6af2","score":3.714286,"score_display":"3.7","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_18bf23dd51a56ac5e133a7c1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"926d6523f18fbdbd3a9c5d3fa35333a6aed94711319c751af9b9e3b7ef131347","measurement_key":"fe719ee9d2ee823c71e66ad2a720b53057cdf04b561b5843d797bff21ad8696a","metric":"eci","protocol_fingerprint":"74266ae747b3a0ae4e58b29d996911803a428a9206c19520222fd35081db9efa","run_fingerprint":"807f6eaf15ea3aef9240285014994590fcb10a36b9d5799985b0a29f219b7170","score":146.92,"score_display":"146.92","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a112784282b9946d07ab8413","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fe4e1b52f686213cacf8642bbd44f73431baf83d3ec95982458fdc354aaf3523","measurement_key":"c9f52dfdb57f87b785b1801fdf8218bdd55fcd47aad01872a40254394f8b7bb3","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"22dbfe3fc083c8b5919e05121ea8327563fbfacbe07253034fcbf3f801d471a2","run_fingerprint":"befb1c49ab8de3856e086add7cd7937f20c7841a05ae81ef2d62b2a48bfd1bf8","score":14.7,"score_display":"14.7","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_e15386937757ec3e2088b88f","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ed6fe6a45d533f61175e49891805a66a3466e4846e81213ff5d3dd8ec065aaad","measurement_key":"d134c49dd9bfb026b8235454316d816e1b24870aaf9db3d986856920317da7a3","metric":"elo","protocol_fingerprint":"7965dff76749559df20e3509d2bf6e54f959c520febe774b2aa356e982abc5a2","run_fingerprint":"c40203704d883048d9cf584caf0c98e08246b17b727d908874c22cb9fd24e46c","score":1249.95,"score_display":"1250","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_18bf23dd51a56ac5e133a7c1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2c356de3dd532c1c14b951b713e231b204910cbf082a24e7212927d3944f8669","measurement_key":"16c290b691f9727ca336cd7a60dfffc5545f89f8ac272277eb233b933d06e7ba","metric":"accuracy","protocol_fingerprint":"1b15d9cd60eee77accada1992be5cbb948f8802854924763ee21b54e02ddc26f","run_fingerprint":"1a921d2a9386ae169630fd197fa644712a1dc3a1ecbedbb26c6c953f15e2588a","score":92.676,"score_display":"92.68","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6a5ac3a55dc02af104cdb177","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2923ad267069cf57704fb4d7d106248a37a4e681f2b6c335b0ccb204bcf32199","measurement_key":"a83b6a610b6c157f4e16e3f4f7640537e31acf48db31a0e5bff32411a1ee7754","metric":"accuracy","protocol_fingerprint":"80ca7e79dd41fa96e23232818dd5902735c42906292664f7177edaf240580de7","run_fingerprint":"fc2fed03130b8fc7f91310105a18424d36ed8f8a539f338f7ffe17125c8c2563","score":38.97127,"score_display":"39.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_18bf23dd51a56ac5e133a7c1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"60fb50acd5b1359541e0caa383e86da6128c9dcca2c4562328917426e814e01c","measurement_key":"c2474abe7994923851a97210d6a356a2889b3fe680f4ba8748312acc84cc5b17","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"928c7fe84c4b07770e556c22703d6674690d1ae9de1c3de82d5907eb8db4cc98","score":67.25676190476189,"score_display":"67.26","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3197178f18af61acd90327e5","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bb19223f206e3e728b21e8cf2187afdab2f1572fafb40afa00498bf7f5a10bee","measurement_key":"0b9ac90fcb0554971146a0a664c58e2d56315939ea39a09412c1f34e2525f5af","metric":"pass_at_1","protocol_fingerprint":"b841660719bf18b04a6287c32f9cb5f406460b672b26c7f614d6c01c7c546f22","run_fingerprint":"23c09023a043c2c8adb9480b0c1ecba4f6b21ec128531b80038e266a73893abd","score":82.154,"score_display":"82.2","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ef51fefcba684ed7611f3d0c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_4873e5f09254ceba3d71ac2e","benchmark_version":"MCP-Atlas Public Set","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":153,"at":"2026-06-01","last_confirmed_at":"2026-11-01T07:28:22Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"35c45af3cf8f52f9ebb0da9f18dbf2c64a2c55bedbd0089f45af09c14e12b643","measurement_key":"dc5fbcd963302426ed2095a51b956f7860c78a426a7429475483afbb71e12eca","metric":"accuracy","protocol_fingerprint":"e053c3facbfcfe53f448c08c4ad0fe3a017da18caa4fcf1bf742d31d3777a4df","run_fingerprint":"9ea4c8ec00c3440e32a090e84d5a316630d9aa766dd6b083f2938641a9b6f7ff","score":74.2,"score_display":"74.2","source":{"id":"minimax-m3-report","name":"MiniMax · M3 launch report","url":"https://www.minimax.io/blog/minimax-m3"},"source_authority_tier":"B","split_or_window":"provider-official-code-public-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_eb4c46e38e87a4548c65dc96","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b68626b38cb39712c215197d1dba8fe21485054967ad06dd67966f5a19f4dc9c","measurement_key":"409e18603b833f2973b72aded57d6dd35eb14e440a8640ae5b85e2420738e719","metric":"accuracy","protocol_fingerprint":"68c3183d6b5d2374a63aa8392e3467e90f39614ebd12ac078518b4263bf7cbb8","run_fingerprint":"a9b67669dd69c010c1b37df413981759e49768c6356634d53f0ec6124dd93494","score":84.22,"score_display":"84.2","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b30a7dc7d7d151c591b300b0","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9bc442fffb8cd80a576775afcc67b250c4e25ff6a64f6089862cc2d54d03a490","measurement_key":"52df72c4b0677288b476c99d94088a3d5a6bc53fadf2ea3daba1896e4c68c047","metric":"accuracy","protocol_fingerprint":"9c002f8540b8a0f6922c6c41e68c2963a44e94eab38d84e8b5bbd4abb56a3dc2","run_fingerprint":"a633804e6f197472abb1bfc49fa5af38c48ec3c9e70855f2e25176c61e41bf90","score":81.156,"score_display":"81.2","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d535e0c60ed655f9066eb7da","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"osworld-2":{"benchmark_release_id":"release_15c5525fe39f33bc181dfb69","benchmark_version":"OSWorld 2.0 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:06Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"93a2a73d52faa1fcd519ccac761dc837cac95adddf497e738584ecc943322cd7","measurement_key":"c03b1ca038283967e98979b3e4f52bad6ec18e1978aad1abcdf65dfa47087dab","metric":"binary_accuracy","protocol_fingerprint":"fa4b66d5a1199a067fe5b1925d4b19605dfcddffa329b61b71c74d6d20670efc","run_fingerprint":"05192f1dc3fcd0ecb7159fdb9f4ed6e425319513a4f247cc61929de333ba8e5e","score":4.6,"score_display":"4.6","source":{"id":"epoch-osworld-2","name":"Epoch AI mirror · OSWorld 2.0","url":"https://epoch.ai/benchmarks/osworld-2"},"source_authority_tier":"B","split_or_window":"binary-accuracy-500-step-budget","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_91769ced1b80cf6db8086b91","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":82,"at":"2026-08-10T17:46:50.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2d1879e2b2a4710c88a90963c4af6bba1efeb3267193cfadce3330e15508f96c","measurement_key":"314ac30c5d4d69d55a34f998688f8c5e1ffbaa93e30b5ffdfc659bc1505e7aa0","metric":"mean_score","protocol_fingerprint":"217614212a82bf56f939040ce2555be0306ce9ff38db111469c28fc88105ccf7","run_fingerprint":"dd2463cda6a0b929188064149fa18d987669ba54708a160ad626f32b461acbbd","score":26.666666666666668,"score_display":"26.7","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_e15386937757ec3e2088b88f","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:15Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ff692fb398b5d2fdb89d52d5153a63ad9e97fd41b0edfb26e230f62faa665a90","measurement_key":"6375adeb1362577cb4248512329ffb7719d68a2f79d1c40739d84e527785c96a","metric":"subproblem_accuracy","protocol_fingerprint":"ef33c85a77b01f2b6c6767d505eb57e69b4cbf6c39ccdce61e2de8153203dbb2","run_fingerprint":"2749d7e26d79405110b9cafff53ab2531044cfffdd5edb2608c515b514d7a19a","score":47.1064814814815,"score_display":"47.1","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_09b0d8ecd750138e32e398a3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"47175f509793812eb12100bf1e54e8ee9f1209f96e63635bf8a060f53d3d7203","measurement_key":"b441cda6daddb2743e7bdff79d7e86ba91c826e453b9f14fda5e4cae8b007b5f","metric":"accuracy_avg_at_5","protocol_fingerprint":"675ec8382f52f65e03381904418d26e916a0f19bc9b8754d277d20c026700fc7","run_fingerprint":"ac4d6aaaba5e665f4ea3e9803ae8d66d8f422de0dfa3919641803f8e74797384","score":45.8,"score_display":"45.8","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8621ac6c3391417ec3519f00","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"skillsbench":{"benchmark_release_id":"release_093b45b8b752b3f08534f6ee","benchmark_version":"v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":138,"at":"2026-06-16","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"42d0b77222d0d07636ff0449edee1b0ecf9181377d55db26755faa11f290bd09","measurement_key":"1b71214a48398ed7f951b1363c63ebc859195b1ed924c66ec5c49dfdfba75fec","metric":"pass_rate","protocol_fingerprint":"c2ed2025e534826e5e627446f4493a128269710491b35eb2122abbaf19d56304","run_fingerprint":"a00f5a464fa7216792c4963634252e872ba0655a026193ceb678b311a2241752","score":53.0,"score_display":"53.0","source":{"id":"skillsbench","name":"SkillsBench v1.1","url":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json"},"source_authority_tier":"A","split_or_window":"official-87-tasks-with-skills","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_09be712f9836bbf7d088767a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":152,"at":"2026-06-02","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ffd246b1b2075ceae84c43285a7d423faf621c6f76dc7719748a22bda5eabee4","measurement_key":"f3c15a6d2753a3940e7abcaee219f444b2bcdf7fbf1a8a4d4ff8b37d4caa8359","metric":"resolved_rate","protocol_fingerprint":"6d2ec613055dda82bbdb11ee8ff410a0e5080632eaa5d39de43148dbef744585","run_fingerprint":"47c4b19dbea4b1d07d736c78fe6f247f5f919abc6d904361a9847b7df4589a4f","score":75.0,"score_display":"75.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_02c909f667465bb33109fcad","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":152,"at":"2026-06-02","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ffd246b1b2075ceae84c43285a7d423faf621c6f76dc7719748a22bda5eabee4","measurement_key":"f3c15a6d2753a3940e7abcaee219f444b2bcdf7fbf1a8a4d4ff8b37d4caa8359","metric":"resolved_rate","protocol_fingerprint":"6d2ec613055dda82bbdb11ee8ff410a0e5080632eaa5d39de43148dbef744585","reporting_origin":"organizer","run_fingerprint":"47c4b19dbea4b1d07d736c78fe6f247f5f919abc6d904361a9847b7df4589a4f","score":75.0,"score_display":"75.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_02c909f667465bb33109fcad","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"contamination-risk","conflict":null,"directly_comparable":true,"display_role":"contamination-warning","evidence_grade":"C","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8945dc6dddb53f0ab9024730c0cd81936de3b1c5ba4b3c04f660ed32c8e26ba4","measurement_key":"07d07d9bc575390da4cb9316878bdc7f70a5f3840aadd16882e955ddf3755aca","metric":"resolved_rate","protocol_fingerprint":"9b03de353448bec4c09d54b83315b7951e30c2d8dba467c278068f98a4886798","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-05-15/2026-07-01":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"contamination-risk","conflict":null,"directly_comparable":true,"display_role":"contamination-warning","evidence_grade":"C","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8945dc6dddb53f0ab9024730c0cd81936de3b1c5ba4b3c04f660ed32c8e26ba4","measurement_key":"07d07d9bc575390da4cb9316878bdc7f70a5f3840aadd16882e955ddf3755aca","metric":"resolved_rate","protocol_fingerprint":"9b03de353448bec4c09d54b83315b7951e30c2d8dba467c278068f98a4886798","run_fingerprint":"0a4e559414c29b68877d607a5553e35ebd2551fc5ad5f53dd3ba808cdfc143a6","score":47.207207207207205,"score_display":"47.21","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_da68402d6b49d63678a6cd3c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"},"2026-06-01/2026-07-01":{"benchmark_release_id":"release_8d9de222c7fa49c448653fc0","benchmark_version":"rolling-v2","comparison_lane":"supplemental-post-release-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2d09ca24522f02b1b521f6345c96a34b7c64ecd2a008369a620c5cf4764671f8","measurement_key":"0b927107d98d75d2f860f9ac1c25a0eb7e35267e2d5fba881a86824c130f9608","metric":"resolved_rate","protocol_fingerprint":"d0d9c6e1df1f0683aebf39e74c887fc280d9025e54612c0cc9fa0e3a85e6bd73","run_fingerprint":"264bccba2608f656ea08767961d15b07a044672bd709032331dcd408bd2efdc7","score":43.80952380952382,"score_display":"43.81","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-06-01/2026-07-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_da68402d6b49d63678a6cd3c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"0a4e559414c29b68877d607a5553e35ebd2551fc5ad5f53dd3ba808cdfc143a6","score":47.207207207207205,"score_display":"47.21","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_da68402d6b49d63678a6cd3c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6dec54c4d5cc12f5853aa4f8df893dac34b49887284106f09b93fd9552187c7b","measurement_key":"5fe7d1db2fbaec4694e10a40ebef48b60936b3548a0456bfc6e2991a14678327","metric":"pass_at_1","protocol_fingerprint":"44e9ebc0dbd6a44ba532a659443b94234517f1ab1c44aa3f7b045631243bed0c","run_fingerprint":"3fda36d687a9b98c128b39d065d2523034df8317c52dd03f33afe8b880c76e37","score":15.257732,"score_display":"15.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_18bf23dd51a56ac5e133a7c1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":152,"at":"2026-06-02","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6354f79e98a147a9255d340d725ce2058fc7908465d7e76841c53fcf0a19270a","measurement_key":"dbd483ed4489e7826eb51e5953f767e0c868634889510107f7efcc81bb0046be","metric":"accuracy","protocol_fingerprint":"0fa2a10e03c0b94d9d80bf37b1f554b84b05ef7c9ed5c835ee5f901016d1589c","run_fingerprint":"112f8417e3ee4d113b7629830f152fb1c5635348977b030ed570f2bb7edca495","score":53.558,"score_display":"53.6","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_abbe9505531d90fc1ec94ed9","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2c13dba95b385f5f61d3ee73b77e7c6cd105295c696b2fa1268b65bb52c66afc","measurement_key":"061089bc8f939197b7ee67de0607060adf6e533ea7a4ef513149cdb20715915d","metric":"accuracy","protocol_fingerprint":"b1a5a7559b54b8b256544d9f1317a243cc3e3792ce9dc6ca4c08b3bbce7f8b82","run_fingerprint":"ec78dd4bb452f43f8bda80243799589872a7276a6e0595d15000cb6fc5e577bb","score":1.01,"score_display":"1.0","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c48513ab822d22c8f8ac8b40","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cf75b59424a33c89f6ab48ee0841f64a445af78d74ba2eada08d3ce69f4f78b4","measurement_key":"759e21d9aef82945a1d2b00faae28120e30b114d514b70fc1972653e7e84f9d3","metric":"mean_final_balance_usd","protocol_fingerprint":"de681cc903cad707fbf63a3cf8ceb5e6ebb6489f2344af45c1ea84c947480979","run_fingerprint":"bbdedb5475b983b3b835232476ac4506b7388da4d1abcd6c5c17d9885a0ff086","score":2157.7716666666665,"score_display":"2157.77","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_951eac4e039a4dc0d2cf0bf1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c483088299478f2fc65c3562fb7798d8e6e549443ddd7e42482ca046770f9620","measurement_key":"dc508d2a924909b34f4be92eb11caf25ecb79b309cc60871b57cb97e5f23446b","metric":"score","protocol_fingerprint":"0a74c5185d94396ea711a709d4e9636711650b9d504adb512aa8d35508c2c8bb","run_fingerprint":"c374f2561b35c98dbc219cc222cad2548ad866d912b5b3073ce3bb8b8bfab8f6","score":47.566,"score_display":"47.6","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_20bf9dd5ef508261c42af9c9","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"015e9a5fba37a42436f3fa70d73271219ee58690734a0599f2c16197177bde42","measurement_key":"81dc70749c90f2e2cb7d85d842a95e691324901ea56738ffd01ac9ef7b09e8d5","metric":"arena_score","protocol_fingerprint":"2402163598f231bc3d9df99d4df7b769d77309c8c50f1aa56f9096b9305b2071","run_fingerprint":"5ccbbdc00afd2e219d80993d141e2dc2d2034a6576ae92c0dd91a13234a2816b","score":1483.3051511403955,"score_display":"1483","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_565e2d3f37afb7a4e6e7b33b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"minimax/minimax-m3","model_name":"MiniMax M3","parameter_count_active":null,"parameter_count_total":null,"provider":"MiniMax","selection_rank":61,"weights_status":"unknown"},{"cells":{"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:02Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cbe04502368e748138f2830696bf1f5f7aa79589b66df70cb18cd67fa2018836","measurement_key":"e10ec997bb52fcc74e2edd0bc5605da739e0d6571e18d8c647d047ff314c8c8b","metric":"pass_at_1","protocol_fingerprint":"12016967d2e7faa9938f5f386ee5de7cce5e4efbe5099b2df6614195fc385102","run_fingerprint":"9ba1605e6c3feb4576996a6cd87f208a17a38949430dd4e0fbe6dce884fc4e2b","score":66.1,"score_display":"66.1","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c64279d72fe7e5e71cca36ec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e67d15ca59300b3c1fcc6e405d58bf8c53cf05116c0a3f14fae35cba534de8ce","measurement_key":"62a802b1bfb051780c61527591ce84581d04d33cb1d264de0bf22c1ed75e79aa","metric":"accuracy","protocol_fingerprint":"2fdc53687bd0c3c9e45c0d8be86629a4284fc54de5a01963bf2ca2fe71c844e0","run_fingerprint":"851228a218338a012c66f1babf8a779c06736556cc9fb146d6f98ecfa4f72e54","score":28.2857142857143,"score_display":"28.3","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c64279d72fe7e5e71cca36ec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"cursorbench":{"benchmark_release_id":"release_9acebd5b002e9c3f18a30606","benchmark_version":"CursorBench 4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":12,"at":"2026-10-19T22:24:13Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fb09f5cbd4667218b8d7dd2c2a76d6ddfa1acdb76f46d8c337aff9c8981ba2fd","measurement_key":"b299dee57a34f81e5674c5a7eb34528135062043df0f736919c797f31d5bb599","metric":"score","protocol_fingerprint":"1a4b83a2afdac24df41d745c36ec531d1c186b0988262fb09cd7221a7227996b","run_fingerprint":"35d58bf5ec71b6be183254cb4e4cdf872031da6a9567f0797c0d0bff8e90ee0c","score":50.4,"score_display":"50.4","source":{"id":"epoch-cursorbench","name":"Epoch AI mirror · CursorBench","url":"https://epoch.ai/benchmarks/cursorbench"},"source_authority_tier":"B","split_or_window":"official-current-suite","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c64279d72fe7e5e71cca36ec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":19,"at":"2026-10-12T19:00:20.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a038a6f431f098286f786edea5ff1c0282483f84856464422a834138ab641649","measurement_key":"9fb24fdf0c919dfd2e4c4188d04b6b474e9c00012e6434e5dc2bd6de4872f427","metric":"mean_score","protocol_fingerprint":"865164b37968dc801d2248cd52aae4434263b2b3c813983ccf41c155b2d69f32","run_fingerprint":"e5f4afed9fe2bbee92e5d80c25416f674f31d345440dda576ca9051758dca4f4","score":82.10526315789474,"score_display":"82.1","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c64279d72fe7e5e71cca36ec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":19,"at":"2026-10-13T00:37:05Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cb7f4c13f93776ae59fa3ea1677554414467db5bbfe8424628a49807ef84518f","measurement_key":"0cffb5336718df24cbc7fb8f4f319b7d50e51fd152d8ad1c419490e0f30ca678","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"309069d2c1db92bb0dcd099f160618e75970d3f7daee444913eb2282a82831a7","score":81.15589285714285,"score_display":"81.16","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c64279d72fe7e5e71cca36ec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"mirrorcode":{"benchmark_release_id":"release_07bf24088c0805f7b6df7a88","benchmark_version":"ML +Private 2L","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":17,"at":"2026-10-14T15:05:06.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b890cfb76fd11a0b9088fd52def87f22bb6d538908342594b9b6f0b79d02b9ca","measurement_key":"481a202aa5cd14f3f0b1ffa9447c750dc7156e17a638603b0977b8211851d4e4","metric":"mean_score","protocol_fingerprint":"f33a4a2ed881566d0ec3a163b5c816bc31b172e3871656ddba3fc6d53797cf84","run_fingerprint":"11820b02a1bac776eb351015e6433e3bea83aec8323fe8d5f7a4b3eadcfdd464","score":45.55555555555556,"score_display":"45.6","source":{"id":"epoch-mirrorcode","name":"Epoch AI · MirrorCode","url":"https://epoch.ai/benchmarks/mirrorcode"},"source_authority_tier":"A","split_or_window":"15-programs-30-language-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c64279d72fe7e5e71cca36ec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":19,"at":"2026-10-12T19:00:20.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"94de55866ae5b7dc2b9ece154021e0812c92cc8d21e02ba03e7a5c0427464495","measurement_key":"2edee3b0730b374b904e205620fc8bf86c69068b6c12e1ccb247e2fc30534fc0","metric":"mean_score","protocol_fingerprint":"c5e8afe0b262bb13161157a37bf4215e1df3d12bb5c25ca08444f51bc477b669","run_fingerprint":"25fc4b7f006372b4879363f1c0a2ca97ab4629bc65e7a9d62256581af3d425df","score":99.44444444444444,"score_display":"99.4","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c64279d72fe7e5e71cca36ec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ca1849dba515473640c165bd0a9a5eb41a7e44f00825c2c4865eadc53e0255ea","measurement_key":"d54a1cb610f1b43117d919ff1f6f9210d8abd654a681b1e06cecb54866a63316","metric":"subproblem_accuracy","protocol_fingerprint":"e7f0d559b2832e84ec054a7cc453b0de14d649cb9c59eb26f4c80a1541a67067","run_fingerprint":"be4ac6bae072f03a2c0dbf832e3459391dbafdfa32456ebd6da82f62ba75a74d","score":60.300925925925895,"score_display":"60.3","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_c64279d72fe7e5e71cca36ec","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"swe-bench-pro-v2":{"benchmark_release_id":"release_d9b58bd286ce316ccf0ed891","benchmark_version":"Scale SWE-Bench Pro V2 public leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":17,"at":"2026-10-14T17:57:23Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ca7add20e35573d2e4c5a7f1897e5049767582a082c677da2003d3924d288848","measurement_key":"a1d3ec256870e06bd3d2e8b58867aa365eacf0385877b816dc08364e6b64bb29","metric":"resolved_rate","protocol_fingerprint":"3b56176a845831060a17f494b90131f94dccdc928e8752031b37bcbdaad01066","run_fingerprint":"1902dec201b8934264a5326809c30291f2791b60d328dfb62ebf9cefa0ffe0c4","score":96.73,"score_display":"96.7","source":{"id":"scale-swe-bench-pro-v2","name":"Scale AI Labs · SWE-bench Pro V2","url":"https://labs.scale.com/leaderboard/swe_bench_pro_public_v2"},"source_authority_tier":"A+","split_or_window":"public-v2-642","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_7ca4850f80ce42907607f3af","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:15Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2cf48b22073fed44be09cabe5737687d9dec02479b8d4d492b0fe4346d65ee83","measurement_key":"5e9d5439b6396bd05f9f784baef218ee0ef3a6d9339b4c6dec83b5aca3b42544","metric":"mean_final_balance_usd","protocol_fingerprint":"ca4b31ee27bc9d049375d6303d49804bc2d7779ba209152d9a7ed9b280e69cf0","run_fingerprint":"05e58c81498a7587ae45a81bd0dde7cd7f2d01b4e3b648272fcaef1cc5596ea2","score":9432.18,"score_display":"9432.18","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c79a10b1e857fa0c53d86a8c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"25e598bd6ef6413d291228270fc74fee6ba0bbef5169f55320fe1e6569bc68a6","measurement_key":"52bd0403048ba607828d9862e232cbdc02b1414b4de9631ff00664955961d016","metric":"token_efficiency_weighted_score","protocol_fingerprint":"867c92cbe6523d17c2506e8f1938872625ec5c7095976601a846815178e97ff9","run_fingerprint":"336b5cb43a649834c0c1862868867432141b38e1004603402c4e0b98ef806dd3","score":15.191042532467533,"score_display":"15.2","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_7ca4850f80ce42907607f3af","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"meta/muse-wonder-1-0","model_name":"Muse wonder 1.0","parameter_count_active":null,"parameter_count_total":null,"provider":"Meta","selection_rank":62,"weights_status":"unknown"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b89e55d7d114ab8a741245542b20152bd6a24fb27e2d8f6eb797221a73a4a3bf","measurement_key":"bb753ad078d6d0e22940a80b06364b95a6202637ce3b53e8473a92dda82d5c8c","metric":"performance_rating","protocol_fingerprint":"04e6ac1332540961c0b5a663bb13fe5851a752dec7ac4d9a7e4c507ff8094681","run_fingerprint":"3f032ba9fb6f3fc48ffb803cb6059d8c00cbb5b4ee395a41dbd8496dc9a77e14","score":678.2,"score_display":"678.20","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_ec6f9dd70348c797be90f74a","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"85e242010bd5a9cf7fe64a24d557be68d5e680ec5523f7e3a8fe8f49bf2f3db9","measurement_key":"2c0bd3a1ed44f28f28b59184976002155542d9b4ad048c7a0372bbc99081dfe7","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"64774c3307c4f152815bb478820a530bfc69911d72c0d5779cfcbd890e0090d5","score":1438.6546684400676,"score_display":"1439","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_ec6f9dd70348c797be90f74a","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":52,"at":"2026-09-09T23:36:58Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a97b8bce3b01dd844069272433c2b9ee1f34dbc1ba1402120ebfc5240c35d6f9","measurement_key":"e857ff9669c0f6ef6e80a7581f0562e8bf3b115302f89327f514192d6cf8e2aa","metric":"accuracy","protocol_fingerprint":"3ac97c3206650b74f25224218dab2ddb276c85687e3e1ab6c72733caf61af50f","run_fingerprint":"29e5d7206e0d2ed52ec89713a13e29db658fbaf682f4940faff5e927361dcd83","score":0.285714,"score_display":"0.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_eda89840d177ea9f880a9299","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9238619bc18e226d74a594c59bb2e9ffffbce91fe93441b3a9b4e2e2d62f6049","measurement_key":"4e24bd3e9fc8c49fc872dea6faa6467ff42207743974de40ac8d418fcff127e7","metric":"pass_at_1","protocol_fingerprint":"e858d0bfc6745368cc291d05a20f98f384295dfe782269142355d5d72adf3db8","run_fingerprint":"af904b09b8ddd41cddb0dee730909017d6160fc6fbcbb23b39d6d457da301045","score":53.31858407079646,"score_display":"53.3","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_277305b76ab123eb94f5d2b8","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"363b9be137624a6d034dee95aed0d8c093342407c157f6f5c95be874f52bd88d","measurement_key":"6764565725ff7d658a433b1ab51b6bc50e1a25ae61ac3de656b5149d7c012766","metric":"eci","protocol_fingerprint":"0b21fc9f1947236f2b062e2b2f0ae739db3353a23d4d3dbc8e9c4eedd81c6b18","run_fingerprint":"cca24ba91466cf66a2768c10592d85168ffcbd2bb8c1238b278100433750439c","score":146.2,"score_display":"146.20","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_eebba79f988efd30ca30bc67","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"gpqa-diamond":{"benchmark_release_id":"release_f83cfc2a9e19b8d654d7b58e","benchmark_version":"GPQA Diamond (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":52,"at":"2026-09-09T23:36:58Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8bdf10bd4375fbe0cb33b6da0d0422a56df4c15f1ad98fe148a42572f17a4e56","measurement_key":"8a12954fc16a9ad2adf9aacf1ecb38f192574e3a0c76c8e31360741b789c633c","metric":"accuracy","protocol_fingerprint":"ffe952529fe1690559e859136c0741080672196f94432543cdc2b55e58ada696","run_fingerprint":"c48da74884a27ae1895b897d5a74bdac3407a5a6f03cf389a5d41977e6eb3c00","score":71.616162,"score_display":"71.6","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"diamond-198-zero-shot-5-repeats","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_eda89840d177ea9f880a9299","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_1f4bfa5486eb4deec4942449","benchmark_version":"HLE original","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":191,"at":"2026-04-24","last_confirmed_at":"2026-11-01T07:28:22Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"7ea3e8bc80cb124094bac0118ba8cd4f238750b1cff0bcd9f531e6c85cf2cde2","measurement_key":"f49b513e1b760dc0a479630bd0a4a0e48ceac2710d433745ce10c4d292c30cf7","metric":"accuracy","protocol_fingerprint":"9d79f00315c23bc47d2293c9003ea42de6ca857854c04113ff97996ca36b3878","run_fingerprint":"4e2ebaaa6dae65fda59f90543a4b050e62959f217320f102bd15cc717bda481e","score":34.8,"score_display":"34.8","source":{"id":"deepseek-v4-pro-card","name":"DeepSeek · V4 Pro 0813 Model Card","url":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"},"source_authority_tier":"B","split_or_window":"provider-report-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a5bf84569eb675351feaaf13","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":52,"at":"2026-09-09T23:36:58Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6f7564eb6a494b38330fcc9c84b29c924f7cd7a47dffa49f09f1bf0b545d8b46","measurement_key":"91d30067dd7abb74e0a361a0b54ab99ec8c19975636fc31976527d0709abb5bc","metric":"accuracy","protocol_fingerprint":"79335436b03dfb862b6194cf674507844905c3d45289028b9afdf4387cc3f45d","run_fingerprint":"e06c4d8352f94395bb4a55ac011df146b2f51f389a831f127f434bf1ce7b17dd","score":7.784986,"score_display":"7.8","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_eda89840d177ea9f880a9299","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"93a93d5d5ea0e0fe97f3281bc14a678c041776ae10dc5f238d4e69bdafe7f4d4","measurement_key":"8fa25aafd1eec726b9d31c05a91f0983a6c5a30c6f9cfb0b4873261a6b0014a6","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"5266991625c4f00094c13464dd33cedc6ffd88cd1ebe70395462033e92424db8","score":65.48110714285716,"score_display":"65.48","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4205393e3ffc155c0364a879","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:47:54Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"637343f95289d46c0579a54f45854945c32dbcb483c02e42b1a6a9630a78f045","measurement_key":"52a318f9596da04b20f867945c86f921333e6b541dc39177d2f2d96bd6153264","metric":"subproblem_accuracy","protocol_fingerprint":"1b7162bf1583ff5201fcc2c31296c7dc34046178f2bc03b1dd3fd3a5f4c101d8","run_fingerprint":"6dcbc9e25f002ab22ce73feba69e87f6ad77ddd8f6ebbd9b71a6d21d30942a7e","score":44.907407407407405,"score_display":"44.9","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_277305b76ab123eb94f5d2b8","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1ac33e3ed1f409da3e5af9fff3e1245aa9824110f9ef0ff0f6caca6ef77f4047","measurement_key":"ea81a8e073b34e99044140cb6d1fbef32aa9bec12d795969f1ac74915ca3b7ef","metric":"accuracy_avg_at_5","protocol_fingerprint":"2221c745b377caaed9b0d2163c8c860d834304111b9d41acb2983d63b8dd702f","run_fingerprint":"4d8c5f3cc0c3f0e1a43ff38d8239c68583e59aeb581768d971916e7e3bb73888","score":46.3,"score_display":"46.3","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1f7d663cf31b9ff28820da09","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"skillsbench":{"benchmark_release_id":"release_093b45b8b752b3f08534f6ee","benchmark_version":"v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":138,"at":"2026-06-16","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0c6f6dcfecc265f7b63ae4e140d08e2d49cb61563b28f532dd9d760fb8f7e648","measurement_key":"45acd741851c01bef146873b1f7f254684c8e104f9bbb3cdb39b81363bdc76a0","metric":"pass_rate","protocol_fingerprint":"c2ed2025e534826e5e627446f4493a128269710491b35eb2122abbaf19d56304","run_fingerprint":"9a1d3bb48584137ac53d1dd9f027f9f5bc3eaf08fbd57ba1e1ae72f4335950cf","score":44.7,"score_display":"44.7","source":{"id":"skillsbench","name":"SkillsBench v1.1","url":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json"},"source_authority_tier":"A","split_or_window":"official-87-tasks-with-skills","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4ce18cb91b2b4b478d573def","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"swe-rebench-v2":{"benchmark_release_id":"release_332cbf0e979daa9e173de9f4","benchmark_version":"rolling-v2","comparison_lane":"supplemental-post-release-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d4102e0fdbef1329b958da4b9a2ad911e0afc0f96e4e194b1c76a4233a5720d2","measurement_key":"aff5096c53b82555cfa2f4660de3c506a184bb47725d758f2d46b144386cdf2b","metric":"resolved_rate","protocol_fingerprint":"3ddda07372b15613c728aba016bbc85e044ac6f484d9590196b5cd0f7c102c71","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-03-01/2026-05-15":{"benchmark_release_id":"release_72d764965dd7baf34f983249","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"da59e3af7526b4209f0e0293fbb2c9302ddb22018548b82b7ccaa5dad06a63f9","measurement_key":"39d78676c8f6eceef763edf9f27f8de9b30838086daba858e9e2681b686a2ee3","metric":"resolved_rate","protocol_fingerprint":"3f3ba7fea411425c341e66a052563aee36c46bb459ea8d03c0445ec138bc3ef3","run_fingerprint":"2a6c718340b3371876cbe46b5fb83b947057b6a09b581e179387be0ad8b3f648","score":38.36363636363637,"score_display":"38.36","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-03-01/2026-05-15","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_ec6f9dd70348c797be90f74a","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"},"2026-05-01/2026-05-15":{"benchmark_release_id":"release_332cbf0e979daa9e173de9f4","benchmark_version":"rolling-v2","comparison_lane":"supplemental-post-release-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d4102e0fdbef1329b958da4b9a2ad911e0afc0f96e4e194b1c76a4233a5720d2","measurement_key":"aff5096c53b82555cfa2f4660de3c506a184bb47725d758f2d46b144386cdf2b","metric":"resolved_rate","protocol_fingerprint":"3ddda07372b15613c728aba016bbc85e044ac6f484d9590196b5cd0f7c102c71","run_fingerprint":"3844059c64b7ee0430d0b146b0378a0e4ae15763234634cbff5ad9b5e0962505","score":40.0,"score_display":"40.00","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-01/2026-05-15","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_ec6f9dd70348c797be90f74a","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"3844059c64b7ee0430d0b146b0378a0e4ae15763234634cbff5ad9b5e0962505","score":40.0,"score_display":"40.00","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-01/2026-05-15","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_ec6f9dd70348c797be90f74a","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"terminal-bench-2.1":{"benchmark_release_id":"release_83e2a53bddae6e68d7ed56ed","benchmark_version":"2.1","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":93,"at":"2026-07-31","last_confirmed_at":"2026-11-01T07:28:22Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ca4f42e7973a5ae25c4a66240134a0079e353cd3d069bba98423059c5085ce4d","measurement_key":"8b2564f0a809baac9d57de1698fe5d40d1b42609a8486e374bfe18b0b22af906","metric":"mean_reward","protocol_fingerprint":"2856f01ce5091a1b0fbf9afd2ac976cbff4761be067a817d79b63afd325fbd4b","run_fingerprint":"d8e97704de6d2539f0af3ce07dfa4fa815d05fdbabae8e24d0289116be968379","score":61.8,"score_display":"61.8","source":{"id":"deepseek-v4-pro-card","name":"DeepSeek · V4 Pro 0813 Model Card","url":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"},"source_authority_tier":"B","split_or_window":"provider-reported-terminal-bench-2.1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a5bf84569eb675351feaaf13","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"C","evidence_rank":4,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"secondary-re-report","verified_status":"secondary-re-report"},"unit":"percent","verification_status":"secondary-re-report"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9ec17120eed9fb2e7fb3350adc03be5395d03fdebed4398b12b3fdab7637535c","measurement_key":"28a38af19930f191907cf6ce19c10c1d9bf613670b4430851273ef9525d1fd2a","metric":"arena_score","protocol_fingerprint":"67f2d4b9fc6ab4c17eba26475c1a52ebd4b93b2355d8fa5e2d1968900cb10256","run_fingerprint":"ee4026ac4006cfb4fd836d7fd2220369bdc2b86a8573e71772d468f0ac30a3d0","score":1430.4821164472921,"score_display":"1430","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_ec6f9dd70348c797be90f74a","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"701753a8e1689ab6d9ef13c7630123b6b83409de62e8e749c117ec64c3fcbf31","measurement_key":"a5a8439ff708bfc333772d6cc39add6542b329d566ff1f67ed83a5f8fc150163","metric":"accuracy","protocol_fingerprint":"c7df614619f26d191e0477590f0757699f3397570d859494fc0fdbb2c29afa98","run_fingerprint":"cb5be2c791183232a385105a380493966a2ce01edc3034759a2aaf99f66304e9","score":45.63,"score_display":"45.6","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_277305b76ab123eb94f5d2b8","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"deepseek/deepseek-v4-flash","model_name":"DeepSeek V4 Flash (2026-04-22)","parameter_count_active":13000000000,"parameter_count_total":284000000000,"provider":"DeepSeek","selection_rank":63,"weights_status":"open"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"daa9971d878535bbae28bc7a1f5bc08f9e6e6e85610ee86dbf6584df4912096d","measurement_key":"98e4af4ac128c1e25790a63f203ea3763a4445f18f349206223f3243bb76f70d","metric":"performance_rating","protocol_fingerprint":"5d3e6c572090ddf18d17752ee4d05457b8a476757b729a0a74b381f830b00dcc","run_fingerprint":"109e3f5a118e1f980cfbcacba3ee520183ea1b8e4bc3ee816acd46f6a3815f6f","score":1188.58,"score_display":"1188.58","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_cd463b62537d29712133caab","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2281f723afdbb928874921ddeb071728a9c5bb1a7a2d004231dc99ed5e3c9052","measurement_key":"a3af0d9761a3906f33dc6eeb866bea6fd6161ab5686fa9184c9a4d735c33f7c8","metric":"pass_at_2_accuracy","protocol_fingerprint":"ae6f6765b96f58fc9143382fe604f5c2fa58622e65ef712f44f33e10871bf936","run_fingerprint":"8e3a6ce445cda7ae6288963025851e41539b91a1e5e280cf4383b588ae479730","score":63.67,"score_display":"63.7","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7a05f4cfc25c7876af6e3f4e2960f4cce2985efe9acddedeb6eeb574242a6bbe","measurement_key":"9a78c07322e90434270ea5b8d8e70dca30d884673d796f3aa4f3d39ebabdb4f9","metric":"accuracy","protocol_fingerprint":"e80a40dce6d44e9548d8b5cf7f58dbd5b98a2218d63a513b4a980ca9d1acb61a","run_fingerprint":"bb0eef2b77b1d76edd7e612c8c94fbbb6b47baffe44d63034953cde75bd57dbb","score":18.9,"score_display":"19","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1bb5cd55dbc951ac63a3103307516811107e4fe42d15f562da1fc4b528c28992","measurement_key":"875e243278d49e80c80963d1b410e564367d9ab247d739aac020985ae2a3d494","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"ed2346510b3e5d33b4d82517046d62e7add5b91c063eb02d811e0c0878c965cb","score":1447.1749944782787,"score_display":"1447","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_cd463b62537d29712133caab","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T14:02:26.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1f2e1386bcb4f941d96e8f125796d75d47999452e3a781b14ee19411000e79ee","measurement_key":"18491a61840d01fa9f762e9bf8b4c79968fb76eafba343230df6f048510ceb9e","metric":"mean_score","protocol_fingerprint":"fbe42d1459879fe0087939401722acd4127a2251454373d72271b27aa2489d1e","run_fingerprint":"2e793651f82281230b768fffe4248a8a2f93aa87370b255f786a27be95767c17","score":17.0,"score_display":"17.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2b86689e9493efb86d56157a45d18f182782349032edbb8802083675892c7853","measurement_key":"72883dac6457b5258b4fe9996c36baadac7012b3b61b27fc8dd65021c9c1200f","metric":"accuracy","protocol_fingerprint":"b9c8600f4fb5911c6e6a2c59f7ba2e7e43eacd49781d70c54cd9faf155510642","run_fingerprint":"f47350749ea3dd392f3a57c52efe326854c1a1d7dba9680ccab8715d481beb68","score":10.0,"score_display":"10.0","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5777566c2b480267f34f3d25d12860aeb813319ac6570f38065c0305b35fb260","measurement_key":"8e53af1e01415ed7af8d5f2424d6dad08f749d5006eb590ce3b99b637fa1f837","metric":"eci","protocol_fingerprint":"ae6c569248bf0da4a0acd1aeaf38b0a976f14bba98a396b489c822fcb8b1b25b","run_fingerprint":"1e9c113d83c02dbfcb837bd0beafef3d081430dead430d74bd3eb659390c7d0b","score":148.82,"score_display":"148.82","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0c4947d15e8e8b2e1d736e54","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"acd2b5e325e17882a1b1ca155245b0315f891aaead64d37af27d6c30f3984a01","measurement_key":"0de4bfe2f71fc6d82dccf4ca34a7c5eaa81c760ec2927169e45cea20639680f2","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"a914ef90457ec38e014bd6d0c4fa13247b98e205edefeaef436af0da0b0713f1","run_fingerprint":"ab11ecdc6ec69cff9e0534623a597d634d4ad63c77592cebc2bba02b8011cee6","score":27.04,"score_display":"27.0","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":141,"at":"2026-06-12T16:40:38.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c389e27ba1e1dcd89349ce735371ee826b5d2e65b467693027348a6845611c28","measurement_key":"5ed9614a64c55967b157852c00963ba6fcc683359646d60a7de49a0e7916c6da","metric":"mean_score","protocol_fingerprint":"c29be5d216a0fb49320061c3ebdf535bfc5fd74d6084a85230e48503aa015a3b","run_fingerprint":"dc04a8df58946cb7f965389054e3cbca36c821ed3c3060dddb7cbd7f8f06a740","score":51.2280701754386,"score_display":"51.2","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":141,"at":"2026-06-12T16:40:39.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c340d38e1c989eec5795a20d4374a4ede9f40e8d410c0f64b94ff2d49be56cdb","measurement_key":"5168b43ccaf135c5d32932b670ef08b121355a29351de46899d4a98e376aaf48","metric":"mean_score","protocol_fingerprint":"3a6f043e3447e4f181bc0555c74923aaa94035d15034c142b42db7f783a752ba","run_fingerprint":"7aa5032e387cc68152f8354e9efe25a10183d917b129ed6b7a87411647368bc1","score":9.75609756097561,"score_display":"9.8","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bcc57014069af24c8daaccb9dcd1029156cd341ba90645417294d44ccef337eb","measurement_key":"176fb79b95cf121fe2fe20ab27d00b2ebe3134618dc82a879a5085e83e966155","metric":"elo","protocol_fingerprint":"eacfae557cc981fdbbb8a10002567bfe3e737e5aebb5da1e1d848ff3c154a0c9","run_fingerprint":"216560cc378a7d801c764704514bcd71c87674a03acd2fbe9b2863379306c51a","score":1021.79,"score_display":"1022","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dedc5e6df3fcb08813b0d740ded070aadd42e902fc85c7a224c418b271e47243","measurement_key":"6c4a9762dce2896606d0b895c5df9d4073f8301c85fe8ed2ee9b00c5061afab8","metric":"accuracy","protocol_fingerprint":"bb5ed5cb8f0d8db4cf55d5128bc1072501d648d4acc49ee6d831310a9bc919a3","run_fingerprint":"f4bf0023f19ff09fd23afa1813785d26f62e3c7a97cb6c4508cfe694a76371a5","score":83.08,"score_display":"83.08","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c542e5df54838e4a4728b3f017a3c1aff079bb28fb8cf9eb2f991f714f1c0a7b","measurement_key":"b7e099fe17cf192c63069cc5a1b03000bec00ca06158e512ac16b80eeb732f38","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"0ded6574c296b79fb1ec97c5212bb713302dccea22580b5f6e65b823ba3e880c","score":66.37396428571428,"score_display":"66.37","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f83374d904ae3ac3da645629fd9087f42b1e22ed671ef7ca193e846d82d7b28c","measurement_key":"de3d284ca200eb95e7d21596b7bd7f77775ffb0ed4cdeae6340270768ddf2b7a","metric":"pass_at_1","protocol_fingerprint":"78dcd870a36869d98bba3e069be5ef96b7afe47143d5ceee126683bfa158bdb3","run_fingerprint":"38ce3e9a9bfd785723b7c7c9a93763fa7ada3f25fd299cdf54154011454a09c6","score":81.465,"score_display":"81.5","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5329cdba31001e5a0fe134f9465b70b2aaef5cdc49de82400757f42713fab78a","measurement_key":"63f4c49c9cf828676cbdb5bf7c2335f9cab7e22788268b2bfa6128848bbc3caa","metric":"accuracy","protocol_fingerprint":"6f17099ff66a523d4d6a6f88b32a39f321eb1acd5e0fced00386a94872e580af","run_fingerprint":"43b8e3ef40ed531d8826d189b2cbd0ca3f465a1cddd7ef7fbbd1ed8877958df4","score":84.554,"score_display":"84.6","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:41Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"964e853cdd98fe992ddef66dbcb6e69a3313e399e021523febd69fddd0ba0711","measurement_key":"bd82f5c0b00e7de875c243717e72e201123fc9e97deb81f64f92fce472cab7ea","metric":"accuracy","protocol_fingerprint":"60d5afae34318f4d140d29bfe7d6d12e78996eb082871bb2ce95e5449f760843","run_fingerprint":"91dd7a1926794c16ea6c27dea47b23da459d801020b36cdf5e1e34c5a93eaec2","score":79.249,"score_display":"79.2","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-07T00:56:59.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9bbc062b4fceff66f9a7d5d415e859138477092883a01492f3c6624abb01ddbe","measurement_key":"a76b46bddd27d37501a3ac7797b0e117f0cb88d11c40b4b97104c194cd95bd41","metric":"mean_score","protocol_fingerprint":"46c32a6dbd5cc35e27c1a07fcce0749d6df3838e83710dce955b3c864b4e92ea","run_fingerprint":"f11546dabf32df439dd5ad5d7ca1b54d4d878aafb8c55394d560c70dc939b149","score":88.88888888888889,"score_display":"88.9","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7f59c34b09f885b1a4f834f14d771a6e38b9205ce18982937604e3da0867b883","measurement_key":"4f0fe98daabaf39c2f974cb6343afdea6bb0b9187f6d938497bfbf7000771902","metric":"fully_resolved_rate","protocol_fingerprint":"cb64a34cb8c19214a8e30a3566309ab0e9b47df4eea36a9d77a3ef0800074d4c","run_fingerprint":"2c72c623a77a8ff708324314a44785f83e210d29dec4872bf855f776a0f11db6","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b4896f26497a83368338de672588cfb7bfa683553c9f564b7f4e52b59f1fe2fd","measurement_key":"3e7843da644ac2b355ef7e4ed120b99ec5f6b69b09834f41887de8ed372b24b8","metric":"subproblem_accuracy","protocol_fingerprint":"644e6a16e1503037efa3824b666795244b991da92c77edea91a9f52f77fee232","run_fingerprint":"d9d3d6891dd5f5487d32f261c0deacd3dc2b9f7dd253d170776802c6ff74c733","score":52.0833333333333,"score_display":"52.1","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:28:49.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e21f2c2885d5b75b6821d0eacfb7c3f03756db59ac07d087a6a6542762a43fec","measurement_key":"a4fceb4ea078340910f785edfb39569a68b925ccfced0e20e50063cba7e48688","metric":"accuracy","protocol_fingerprint":"72fa00adc85d3388e9d9fc1c13acf750aeed030934a81665e85e3976b5089d87","run_fingerprint":"ceb86e8cab7e425096679c47d9cc18235bb62f8caf5958bb908228dd1331f406","score":29.4,"score_display":"29.4","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_cd463b62537d29712133caab","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"skillsbench":{"benchmark_release_id":"release_093b45b8b752b3f08534f6ee","benchmark_version":"v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":138,"at":"2026-06-16","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5e27ceca0d7c694bf196c1c987c4d9833e418600e361a562e5b5f95c55bff6fe","measurement_key":"0c7420d1dfd3b1f5b770a1d0fba6b0253bc7acfa5a8b0148b6ad508dfc84e0b9","metric":"pass_rate","protocol_fingerprint":"c2ed2025e534826e5e627446f4493a128269710491b35eb2122abbaf19d56304","run_fingerprint":"0befa8ccd464ba5d0240bc986890964300ffdddbb51089f3b7886c9c61a9b0cd","score":41.4,"score_display":"41.4","source":{"id":"skillsbench","name":"SkillsBench v1.1","url":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json"},"source_authority_tier":"A","split_or_window":"official-87-tasks-with-skills","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0ad87315d87f37ec5bf6e958","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b5eb5a131bc1544c212e3bb167b57dbe0aad4baf8e754055b679d941f4d14703","measurement_key":"21bc47430a3238352370ec1466c08c41fa20f04216565a8d066eecd669424100","metric":"resolved_rate","protocol_fingerprint":"deddb0dfbdb6baed3a07d79ef533ab29aaf4b2085dbaa218755e23f2162181c0","run_fingerprint":"1235b6fd91e45720eb84724650680b0f6fb3630a17997fe4b93542b80038cbf8","score":73.0,"score_display":"73.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b5eb5a131bc1544c212e3bb167b57dbe0aad4baf8e754055b679d941f4d14703","measurement_key":"21bc47430a3238352370ec1466c08c41fa20f04216565a8d066eecd669424100","metric":"resolved_rate","protocol_fingerprint":"deddb0dfbdb6baed3a07d79ef533ab29aaf4b2085dbaa218755e23f2162181c0","reporting_origin":"organizer","run_fingerprint":"1235b6fd91e45720eb84724650680b0f6fb3630a17997fe4b93542b80038cbf8","score":73.0,"score_display":"73.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"da4b9de6ffc1104ae1de450ad48b6c7d1bf7d01f809037e6a7c61146ef37a871","measurement_key":"f2ff062709a3ce38657aa46f8d283ba4cf24ec1d27550c900b7bf22622b8e91e","metric":"accuracy","protocol_fingerprint":"7f427938aecc10eab238c7bd96d09c3efa44115f71632c55f8a9f164f10379b2","run_fingerprint":"642c100b11df2c526aeaf85f940c2370baaa86ab8aae8c32222824fa42907550","score":54.682,"score_display":"54.7","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_cd463b62537d29712133caab","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8e57656f351ad8ef919b300b628ec3f7d850c257ba19d46d59f2906644355ff2","measurement_key":"98e90ca461d8f08d2ffa64a005bb428c24c22b544bd8f028064a11ec69387877","metric":"accuracy","protocol_fingerprint":"c06fdebe841d5add776f6a399db64ea85c5ccd79a0be8fe889c197801fa1c124","run_fingerprint":"fcf1457fb396aa4f8a0260d3e32d91214b57b55c70cc3921db34443cf7e50316","score":2.525,"score_display":"2.5","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"92d9636da8a6207c082a58657aba6f9f89d3eaa594c63f958fd0b4b4538ff68c","measurement_key":"58197232b148972739d15a49905785c8be58310c73faa6862564daf24cf655cc","metric":"score","protocol_fingerprint":"304e82c65fab2b71f3b2e514b7ee483ad4399619ce2c6ea05928a5880317f8b0","run_fingerprint":"981e61728794cba1a13baa812f14811235d367b449329321fc3a703d49176462","score":47.969,"score_display":"48.0","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_c6f0f8947c7f8dc16f5517b6","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"67da42e438e54bb49450d2b8ccf775248639b61186b3daf4df91dadb5892bc01","measurement_key":"14f96e7b176716c8262a16d1679a6f1d54e00d545656ce96a7a258b2de217b49","metric":"arena_score","protocol_fingerprint":"506c358899f145260726698d1682f26cf00080cc3d585b85a7e92136103dfac3","run_fingerprint":"1c0a731d64f3c34e2ec8efd1a6f0e89d55d4599635de6b3c0e4b95a0a5446d62","score":1397.299194720604,"score_display":"1397","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_cd463b62537d29712133caab","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6c8c8288cf96343444ca8d9af0225d66e120586a25400e1a34955721b2d77a81","measurement_key":"0658165fc1595a4226fa45d20dadd024c69415e2a2899c93b1b7a7b7f6783daf","metric":"accuracy","protocol_fingerprint":"08670d47312fe006c5a06588bea2dbeccbfd7b97875e82e7944fc1ed29ca942a","run_fingerprint":"a99d9e66f8d3b7564b4274b9786c0a9ec5e239369a59a675a7780497586155fb","score":60.3,"score_display":"60.3","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_cd463b62537d29712133caab","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"openai/gpt-5-4-mini","model_name":"GPT 5.4 Mini","parameter_count_active":null,"parameter_count_total":null,"provider":"OpenAI","selection_rank":64,"weights_status":"closed"},{"cells":{"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6801a646d6cea052f87352840d9f0e63e44894fb841319d270abbbb907c9785a","measurement_key":"d5c5702ae0bf58eddb70db1edbf827f6183067c96f9f90a4aa8635dd74ab9a66","metric":"pass_at_2_accuracy","protocol_fingerprint":"bd170eff40b20afe8d63cbc3182879277ef4f6968b7f55e0284fbc36322a02dc","run_fingerprint":"637e791d07c9939199fa668feb7e5b39eaa89f389fd5317b5acc86702c3ff984","score":40.0,"score_display":"40.0","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_926bdc433ee7f4064ce2e951","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_c66f5b82bd3045b91ad807bc","benchmark_version":"ARC-AGI-2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:43:25Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9991a1a186b1119daf0a6821e4f59d8bc1da79d1e0781d94ad58e323616f5108","measurement_key":"c1344d8c83f9b71d31eb72e22f4b69ece727e7909c9124e9e9abc495cfc988b6","metric":"pass_at_2_accuracy","protocol_fingerprint":"4b3084c25aa997f35d6830e86f41d21548d7307ed80b7e834cdb86431ea7ed8b","run_fingerprint":"5d0cdc4137e5eb3db8db5b9efe8c60655d11f87ee865b18c62bb07a1a5d1af76","score":7.779999999999999,"score_display":"7.8","source":{"id":"epoch-arc-agi-2","name":"Epoch AI mirror · ARC-AGI-2","url":"https://epoch.ai/benchmarks/arc-agi-2"},"source_authority_tier":"B","split_or_window":"evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_926bdc433ee7f4064ce2e951","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ccbde14ead0933e2eb7a0fc5cca72a818e33573a4811ec38bce24a5646c37423","measurement_key":"85a2188bc6ad6925d3e101752502d3cfa59e0e1dd57ee3330f259bf8cfb05966","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"434c3719dae7f10e1444d03d98a941fa1dffc66cd49144782275408d9c8cf9ec","score":1473.6904735629234,"score_display":"1474","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_130345efddb139a5f20d658e","raw_label":"high","reasoning_enabled":true,"strategy":"token_budget","token_budget":32000},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"bfcl-v4":{"benchmark_release_id":"release_7d2560723dba9d549cd10b25","benchmark_version":"v4-ede5081a24bc","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":64,"at":"2026-08-28T22:03:18Z","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8d22944d7d361759f06cf27568ea3c19c9cebab1ef34ee5584a9f1ecb62ddf08","measurement_key":"d3a670e52a2c73af1cf9ba97db61849f5ee0b09bc97d555cab6b9c2e4853d48c","metric":"overall_accuracy","protocol_fingerprint":"6a9c99bccbca11748bdf70a2bdd6eb864726c94bf4a029f84ab95898fe96d192","run_fingerprint":"b16b927b0fc6a8c5c57ac2a62bb16f71d47b0ce143c2e4603aa9c1a7cfa7859a","score":77.47,"score_display":"77.47","source":{"id":"bfcl-v4","name":"BFCL V4","url":"https://gorilla.cs.berkeley.edu/leaderboard.html"},"source_authority_tier":"A","split_or_window":"overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_add9f33c77552c619900f72b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:42:24.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"34c83daf144bdf4cc40197209321ca63c681cfd5a0431f3841dd8bee63619e9b","measurement_key":"8713c1f175a30992ef312016bd9c8085a5c4b7d59254c6ca927f101447956a16","metric":"mean_score","protocol_fingerprint":"4afd2c28aad2fa3a03ac5912780e4205a03bf886063f351bfd2a27a4321a1f9c","run_fingerprint":"ed22f0ebf09987c064a3fe872e60ff5d2e7ed8454913abdd5905d78d7669c921","score":5.0,"score_display":"5.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6eb479ddca0f4373f2bde9be","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"91821d16d847ccc456c5e842d00135b9f245454821227a76a41347d7ae1366d1","measurement_key":"490ac85aefd800caba400192f8072dbb40e9d52f89b6e7c8234bb24c5eadd2f6","metric":"eci","protocol_fingerprint":"4aae907a1d796e85523324700c3de958e63e1cbdf9ab302865ac9cdc1abfb748","run_fingerprint":"d527338669ca1f8a6a4b176f1b8c8634f777a6c8930593196d4af21cbf23a9a0","score":150.2,"score_display":"150.20","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f5e834ff6a9d4d675c2c021a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":143,"at":"2026-06-11T01:55:25.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b4fbffc6fc6329da4aa514fb363753072e6c4ae1e49bcb78f3b19c269b1bbb30","measurement_key":"7ac15b7266356ee5f5868c8708652baba53229dbcddb5d048a4b1b13a5c33996","metric":"mean_score","protocol_fingerprint":"25b36e77ff057a5430c68caa40fa10bc60073c75fd6fc13c93f34b7ddb269e8b","run_fingerprint":"48de2b49b95bd69b8a26fd9c2f13a24287dc9986a1eef79d15c71d7c62b141d5","score":34.385964912280706,"score_display":"34.4","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_597cba506275a64a67c0cb7d","raw_label":"thinking-32k","reasoning_enabled":null,"strategy":"token_budget","token_budget":32000},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":143,"at":"2026-06-11T01:55:25.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"035c206c331bcf243beea8d28a7aa2230142d7cabffc60387c97c23c30aa1f6d","measurement_key":"f582c4ef6128545117242e9fa7d4b9dd87dcf915925291720791798f80aa9df4","metric":"mean_score","protocol_fingerprint":"52c1ea0466e69627d2998ab353768b351763ae03145f03084de8f4c7c1fc4a31","run_fingerprint":"5d9e57a0155114ee7b3a7bd35f6ba68d7e28bfde7c05f5d9751ccec3d1096c72","score":4.878048780487805,"score_display":"4.9","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_beecacca1fd5f3ea74568a4f","raw_label":"thinking-32k","reasoning_enabled":null,"strategy":"token_budget","token_budget":32000},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval":{"benchmark_release_id":"release_730527fa346470703bd19e21","benchmark_version":"GDPval official leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:05Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e82ea31213a709ffe2cb81e68deca2fa1f303845cfe2797d37e42aa0f93872e0","measurement_key":"5320e1f492ea9acab97f23091f8cacd93bf6c3957bdbd8492201934a95bb068d","metric":"win_rate","protocol_fingerprint":"378fc1a8e117ab4f314c4ef7da05eccc63a48ee1c23b7e95a30acb27f82c58b1","run_fingerprint":"2abf0ade10240f8830d9f6bba725ca3500dfad78cbda608ea6ea6d11d5dd13d6","score":45.5,"score_display":"45.5","source":{"id":"epoch-gdpval","name":"Epoch AI mirror · GDPval","url":"https://epoch.ai/benchmarks/gdpval"},"source_authority_tier":"B","split_or_window":"expert-comparison-win-rate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b5b92874a5c47d9cc6e62f91","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5c283b1863945eeb1ced6280a618610bb3cfac94f2e65aaea86b9e29e91b5a4f","measurement_key":"b56847144215565bf5ae141722bc35898e78672c6bd0cd6c72c552eb84a05d77","metric":"accuracy","protocol_fingerprint":"5d265cc0e54a9e3d776b2e0a2b8f33312db57cabdf2254c07e8691f3f3f37089","run_fingerprint":"f045497f70a0d1c9c4f6fe0af0badc181d52f906fa30fd1172efdc87c3714d46","score":85.859,"score_display":"85.86","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_38e056a3f25f42f22b205781","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gso":{"benchmark_release_id":"release_176f07ea4e9e0b8dfeede990","benchmark_version":"GSO current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:04Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c62b12a8f515d8c85b08d0e31051d883fc5d6e8aa0e42524e15b629d1a864e67","measurement_key":"c6e2789d33dc09237512f8a04ba0fd8578da74444a53061a0f6495c9357d0417","metric":"opt_at_1","protocol_fingerprint":"72b1185f7df85085f15496c403080aebfabe615e1f401dd190b8f8a25bfe10a3","run_fingerprint":"b7067fb3bb3d809f77604b24b8e3a2bf0b8eb6cfa587f268b78e88d5b3b5ede4","score":26.5,"score_display":"26.5","source":{"id":"epoch-gso","name":"Epoch AI mirror · GSO","url":"https://epoch.ai/benchmarks/gso"},"source_authority_tier":"B","split_or_window":"official-set-opt-at-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4c7c0b6e9b003d3102b8548e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"hle":{"benchmark_release_id":"release_8817af9d9a0235bce0826e22","benchmark_version":"HLE finalized 2,500 · Scale protocol 2025-04-03","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":339,"at":"2025-11-26T20:25:03Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"ceff2c03b3b7f67fce88d60f28dd05b4edac42734a76d34600b8efc2dc97d455","measurement_key":"f6d8a3bf5a0a5b35d0555aa0f087a57729c83e0029fe51d7fca44f01859305a3","metric":"accuracy","protocol_fingerprint":"51f4bd9527026f51feb786e7b5f5baa6d2c65547995dd42ca0fd95e4743b7901","run_fingerprint":"148c3a74014f7eb6def4453b1a5fa19fa0f0b73b8164314eab52abb0ce0d0e6f","score":14.16,"score_display":"14.16","source":{"id":"scale-hle","name":"Scale AI Labs · Humanity's Last Exam Full","url":"https://labs.scale.com/leaderboard/humanitys_last_exam"},"source_authority_tier":"A+","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7c52e44fa1806e202f8c3942","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5e2cee8e322e531eb7c7fb4d91a80c78c7195111a246f6f5858d0bd3efb959a4","measurement_key":"baa07f817729b5674a21ad99f4e3819b1c7393adfe914f80ca517598601a1944","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"1318b23dcadb7660f8e584baef5824865bac2341937e66cea62db137bc669487","score":72.58216666666667,"score_display":"72.58","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_139bf317a1ccf46d0ad71c1b","raw_label":"high","reasoning_enabled":true,"strategy":"token_budget","token_budget":64000},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"56cf58fe02ed0ff933be71f6cf9b8818d059817368c4f998ffaae52902a557a7","measurement_key":"b2f25382b5b7f93296dc15106cb9831f1c57a12cd716c835d013d45562f36d6d","metric":"pass_at_1","protocol_fingerprint":"cecc93e7118cb670afa1c1a74f65be3f0344051f547a97e5f392ee113daa0fa9","run_fingerprint":"3dc9933d1db16259ab8126292b7af1b5dc4f7926c07d94201c4f329da9e94928","score":83.67,"score_display":"83.7","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_38e056a3f25f42f22b205781","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e143addec52de82082d13b7287180c02abecbe5d857ab3066683b956a3b59d61","measurement_key":"394ef91c8d8ac5b681bd9bcc2213f2a01d32ff182643595b4c4e855197d089c4","metric":"accuracy","protocol_fingerprint":"d7e438fe3ddc56d7fbaa49bea102c0019cf3a472fc20942c8309f85c7c9acc91","run_fingerprint":"1bba8deeab7e3570b86daf5c87b584592de999eb1f9eb86e8624c24f2d23a3b2","score":87.26,"score_display":"87.3","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_38e056a3f25f42f22b205781","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f2d75c69d326d564167f05fa2d77216641c254ca28ebfd91c618533d4aa7bf3b","measurement_key":"2229fe5432554fb7a4728cab75c186ace91f3d65b35d35d6ada3f83eb4770c32","metric":"accuracy","protocol_fingerprint":"1c15fb011e384b8a984f6a69c456c68cb1e57456cec7fc37c03ede17f209b136","run_fingerprint":"ecac4483239faa9e514ce664152be84a5cef899a7dadc7e68bf52cfb7b8c84fa","score":82.948,"score_display":"82.9","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_38e056a3f25f42f22b205781","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":341,"at":"2025-11-24T20:47:49.364Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"ef30b32555e0605330ebd0cea850634402408f610fd487e0d2445be9849ecb3e","measurement_key":"d7ee9800933eda6275fb6ae5f01d16cab9bc81a1944bc2ecaf6a00c664e9009e","metric":"mean_score","protocol_fingerprint":"2fa30ce7c948cb2db42398112d6401b364afa08c3e7b7a939b5a2d4e2f252d45","run_fingerprint":"d156fc4f0a15ab6edce11bae6ae0251444cb284c391df1c0c09292c5cc953b2d","score":48.05555555555556,"score_display":"48.1","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8163073ac76db4da90db1b36","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c38c5b3ad541eda02385e92bd62a17ace6f6812ff893b1e6ef1e99ae56844ffc","measurement_key":"932f613237c08c73fa83f2d4257b932ad231bf6ded5ea36168bd607e9c689ca2","metric":"accuracy_avg_at_5","protocol_fingerprint":"bd4a0e71c7f9c39ccbd5b3fab0cdc3be9fce0b80743bd8d092a4ce230a25f1ec","run_fingerprint":"7c82d671b3b48c6df64c46fa366eaa988c12b110787f968c5e738c3139d65e39","score":62.0,"score_display":"62.0","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_56fcc66f50d70a253236a8bf","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_ccacd6f679c9142b534364b4","benchmark_version":"task-v7","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":341,"at":"2025-11-25T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"ec8fadd030ac501d2a8b9e139d4e132d5283b1a16d9eed75dccb8ad776bc86b2","measurement_key":"65e090a9db3968dff341576cf49a01904682beb8a7844f0df1fc4776971fcd6d","metric":"accuracy","protocol_fingerprint":"644c85525faccfd7fc3a26dacec1284e5908cc1abd3c0b92a30923675045f344","run_fingerprint":"d569e03b8c346068e029a97b3abf6c71ef2399e46457cb306b49760c3d1ad5de","score":39.004149377593365,"score_display":"39.0","source":{"id":"simpleqa-verified","name":"SimpleQA Verified","url":"https://www.kaggle.com/api/v1/benchmarks/deepmind/simpleqa-verified/leaderboard"},"source_authority_tier":"A","split_or_window":"verified","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a72b975b52d107a214a49b26","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2bdc81db69bf376c7ddf15e96505709518dcfad0a6a6adfa0c923b406fb35b7b","measurement_key":"68478f72e4d9c307ff7a00921d9a092abd28d750597b6c1babaced14ffed8e37","metric":"resolved_rate","protocol_fingerprint":"266500a34989fc6bc3ada17acf30da1e972378b6bad797583daf3c0cc52735fc","run_fingerprint":"9af256aea80ea0816cfc8cdc697148f716a7e4cefea34951c9ecba3d832a4175","score":76.4,"score_display":"76.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_38e056a3f25f42f22b205781","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2bdc81db69bf376c7ddf15e96505709518dcfad0a6a6adfa0c923b406fb35b7b","measurement_key":"68478f72e4d9c307ff7a00921d9a092abd28d750597b6c1babaced14ffed8e37","metric":"resolved_rate","protocol_fingerprint":"266500a34989fc6bc3ada17acf30da1e972378b6bad797583daf3c0cc52735fc","reporting_origin":"organizer","run_fingerprint":"9af256aea80ea0816cfc8cdc697148f716a7e4cefea34951c9ecba3d832a4175","score":76.4,"score_display":"76.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_38e056a3f25f42f22b205781","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_1c18f4398e32b2e0fe7f7d86","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":273,"at":"2026-02-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"b0db892ecc6b19ca4db9caae151c345c3bf55c06a05cb6810cd972b8f021396c","measurement_key":"fad73709a539fec30ce536a0546d6f5b427bda0bcdc425c55bed508b23299bf4","metric":"resolved_rate","protocol_fingerprint":"55c67f29f9caeae2fb1a7af296decbc5ef7cf3d6983fdb72f33fcc65c4733416","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2025-12-01/2026-02-01":{"benchmark_release_id":"release_1c18f4398e32b2e0fe7f7d86","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":273,"at":"2026-02-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"b0db892ecc6b19ca4db9caae151c345c3bf55c06a05cb6810cd972b8f021396c","measurement_key":"fad73709a539fec30ce536a0546d6f5b427bda0bcdc425c55bed508b23299bf4","metric":"resolved_rate","protocol_fingerprint":"55c67f29f9caeae2fb1a7af296decbc5ef7cf3d6983fdb72f33fcc65c4733416","run_fingerprint":"14da9d4fd1eb38bd417024f7698503edefda5bf54acb32187b53beada1dd2408","score":53.541666666666664,"score_display":"53.54","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2025-12-01/2026-02-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6d7d2d1817324164a6889f68","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"14da9d4fd1eb38bd417024f7698503edefda5bf54acb32187b53beada1dd2408","score":53.541666666666664,"score_display":"53.54","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2025-12-01/2026-02-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6d7d2d1817324164a6889f68","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":180,"at":"2026-05-05","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"60354dfec2ad4573e95efffb3135c8c8cf0e63a452855134cec3db53022ca2ff","measurement_key":"181ef07d47e60cbbe1d43d1445c297f2ed4079a5b07944f6a9593983ff52a2bc","metric":"pass_1","protocol_fingerprint":"67f26e9643b98a8dfb5466fbbc338423afd93b9175dbd49cdf6dc026e61077e4","run_fingerprint":"9a3d4866699a04b9f9051d9796a8c11ef3e2c47a4d17dbbcb995cc7de09bff7b","score":24.74,"score_display":"24.7","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_38e056a3f25f42f22b205781","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c25593b775fc227f7ddf3e5f99bcd661d01ec118b1d3577cae3c1fd10ecab3ef","measurement_key":"d4bc4ae29a5566119ba0bf88954c2e7745c1466ae294d3984a35d46ef4fa61e8","metric":"mean_final_balance_usd","protocol_fingerprint":"d0d6155566171de54f7bb1d6fc1fbe71b75e8ef263810485607e592935427ef8","run_fingerprint":"ae472a7b1b7fdccba65be59d83e8913c34a91f9e7af41603c0c7d3c99f8f1da3","score":4967.056666666668,"score_display":"4967.06","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_acc9610846795e84cd094615","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"163e8d953ce876eba610c5e399db370b0631faebd918639e52f3770fdc6b59e4","measurement_key":"b66167f6f06d85722f650e249ebc816ed024318ae466674445648f5f99eac315","metric":"score","protocol_fingerprint":"13b83b290f4812953b87168bb38d8d29e562a97c32eb43cef14902469723aeef","run_fingerprint":"8f938fcefcca26c9b6283ff64cf2257d9d326589ab62e5d8c3e20015f0f8baf1","score":20.63,"score_display":"20.6","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_38e056a3f25f42f22b205781","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"20db45869a4d6c0096d3cc58eb931dd65e0b3a3924fa29ca0450b9900cfc9271","measurement_key":"f0fdc5ecf34c7170ddccd09e30989788a396954e08dca606b93d684638e14712","metric":"arena_score","protocol_fingerprint":"b13d87ba71e682faa1a11073183a5b6282d1460aae5fa73c48679d9467e3069e","run_fingerprint":"7224f66f1d3fd2c5878d03ff6d6fd23b3b0d9759ed8bd6aa816b8f8c631a344b","score":1493.6607664512705,"score_display":"1494","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_130345efddb139a5f20d658e","raw_label":"high","reasoning_enabled":true,"strategy":"token_budget","token_budget":32000},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"35403a5961b65093af7f8d353bcd52dd8f4cb8d1ec81a3b6e3c42cec8a730c14","measurement_key":"e81f3436f58ce7e5bcc6d8ed311ab30cf6f1403e5d418833b8573a082fd61da5","metric":"token_efficiency_weighted_score","protocol_fingerprint":"1a3a2749f388bd22e3e4ed0cd91ccefd02106aa3944e4cb9c223709565c62183","run_fingerprint":"5460220703692c88b32a10fcc9991bb6eb71c91f66776a779e07c0e02fc1e63d","score":6.5148765151515144,"score_display":"6.5","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_38e056a3f25f42f22b205781","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"anthropic/claude-opus-4-5","model_name":"Claude Opus 4.5","parameter_count_active":null,"parameter_count_total":null,"provider":"Anthropic","selection_rank":65,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"965f507ab05c1b0f28e79cc03ccfab08248fe5709ecb9db40385852df1d38895","measurement_key":"c557d7493bed957743012dabb4eae530864d6598255e1c09d7c8fd8799da3117","metric":"performance_rating","protocol_fingerprint":"332e5148a14ee8714a7566d28a9eb053d3e7fa4e32accba9de0c5dac596f24c9","run_fingerprint":"0c6bc7f237aa84b101b6ba38b86731ac1fb9f5947093175f67dddf0d8ab28366","score":899.8,"score_display":"899.80","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f27c99ca4ea89e5927d9d756","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"54784f0db036b973cf4cc1b442923482ebb48c84b80e23a0be65e8a9058b559a","measurement_key":"dbb634f6c3ab54741f4fc6427bb343372547ce1db7c3cffa29ebce9323085b49","metric":"ips_score","protocol_fingerprint":"f70df5b9f0aff58ead73e129c7080cc3691c0764a7d15fbebd11a30f682481b6","run_fingerprint":"1b0f5718367bb9d8c8589bbef3a56ac3276129c7f64bc7fff4cd83ad838a0b4a","score":-0.08932691327565813,"score_display":"-0.0893","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d8ac0691b0cd4bec10937bd4","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"eac64dfd7af3fef51ef4d399d066488072d9b392b9c3952bbb966aa0b5442165","measurement_key":"cf77644ba563a0eda1d240b5807bd342b45356db165692cb1c3ac271bf7abb74","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"0e6abef28af512d7d30f549bc9502ff7bd802875a4f276f19ea7e9cc1fa41061","score":1466.599824571988,"score_display":"1467","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_cf88c4c74c23c65e8505ad74","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-09-17T14:33:50Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"653e664082cb328ad6f981ed0422ee17f81eeb1d369b9ed1eebc07fdf3565e7a","measurement_key":"5174f7f88029a68b65b0ccbb1aa878a6f8cd61af756b1644733b8f0ab0d2dd60","metric":"accuracy","protocol_fingerprint":"0c3ea6fcbb859d82df8441105ff8a6e25c282fc65d419aae0af8d4f2a9d33f39","run_fingerprint":"cbc911b2c0a893534395eba203ed18d6876599c1f7dfd997109aa7f8efd2acb1","score":4.0,"score_display":"4.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8fe48d99b25cc95375221a5f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"977f8ded466eafa646eb7d24a3c84aab7509d29f8ff0bdc9b0ecbfa596aa24a6","measurement_key":"85a40aedafbf16fe8588f06049fc55cf55795c697b04112c92624f4f815c3f5d","metric":"elo","protocol_fingerprint":"609edaa4443866ff024ee88d9c3acb2f02e7f9e00c012b4c9188fdf4d4ff1f3a","run_fingerprint":"e65401b5ff62d089583bd0b61dc453118ffe489c72e0db522e92c53257fef441","score":1128.63,"score_display":"1129","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_53135ec52b36e5ccd955ed0c","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"70bee2b0999ec5cab4b4092d798b0fbb1d080a75a25718436f52677fe4c35aff","measurement_key":"f72293bd3aa62f2cb75d38e38a860b79227b0fdb4bd36b2c386af96c864e0b47","metric":"accuracy","protocol_fingerprint":"3809925a5979fd5445613e7b58fa86405fb820e071fa34c0a1624164881ca6be","run_fingerprint":"05e7a854fed643780920a931cbecd8feef11821de204f3ad784ba317a8d22f32","score":82.576,"score_display":"82.58","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e8c081afa28a4a38e26e8d28","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_5f3023448c2ae4632fe1a43b","benchmark_version":"reported-runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":193,"at":"2026-04-22","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"decc6b5e09456be99db61bfc3196dac55313bed2c73ac3031a3cb7a74a069bb0","measurement_key":"142119a922dbf90a128a65cd2d296b5d66906f1fae919a43b122bbd4c447aa16","metric":"accuracy","protocol_fingerprint":"9bd3fcd30506d02bd2fd6283175199d72d7010226d22784e554ab0bbbf43b033","run_fingerprint":"8bf66fe5ead5c0c61ca5a7b84a0901923b58ddc74248303b3751dc3b5f234d95","score":33.8,"score_display":"33.8","source":{"id":"evals-report-hle","name":"evals.report · Humanity's Last Exam","url":"https://evals.report/benchmarks/humanitys-last-exam?tab=scores"},"source_authority_tier":"B","split_or_window":"public-multimodal-mixed-run-configs","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_dd5b317ecd1d74199c314ed7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"evals-report-verified","verified_status":"evals-report-verified"},"unit":"percent","verification_status":"evals-report-verified"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-17T14:33:50Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"27064251aec739b97f6d9d9d34adde5f9e54624d50af66b541b9bc0018bc8a7d","measurement_key":"255ea3b3b47929b48c40dc26b5debbd9e9c892bcf5404b2297c1ea6afdf96ae4","metric":"accuracy","protocol_fingerprint":"cd0461dadd329d0be451543ce165ca81ac524d86875590417582db8b5908c511","run_fingerprint":"c0a8657a372f1d53876e15d69027514d3ac33939aa9f56bc91d774a7e7f09ee3","score":35.681186,"score_display":"35.7","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8fe48d99b25cc95375221a5f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"07a8f0bf821bf964244eb79a50d5d81f378c390052afe79c05d29a0bfb3690b3","measurement_key":"8f04c550eaef18f5120c3318f874ec5598681cd679b6742b2b714eb694c8b1e6","metric":"pass_at_1","protocol_fingerprint":"0711e0cbafc33a43a7c9043f2ab727348c193386d1387c59f9197403556fd7cc","run_fingerprint":"e7d887be191c638dc3efbabc493d631a44ea5b400e57381b871e4a00f15ef9c6","score":81.354,"score_display":"81.4","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_58d95fa53ab7d749ad91dc8b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e79bde44ef42d1f0fa344b24e2b352bbb8e76a5aff27cae3e84c572864ac1cc4","measurement_key":"2087451e3979538b753b932e6782fecfe8f5a3dace42612a1424d3ac347f0786","metric":"accuracy","protocol_fingerprint":"8e9a33c426fa64de82f744a067d698c830971c2fbe2c88b5aed9149fcb068a0c","run_fingerprint":"b367f207f03d36860f039bb02f4ff2fc697638642d507431f91487afefff424d","score":84.595,"score_display":"84.6","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e23668cebc6abd250154d2c3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:47:54Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3c54ecf29e6a30e3cd12b552160bbdf2d05ce6a4ca4f9beed8124ee58505baf9","measurement_key":"ecfe29ff17b7f5ecfa0d479189df3d85b6fa5055b2fc1df4a9289a77e90a835e","metric":"subproblem_accuracy","protocol_fingerprint":"e77e371acf4336f05f77ff67729676f9e7924a5ae6d4584134e07e7d70528dec","run_fingerprint":"847fbd4846ca3b3e13a3017b757d337ec53024e4604aef10ee2a4f4ec47f7341","score":50.2314814814815,"score_display":"50.2","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_acb46f5b3108016822f0c8e0","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3b228685cd607ba15edf9348b44da33005a7ad6274d914f9668e3f758f116190","measurement_key":"1513d60c3ad7951594992e228e3d8e82847336d11471f22a2fcc5c2c23465ccc","metric":"resolved_rate","protocol_fingerprint":"864652b56c2022f2d0bb0f0d1ec0399044a9c8fec8f1fbfd2a76e5a38479aef5","run_fingerprint":"49bfe323a7a9b888f89260f511f0f9befa3e0bf6f40d27f49aabdefecb734796","score":74.0,"score_display":"74.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0785c90f25f84cb66ec81391","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3b228685cd607ba15edf9348b44da33005a7ad6274d914f9668e3f758f116190","measurement_key":"1513d60c3ad7951594992e228e3d8e82847336d11471f22a2fcc5c2c23465ccc","metric":"resolved_rate","protocol_fingerprint":"864652b56c2022f2d0bb0f0d1ec0399044a9c8fec8f1fbfd2a76e5a38479aef5","reporting_origin":"organizer","run_fingerprint":"49bfe323a7a9b888f89260f511f0f9befa3e0bf6f40d27f49aabdefecb734796","score":74.0,"score_display":"74.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0785c90f25f84cb66ec81391","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9c37c659f201b32987eff894cfee9fb41b5a9c32ae19a45c2474faab2dffa471","measurement_key":"8d9ed300c9a0b7318bc214fafb4edb468ed9bfee5df75b5bd52c61504c8b36bb","metric":"resolved_rate","protocol_fingerprint":"49ad2dfb26d0e8051efe67dd32de507e6b83d1a5fb53f1b6ece7b758fbea33c1","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-05-15/2026-07-01":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9c37c659f201b32987eff894cfee9fb41b5a9c32ae19a45c2474faab2dffa471","measurement_key":"8d9ed300c9a0b7318bc214fafb4edb468ed9bfee5df75b5bd52c61504c8b36bb","metric":"resolved_rate","protocol_fingerprint":"49ad2dfb26d0e8051efe67dd32de507e6b83d1a5fb53f1b6ece7b758fbea33c1","run_fingerprint":"cd7e714afccb62b9c0e75bca9a25f10c60e2f378e0f231976a7859a55918de3d","score":46.48648648648649,"score_display":"46.49","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1fb89a7ed9a95fce8391c709","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"cd7e714afccb62b9c0e75bca9a25f10c60e2f378e0f231976a7859a55918de3d","score":46.48648648648649,"score_display":"46.49","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1fb89a7ed9a95fce8391c709","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-09-17T14:33:50Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c3b9938486286f786199dc72ab674e55d1bb341126c42a5439d955ae6e167c72","measurement_key":"422ba03e4a9b81dbbd478c10fa305cd09b2defa42f4ca70fa128c1e2da6ef169","metric":"pass_at_1","protocol_fingerprint":"66241d651244d29c262a1ee61a7e597df71b9eb9e7f7dae6ccb808ae74e61581","run_fingerprint":"ed630d4f7504cfb817a5183556f0a89e03a2679b5940beedae0d091a7b0fff20","score":9.896907,"score_display":"9.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8fe48d99b25cc95375221a5f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bc3064a201d471fd8b8909cf4a25260efc6a68295e8ec16841e1fc02cbc68d32","measurement_key":"5709d458848141774ad50e9f9e449a2f150bce999c12f2f52ffa76a5d8a2b6dc","metric":"accuracy","protocol_fingerprint":"80022cccfcf77158be6f9c315263156b66d144105405995ab53279ca4f158761","run_fingerprint":"0bad67720ae821797a6148e0a57a51eaa287c2cedfc91a3562bb21207e72c197","score":57.303,"score_display":"57.3","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6690d5e0f6e56e1612dfa415","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"15819126fdeb1109683f242097ec2c563a84cbd6c9424f7da71d79934eb632c9","measurement_key":"73a7ab16342acdae496a478b777616485b40695aa499b7dc88439c602cca91a9","metric":"accuracy","protocol_fingerprint":"ca84380a4024d52fc7d440451981caabab206a341c119e17c9f60894bedba933","run_fingerprint":"d2b5bbb7da1c4ad2df44753b562d9fc244fdcff99344bdd6d5895eb65bf3b987","score":0.505,"score_display":"0.5","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8040fea5627284b131560e23","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f1903ec7ef5f7b5c6ebbcf9681a683aca8c000ca5afa2ef0e8469f956390ea76","measurement_key":"fcc31f32defc4a44199619f406c96ae0cbb714510e85c022a2ae591d23da0931","metric":"score","protocol_fingerprint":"e118ec95a6d19aa65c4107d4979701f48356cc6508659b5054017d4dcc9f3b1e","run_fingerprint":"0b171a0387fcb7b32020d50c57a607cc7cfd01af365f4533e86bf449a2301e83","score":34.113,"score_display":"34.1","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_33eda8b12928b09184788407","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fd35d6d7e52b44c3f770e1e24bf9035352154d28bbda00ce56028a652c6f828c","measurement_key":"704c65afb0e68bb0e04ee1ec33e21e17d5a13ee57d244fe3277165f27e008cc4","metric":"arena_score","protocol_fingerprint":"46b722f1547f93e3f68f5238cd32f974258d8c8948ac6d4c68d410fd978bb37a","run_fingerprint":"b993fc30477771ba347d5eeb0002a35a6d851b6d6a452de761e9fb02c0078171","score":1480.4355329379657,"score_display":"1480","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_acf227e528e7a25cffba9cf6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"xiaomi/mimo-v2-5-pro","model_name":"MiMo V2.5 Pro","parameter_count_active":null,"parameter_count_total":null,"provider":"Xiaomi","selection_rank":66,"weights_status":"open"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5f8722d88ab0f38e798786c92b4d830745db89f24a43fde25ef4c0b7cee147ac","measurement_key":"e52daa2b2d4cacf4cdd6a695efeb9eaa8ea6ab7ac46d56f2ec269cfcaa5b17cd","metric":"index_score","protocol_fingerprint":"5b7e3eeff2eef9ab59ebc6432b2bded7c577fe9bd629cf10ded96f6b139cbfc3","run_fingerprint":"aedd9b98ab97cefd41ace0b279a2b0e34d1f3861f1f40990b6cd67c7cea2886d","score":28.528309,"score_display":"28.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6163e1e4e2e25c4ca85b2f88","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"59c0c49cb20538dacf01ceb6a875e2fd753bb75dbe47b0f9adecfe64271e5c7b","measurement_key":"c4bf51ffe32c0ffb14b2dfc9e1f7a412c73427ce5a4ce19c5b563ef99253dc62","metric":"ips_score","protocol_fingerprint":"017f316bed400a9a52ed55035fbe8bcbfe9a3ece72f6a33b2f6e99c4e2595b18","run_fingerprint":"ea20f19f811fd357750cf487d73241686a677e452918a9967f9d7f674483560b","score":-0.026798104156421143,"score_display":"-0.0268","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_73b151451dd1e7342d7ff672","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1bf8412fa0ea7e29b5bc3a7a0a44f7df84be7d1c44ecdf78cdd0edc624b6a499","measurement_key":"641a914766922013df8807fcccda7ec32c8a955ac38a7cd25e386397cffee74f","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"f551b07744bac5f63daaad9885df9cd2b0e33bfae8162bd0db09d719a92f5542","score":1448.3740011611799,"score_display":"1448","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9f6dcc62a58559d366b17164","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-09-30T18:53:23Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7f55ac64f00a479542ed801832541c15e6d9d213d929e5a3aac424d7a0a94e50","measurement_key":"c0b19287ff39e088dd9a4fa9249e40b84e9f353d78b2a54d156e69a29bfbc76f","metric":"accuracy","protocol_fingerprint":"53d9ca1fce38485bc5d138d525725f6f7fdd90f6c5436209d856d125e2da461c","run_fingerprint":"c2012c1e5f904113d03427dd0150fc24d7a50e0770e34d95f2640dc92464b9d3","score":20.857143,"score_display":"20.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6163e1e4e2e25c4ca85b2f88","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c21c7a4483d870bda24b45dec7dcb1cc24469a91219eb15713b24f7244dc5575","measurement_key":"933c5ad7856e505f014ef2a389b47f9ab91e9686df71a106eed22b75512d528d","metric":"elo","protocol_fingerprint":"1dfa9cf9491fbc336932063c2a6b54081c62a4537427d22ba3c521094f8286ae","run_fingerprint":"ebe293e6c6a4af63f3e96ef7cf9874916ebbe368d4ee0e9f3af548c9e2f86b2c","score":1593.99,"score_display":"1594","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6163e1e4e2e25c4ca85b2f88","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-09-30T18:53:23Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a3366db8bcfea21183b1c52235fb237887b92bec998ed195e5b88fc6ffce74a8","measurement_key":"ff4cf037f5a577f04c2db9f5bc6960318321c187626ff8555857a812b5e0faa6","metric":"accuracy","protocol_fingerprint":"dcf90562187180c47145fec344807665f6ec83362938f3547fdef2b3c17b40f0","run_fingerprint":"b8c3cde3423d1a89b7d8dcfcc3294b6f90a8d0d1aa4eae4c4ae2f8dfa649ee64","score":46.478221,"score_display":"46.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6163e1e4e2e25c4ca85b2f88","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0bd06382806a98c8ae1d3404291a714bb0da39a5da6d1998b08a51054fc2947c","measurement_key":"f33dc238cdf8e89ae74d34958b4c36a005ba5302d9e2ce0229bec86d95507d36","metric":"score","protocol_fingerprint":"369a3d45b774fe21c4a88153ddc53c7161c10fbd09f232e2acfcea71701bb31d","run_fingerprint":"8f2b52c67ddd105f75291254359dda62ed23edcc5d039ae8cbb4beb28ff28990","score":38.056,"score_display":"38.1","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_80831aa0cb0d312c1beaf624","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-09-30T18:53:23Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"81bc742ac149236b1d99143b7626bbf7028df4cff08387bed8e49e23d1015ec6","measurement_key":"5d9baea7506df43518c92b799852db4c3fb50bf75a0bbe74182f3e3e825ade33","metric":"accuracy","protocol_fingerprint":"6b757dbe83d1134f358c6084fb236e80413b45947fa8968d75244506ad7ac8e1","run_fingerprint":"4350372ac3dc92ff71163c4c13cc27e7b793f3637973ea62436d7e8030784754","score":76.358382,"score_display":"76.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6163e1e4e2e25c4ca85b2f88","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:15Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a2827c2706ac74c3c7527a1364f8f03f4e8ed03aa9558d3e0d3a6cac1de6fce2","measurement_key":"1da4d0a65493f5dedfba24eeff8792d8ea2fe639380a89711f12a48894555434","metric":"subproblem_accuracy","protocol_fingerprint":"962f818b99d0ed7640b7d946bb09198eb356bcce789b2edf6bdc6f821c7a3019","run_fingerprint":"faabb805206e8b25a16d375a95665bf2f96057500b134040e442c86d32cde29e","score":58.912037037037,"score_display":"58.9","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9844486f407e9d5626c38e1b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"06c623f574c419d36c31c894caa3cda9223528d79649cd5c0f6af2daaaee75a1","measurement_key":"7e3b030f9947d02f638f837cfe241c13f3da91b2a539f26b6a3ef7fd1d6530f2","metric":"fully_solved_rate","protocol_fingerprint":"a0e657cf73572616f8deda4e80c9873148b55876068435e4c6e0596077de6ce2","run_fingerprint":"b62a3c51f5f1ed7590609511522ed84fdd14f1199faa4322808e6337225910f0","score":0.382,"score_display":"0.4","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_cca308f9e01203fcaa3c0965","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5259e80521341a171279df007ecdf22928992eb307c6dc8e961fff52fa451d08","measurement_key":"0cf81df7ceca47aa0c52636ea49fa65f82d56b99316acd7afbaccf82dd8050a9","metric":"accuracy","protocol_fingerprint":"6d46feb70a5389e6949c036a71dfbea659fbcf1def3e8db0ec0415f044dd9dcc","run_fingerprint":"b84b40e198607408a333845b1a45f3ec46d5e0d5d5d05b450d865bed71ffd4f2","score":31.818,"score_display":"31.8","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_81929620d2e48ed2e1123532","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"218250f99c79754fdb7e8d0fbddb20a6108c8482e2668829add0fea10e0a4a7c","measurement_key":"0405fbee38e6f6249414fc6fd6690eaffa25d086b2fe047c08a2203c8d411553","metric":"accuracy","protocol_fingerprint":"39d88bad143f94079f2984645a9ab692b81d3d240b2832fe90703029f137ebad","run_fingerprint":"3ce8bc3969e35cc52967474bcf9e85506907699907bf234fcdeacf535a5489f5","score":2.857,"score_display":"2.9","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0420341c0f15397d2dec1ffc","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3adeb561eab52844360ad2fae57a2cb3f43a3e25496b68a7f1256d620d57afa6","measurement_key":"9f6490bb6484cbe29dcb2727f312a6d3e9086b197146f953e5d9731fd1230402","metric":"score","protocol_fingerprint":"c9312e0fddbb682fbdc5a2c4fd70cd9ea96ccffd05a50ed21acabbfbc7ef5fc3","run_fingerprint":"1bdc690dc97e33172f043f720d68749a69c631f8e0775510ae5affc98c1ac01f","score":70.399,"score_display":"70.4","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_404128e4ce18921deeb03b6a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1be3fa9ad7c7df12baa3fe24712c023659eb703f5025ac5b2003f344593cc479","measurement_key":"549e2d9791cc2e7a9377140ae55abeeeae00fa2f8c2283cac10625abbf36445f","metric":"arena_score","protocol_fingerprint":"2abf9de703f38c4eccfa33b5d1cd6f4d331467691d3245db69a479e6ca4f6af1","run_fingerprint":"94374aa42b4385e8e0247b0d81746281d7bb77880e929e86536d1c378a063833","score":1571.03868087871,"score_display":"1571","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_eb70fd26c572537944129f9f","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"stepfun/step-5-preview","model_name":"step 5 Preview","parameter_count_active":null,"parameter_count_total":null,"provider":"StepFun","selection_rank":67,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"60fc1de72b26791163f0a4aa634f0fb6627838c8af0ff09e8141862e33660868","measurement_key":"0638138ea83550db301892d7a1a669dd5abfe45e904828138df1ef35e28ab902","metric":"performance_rating","protocol_fingerprint":"5c52cef2c13349fbe526e4444028f3f8d339f3aa4a2cef822aa8893adcb1d572","run_fingerprint":"2e38f38946f4cc91b4bab2288d401fc3b5b779f8b862a51527f73d88528672cf","score":944.17,"score_display":"944.17","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_43f75a9097da6dcf80b67be2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ea18b1e035ddfc0960a392eb8fe20d5ec009e43e9b9aeffd99b08975d5465cd7","measurement_key":"13311603ede80e2f5131e543a2ca2ae485a9f729f03e76219c930a6190145a7f","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"6bbc2652e37e560055fa1e201c7f976b2e4718f41276c9a227d639adc9d1d8a7","score":1441.6307836382434,"score_display":"1442","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3c0b61d8f0225024eaa77540","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:34:31.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3e43081b46f624d7f4ab1d9c088a54fdb174b433a4d7ebbab37c81a334718a58","measurement_key":"4c8cd6225f874e46306817b8195a9c2e32631a5f522ab357965cb19ec59216ac","metric":"mean_score","protocol_fingerprint":"7498cdb388e0f524a643f5988aed656ab57e66bff68d4818eed1961ccb13823c","run_fingerprint":"1bda84316796df226f117fe2dc0e6b3332f4b342e8be880ea80bd7c477f76dac","score":18.0,"score_display":"18.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_a8d922f83837348cb06cd2ce","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0b9737e36142d00c7d3e9282bf2bf1304a814420e1acf339f2302d738ebd8352","measurement_key":"6efffbb6bcb9056958eb0547c95670589a71bfb370d6ae0cae2b1a4b98dcd571","metric":"accuracy","protocol_fingerprint":"532daf285be09e39d56c072e92ae6b14218de708d839304b6ae40f1138330f0a","run_fingerprint":"a734266e2aef9b557287e7012478a2328247549ce6202a171f659d3cc78894f3","score":8.0,"score_display":"8.0","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_a8d922f83837348cb06cd2ce","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6767b730605b106c5fb8ce3cefd54e08c7b65a18cafe6b22866ea055870a6a8d","measurement_key":"0dfe2a7a1206c03e2e87a0d0d4d439b96b9ad01eec537a08324589777a6a125c","metric":"eci","protocol_fingerprint":"6d1afb6719ffaceafe3641009407d50b145d3c5e3c7ad7fd08a6f1003ca70b20","run_fingerprint":"19d42cca2f4a6b320fcdcc1ce4f7c5ff3fafa09b78a9cd83bb7bd154eae9ee6a","score":148.95,"score_display":"148.95","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_59e6bbd0b1c44e7d3a4db8e3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":136,"at":"2026-06-17T17:10:48.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bccc52dd66d20e74ce573005584e52e9b4f2c71504c7bdbf2a7f2b3216f82e07","measurement_key":"cc9c01f3e9c2680775377b31328df7e2baad9d9972976465d2bdec63d055afa6","metric":"mean_score","protocol_fingerprint":"b957245226b13d90d28b7cbd6831a61d6ce276763e5442919988d1d8561d271b","run_fingerprint":"dec84cc91bc62b346a72c1490916eb798274a080c6e5542785e98f4f3bb6c787","score":42.80701754385965,"score_display":"42.8","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_a8d922f83837348cb06cd2ce","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":136,"at":"2026-06-17T17:10:48.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6386cc19316007c40e522a741a7be9a85edde7862ab6abbcc46400b0b1392ccb","measurement_key":"4c6058edd3669497fd0dde1cfc442a265e58fd15a7ad03f6f90519f1b2ae9a7b","metric":"mean_score","protocol_fingerprint":"07e2c15de85b808280d356662611df8d1b6699a3abeb5bc117715cef545aed89","run_fingerprint":"f64418a6589093afd1b3a30b1e57d148176e6aa96741ecba28fc7ee819a85107","score":14.634146341463413,"score_display":"14.6","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_a8d922f83837348cb06cd2ce","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bffc57eff98f789f43c66db20d009c4d899d3181f9a0257effa8280e7589e565","measurement_key":"b3cb9317ad5e3b8531d89c82f737a3d1997999cfe792eb6f5f9efc305afd6d9c","metric":"elo","protocol_fingerprint":"16bd08254293e743dd37f0e558c960f648550062c3ba6cc8a9b8fa980484713f","run_fingerprint":"860fde784ecba1fbbb6c8d84e94bcac910a25f90d5fbce772ea594fa657225bb","score":945.75,"score_display":"946","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_a8d922f83837348cb06cd2ce","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8408f9e21619e5e168d7e1cec5dc44f5fcb6d04076da7ac972e1c781444551cd","measurement_key":"4c9456dc2a6b78531369cc7f923f8a624abf753fc036a9b95664e19460695739","metric":"accuracy","protocol_fingerprint":"4b68b93d0d9f71b5644d6090c793acd555c4ab5b3bd06fdb8242d45e3991d9e0","run_fingerprint":"9c0e897eada1d59bdfb15609425bcc5c0338ec87b62dfbeaf95ebf31868a5969","score":91.414,"score_display":"91.41","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e6219133f7d970918eb71d3a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_5f3023448c2ae4632fe1a43b","benchmark_version":"reported-runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":198,"at":"2026-04-17","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"c630b7051d48f2911cfae02c145a3332b085e2446bd5df0032ebc6bb79681856","measurement_key":"7b156c1aa9cbf7dc37483306d09b76362a166a11aab1138b3f97dd115ac7d44d","metric":"accuracy","protocol_fingerprint":"d0d156c8a19ab9488a31e274e6e36ac05b2a97e639a4aeb7a6342e19708aaf5d","run_fingerprint":"360fc8c58b83e4b4a9c6f42d710d9098d81653226153dfce86fae730a4205acf","score":33.12,"score_display":"33.12","source":{"id":"evals-report-hle","name":"evals.report · Humanity's Last Exam","url":"https://evals.report/benchmarks/humanitys-last-exam?tab=scores"},"source_authority_tier":"B","split_or_window":"public-multimodal-mixed-run-configs","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d2089c665b18a125cc91267e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"evals-report-official","verified_status":"evals-report-official"},"unit":"percent","verification_status":"evals-report-official"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"308166dbd883fcd125e78697d6c71441a548e6ccc1c69c4bf753400eb60c5cff","measurement_key":"3592febea63938bd4039fec0bf5bc1cfd87fabc14e6c754b02bd360484f75c4a","metric":"accuracy","protocol_fingerprint":"eefdd6e9cbbf4533f92c58fad483574dcaf1f14ad34508ad557dac64f444dbdb","run_fingerprint":"f61bb65e81d1b4406a2ac544a8d0ba50ac3639d4ef02152c3ca82b45d59ae7de","score":29.981464,"score_display":"30.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_1c8c583aa239a9f12d2052a4","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6aecd69e8240e7acd9121fc9ae9116cbc5c02b7f3603beadced7d6883bba54e9","measurement_key":"0d749f80ae111900d675d6ca79e40c355de7ed2ba8db11d26257e83053c3f944","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"5b1bf78e46e617917bb9e4ff6152e7a7103c28a7b526832db35ac47d668757b3","score":62.24735714285714,"score_display":"62.25","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_696ee2e03f20836e5b0f3f47","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"50a5f174da125725b79745897a5f1cb44386cca0dd26dd5b5da951a863a91b21","measurement_key":"65417050b0febe7bf5b82760575c11e239b0e0021f3004697f89ee1b279723d5","metric":"pass_at_1","protocol_fingerprint":"e7347e25f2230e98cc2980f50512fd159badf6ca777985ea444e5fe9086f1838","run_fingerprint":"b80813fe58bf3345a261564c9f1add521d0b9c517fb1bfd85c18b1b76535950e","score":84.494,"score_display":"84.5","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_a8d922f83837348cb06cd2ce","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a685eed28666d1c36e8ee18c90d5b0dd9068574f8612f63cf34736d0976ee85d","measurement_key":"ebad5958b63d0e9acf0c3319f190cd9fd25f3604b083aa0845c67ab5d28b424d","metric":"accuracy","protocol_fingerprint":"6b2a3bc18d23bd7aea07d1c6510f91c4558c5f54090d87c2da3523bd19ce9ca6","run_fingerprint":"18b4129fbb8fdc5101dd721f3ba0e3c42b5c4f859c44299bcfb9453510c0be0c","score":85.838,"score_display":"85.8","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_a8d922f83837348cb06cd2ce","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:41Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9bcf0579f7cd262f7a8edac4619900c94eb8761c5454fddd74d25f066cafe196","measurement_key":"69730bc1192e55d81806b659e647c43983a681e5cfc79f27d9944efc1987af3a","metric":"accuracy","protocol_fingerprint":"fe465ec518e4224ab3918fed0b4971447469d1fd105a52da216f494e4c47d9c7","run_fingerprint":"2b12536e50956654118c2ab83d5bb749c36df968c195f95fda720f30eb5bd2c2","score":83.064,"score_display":"83.1","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_01923756939b60f21f059b03","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":136,"at":"2026-06-17T17:51:54.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"02a623af9d34c7fdd4401ca6dd2423000bc41834dcbd506c8db07243ecaae21a","measurement_key":"d5297efbaadc5bd95d143c60d37435e141469c03020417f2930f4335bf8cfaab","metric":"mean_score","protocol_fingerprint":"249b023e199255073505beb6a67e06b60015ca533978a6656bff2f43483690e1","run_fingerprint":"4bff4f49db8650fe0d8e6658c71b34feb8db9f66cd918a11ed8486d463cae4ff","score":93.33333333333333,"score_display":"93.3","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_a8d922f83837348cb06cd2ce","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3a9f7e32dc018bfab33f24d594ef2787f7cbd2b735a607d2817f2108cf955b57","measurement_key":"a4300097dace2e995f7a56aeda929962cbdd208340ae82b2094c810529942f2d","metric":"fully_resolved_rate","protocol_fingerprint":"89f16a602e79fefade7de87d90c75548a0f15b2c7744d0c45e83027c26bb197d","run_fingerprint":"63ccbd375a9635092a9c75d93d748903ac2dde407ef309ef242aeee9863f42e2","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_a8d922f83837348cb06cd2ce","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e781d330058a7ae5162b69a2706b936aa7b69a400b4ca7a926904d9369a009d5","measurement_key":"ec545a3e139192931bc81a3dccc7fd71b197984c0f1923a341fc0548677a302c","metric":"subproblem_accuracy","protocol_fingerprint":"71a10a968bbc9415c02426c9ecb3c26f0e7357061b93d359bcf5302b77d39529","run_fingerprint":"82d2d1a6cb6d11034646d35c09db289b5667657ddbc10aa2f55eea60bb147deb","score":48.2638888888889,"score_display":"48.3","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_a8d922f83837348cb06cd2ce","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:29:33.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5cb539efdd102e2d1a1934c0a6d96b9b8dfa0dffed0102faa56b1ba1d6f98bf3","measurement_key":"a14448fdda5f68c1fa6f266bbc590ab8e60f6f4336134bdd9d11486516f67ad8","metric":"accuracy","protocol_fingerprint":"7d138963618e04aa90455cf99086e6be055208c460d08e4d47a196a53d8b3ae3","run_fingerprint":"05716c1f1dfe5591d015f25270db15ab6d20616dd62ba04387e3fc8b26a1f4b4","score":33.2,"score_display":"33.2","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_a8d922f83837348cb06cd2ce","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"skillsbench":{"benchmark_release_id":"release_093b45b8b752b3f08534f6ee","benchmark_version":"v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":138,"at":"2026-06-16","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4abd2f6114e6b010340b7aed1f880b04e2739459ad08551eda023a56454c5dd1","measurement_key":"5e1000d124627dae5670a2cb1328b03c061a5cfdddd37f38030642e1125d013a","metric":"pass_rate","protocol_fingerprint":"c2ed2025e534826e5e627446f4493a128269710491b35eb2122abbaf19d56304","run_fingerprint":"57f60ac425091578f669e9f453311ae1d584fd6086bd3432b344bab18c4ab785","score":41.7,"score_display":"41.7","source":{"id":"skillsbench","name":"SkillsBench v1.1","url":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json"},"source_authority_tier":"A","split_or_window":"official-87-tasks-with-skills","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_943719f03cd41fdd64848292","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8cb0d7ca73ad5a104e355bf9f5df33a17daca84b1dabfb87179da2656830b707","measurement_key":"89e874bbe66183647d6fb6112573f58fc83df7451c4be8e78b52882d96d07582","metric":"resolved_rate","protocol_fingerprint":"05f2f7c4256d37844f23af9f6c45dadf2965a17e3370401f36db17a53ec5bda8","run_fingerprint":"fc3189a38d72abdc5e53ef1bd99a0196b57f60d3e59d721e079aa2ef6a2d0aab","score":71.4,"score_display":"71.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_a8d922f83837348cb06cd2ce","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8cb0d7ca73ad5a104e355bf9f5df33a17daca84b1dabfb87179da2656830b707","measurement_key":"89e874bbe66183647d6fb6112573f58fc83df7451c4be8e78b52882d96d07582","metric":"resolved_rate","protocol_fingerprint":"05f2f7c4256d37844f23af9f6c45dadf2965a17e3370401f36db17a53ec5bda8","reporting_origin":"organizer","run_fingerprint":"fc3189a38d72abdc5e53ef1bd99a0196b57f60d3e59d721e079aa2ef6a2d0aab","score":71.4,"score_display":"71.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_a8d922f83837348cb06cd2ce","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"01fed700a602b4c34b9974c0c629e2b5d8172cdb9bdc91b4c83632e477147dc6","measurement_key":"9146f6244d3f8d126dbb5501a8e92d7c3716284538c9a1193578a47b7f069ffc","metric":"pass_at_1","protocol_fingerprint":"5979f397674c22e4d08500584a4477e8b0036be8b47e06f193d5f083b6fe908e","run_fingerprint":"27b6d9605ca3c250fede56c8ed7068d55f18ac8c0b8e14dc149b117c01941d07","score":8.041237,"score_display":"8.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_391f84c7bb85d165acbd4de4","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6e06b64580915813b127ebb480166bbfa0ef3f77de609482500ff4a9e882d2ee","measurement_key":"eeceab1b96d7ef15db8d53bb13c94d1aa52a63c13a84ad9d513bc03d6117437b","metric":"accuracy","protocol_fingerprint":"d137423a0a3d6a26a943a469a87ef0a01a4b82cdf1ce9fd345d6428c46a4a778","run_fingerprint":"05e25410ce508f0c1b07046009a2d6f6f7fc2adc1145e176f1042837f4026204","score":41.948,"score_display":"41.9","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_a8d922f83837348cb06cd2ce","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"814e467bd261d8c2bc0f6ce6907a476aab1d5e8a9a0e81df3ad824b9e73a1fab","measurement_key":"9eb8e9207f6d17fce5485dfc660147e98032057f0e98c92fede51a12c88ab2eb","metric":"mean_final_balance_usd","protocol_fingerprint":"d34d1ddb40f3254c5f4a21bb94521538b32d1bcefbbe4a019858898e629aef75","run_fingerprint":"160041ab370d6a12c15c955b821d7a073e1737ab7831c5581d65e507faa70cf5","score":35.26166666666665,"score_display":"35.26","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_10dc674a660bf5857afb18fc","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"02e3723848ac242e157111cdfc3336cd9a19dcc7eaaa9e7abc20b043e87aef5f","measurement_key":"f7fb05ff168ec502b68588fa1c02e599d14fa7006ba991b0746c75ec60862dba","metric":"score","protocol_fingerprint":"204cbc04af485f500377c94016fd006a739dbf90c5c43039b4003500b74a4589","run_fingerprint":"06a3f30fb2cbe6965793834df09d861131e570d7ee5500872634627d331b4f67","score":19.403,"score_display":"19.4","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_a8d922f83837348cb06cd2ce","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b7f24910585f93f73791a4fc8f3fa8c61b702f4ec94335f96be1cb4943290be2","measurement_key":"065fa82117d846f165fff090581dbc882f2e9085232713ee36e7ef15ab816b3e","metric":"arena_score","protocol_fingerprint":"d59c63c4ff5944ac07f08a439182eaf5241f00ebddd8932f323a2b4232ac1f0c","run_fingerprint":"a2672a7b3292e5650e8adc663d961953449954337e8b72eeccd068cee12a0e07","score":1357.5695879962777,"score_display":"1358","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_88f0aaf5c213ac8fa693d6b6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"af07d1102510098898f80f75f379e8cd20bdeac356351647dcef45b360039281","measurement_key":"04e363479e99ec734744e7e6bfed152a44f0ae341a99f3816877028053b12e15","metric":"accuracy","protocol_fingerprint":"6f35a6ba42aae1245d3d9ffefa92a51ab123b07abc7377cca91a179998927e5e","run_fingerprint":"924bf460811680cd957d0e42ae4060b4a39b3f74dc59a743aa83ccada6fba782","score":49.89,"score_display":"49.9","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7774caf4dfcc1695a2cae560","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"xai/grok-4-3","model_name":"Grok 4.3","parameter_count_active":null,"parameter_count_total":null,"provider":"xAI","selection_rank":68,"weights_status":"closed"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b5247cf05973005e61469b5d09302860947e52fbdca5e1748b921bd916bcbdff","measurement_key":"d96598e93d2a211f895a5123f33bd1818c619d8e5c28cd8e03a78eb8b0c7844d","metric":"index_score","protocol_fingerprint":"40bdf6a667cd4ddcd96a1096d2b6ae84a7f744cd7afeeb17b8991346d4f7aad4","run_fingerprint":"52c868039bc53144de246dd3ca96fef81778eee7e6f393420be9e79874d4f165","score":11.656346,"score_display":"11.7","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2b05f8827831fc092f12f06f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ad4372e6efd0fced1e7aaaab6a79634d626f546caaf8ad27b06890d3ab3a478c","measurement_key":"297f54b19ab7a93c425fed3e7fc360ddc7a9c6f59cc1c36981c31f4dce0eb300","metric":"performance_rating","protocol_fingerprint":"348938f38e06c3caecddd546cc73a045febe8ba29b77598e5161c8e6611427f2","run_fingerprint":"b1d950b527047898224bfbe0e07e690db31222c68a0267fdfadcd17100831e51","score":765.27,"score_display":"765.27","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4ffb600ecd36bbcb9902a5ac","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:12Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2334580f6eab47bd3815c82ece7e8b3c73408cb9c6fe5533a0a5ca18915a7c30","measurement_key":"e5f43ccdf707d735d4c72c373df12fdd53f8fdce1406ff052286e30e7ee54864","metric":"pass_at_1","protocol_fingerprint":"d5304fcb71b69961e463378cd326f65f4c89ec8e98dfeacdc7a30bb9ffb09643","run_fingerprint":"4c91deb89989f49b1ea720879980e9f1accf383709ee1bd16f440f3529a6ff98","score":29.300000000000004,"score_display":"29.3","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_758dd5bfd286cba45f679ea1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2274e344b0e7cd972ee465aa0248050a38c6804c63310fbc367a075166c56579","measurement_key":"b30a3f0fe46c0157977ddd160016bdc1b05a899746880d278331c002cdea407b","metric":"pass_at_2_accuracy","protocol_fingerprint":"a393ad5a030262b708816637dea83dd77cc9a95eeaa58236c8ac0eaf5ce4da59","run_fingerprint":"8f67af6320136f380c211ef965edcbb277402bd16367b18a5da551774fb8bcc4","score":53.5,"score_display":"53.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4ffb600ecd36bbcb9902a5ac","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"32c376a7c16a467b1bbb156108d4b066a54c70affae32ce5e62b9a6874b12a9c","measurement_key":"4333198957e1571dd849f18e0c61201bf7870b79b8fa80d72ed92a110240b6f0","metric":"accuracy","protocol_fingerprint":"7b05fe75cdb7f2a11f099e9b0f6748abdaa81040fcc26e106ae9ac77eea282ce","run_fingerprint":"b34665bb70682468cf75eab864dc037ea50fb694c0d5478e04b77ff4a850e62f","score":10.277777777777779,"score_display":"10","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4ffb600ecd36bbcb9902a5ac","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f37c27828b2411878edfcaa5f15c7ed9d1d4b4d03943485a394a41087ff84615","measurement_key":"a6419fcfb43458971d25402f3f7fdf9e8c2398f8d5664ab29e095675530c36d3","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"8173e7338fd095d8af40a8be6526adb319620a6b0e26ed5c5878ab5b741007c6","score":1455.6556795012555,"score_display":"1456","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_bb75ca61c28fd70310b7ca1d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:26:52.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a51571488cb309793cef80e307ff6f3a7f3f88a84800f279dd40f1ee7a49e528","measurement_key":"d2b38ab0f434ac113783c4d5f2c89516cf6ff63c67e4fa5be899b35e1e243059","metric":"mean_score","protocol_fingerprint":"12087d4d9063d130367faa3690a4c04c4d8d32c83607d85273de2251a4ffd6bd","run_fingerprint":"7b247c0101de440729abb346cea39cc820c526cca3c48ea71dd3d36838df5049","score":16.0,"score_display":"16.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4ffb600ecd36bbcb9902a5ac","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5cf27c4367106e72bcf4e24f7f5a418479b4837f5b5ebefca43f2ef576548dbd","measurement_key":"98e3e61d96093c98d582600b366d1983bd5b0ae06ee12ed1ea08f80529d13781","metric":"accuracy","protocol_fingerprint":"9b6a1108021470160fff32d4495f470eb3e033d9a36ac83f2e28d9d3ff4b8cf7","run_fingerprint":"5baf0b4e9406349a3d35084b09b1946ddb5318f78141f6c31699b906f6126307","score":0.0,"score_display":"0.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2b05f8827831fc092f12f06f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b4aee8f65dba534e3fa5580adfe1dcd8997560b3584fa172bef7973aa5c1918b","measurement_key":"166b80a8719ed80292c750b76ec7c2bf443eb552e5dc1ea48da4857aa508bb66","metric":"eci","protocol_fingerprint":"183ef5bbd8fee695abe6f30f22f05eb823283ef3c76b75a2020e2cdf06f5cc37","run_fingerprint":"222620fb9dd72a81647ca70917ecf5069069ceddb7bc7baf7557b24802ae7b83","score":144.97,"score_display":"144.97","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f87c6a70e804aea75a8cc3f0","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":91,"at":"2026-08-02T01:20:17.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fc31335e017339769cbb8397ad6342d813532b875e3b15849b40697b99df3bc9","measurement_key":"8df6d2b0e676e94fb98ae944f31e1d56b557de1b76fc37a68118fd5b56fcf8b6","metric":"mean_score","protocol_fingerprint":"7243a9334d237e65559a5eccb07320f679a3321dc0cd08c2f02302f8aa71cddf","run_fingerprint":"9d062ea5eefc098613ca9363f3bb672e378a17a8a951413f37b615946edbd30f","score":25.964912280701753,"score_display":"26.0","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4ffb600ecd36bbcb9902a5ac","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":91,"at":"2026-08-02T01:20:17.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"869a1ea366740bf7cb03ebdfe6255ddb8317cad2fcfbe2c7f4e0e56ddb2d68c0","measurement_key":"0584a61e6a5241831e8e37a4f4f263951318377d3d0997481814aef337b767e2","metric":"mean_score","protocol_fingerprint":"34ca0cd997d4eb6e78ce323fa6abe83669f340371db64e91ba8daa4505c9d13f","run_fingerprint":"b72bb3e649c29cbac1fabeb16dbd98495bbf1ac44b2dd0e81708e60ba976895d","score":0.0,"score_display":"0.0","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4ffb600ecd36bbcb9902a5ac","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"486b432ba5a258700ac96e0b008ed6589176c419d57530695605e50a6100e3e2","measurement_key":"2a883ae938ed2ca420454e271dd67ff6d307651405263fe5b6601862be7a1aa4","metric":"elo","protocol_fingerprint":"63b033b05ce51610e40cd20bf8cea4a045f2bf35d7db9c6f66429e788187d2aa","run_fingerprint":"8db2a11e8103726102be6e05093db24711150a94530fa2c132a7f76a7fe50360","score":994.52,"score_display":"995","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2b05f8827831fc092f12f06f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d5b2e674ad4a3ac6809c0acf42099634fc3371a2fd6b2acf4748ea1e8549b65e","measurement_key":"1b53221f2f0de5f0177df85c37020505919e0e0a6028f52d6141e3ad496ab6eb","metric":"accuracy","protocol_fingerprint":"bfd0934f0fdd6356dc91ac83d1c0c6e5d27c68469b95969f85826652ce5fa3c7","run_fingerprint":"f859c2ac56fa949b22ba6fe50f5eff44cd0ec030c71dd6aff5267c3a6c3ee986","score":83.838,"score_display":"83.84","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4ffb600ecd36bbcb9902a5ac","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"46608ea3ed41999e70a813961117b0330e306e8dc8a225d70afc2de0b83af97f","measurement_key":"2040a3a16200094cb466b64756e91818bb1c7f09ef116ef2937b4f527b8b0a3b","metric":"accuracy","protocol_fingerprint":"e755250c6a771e29007daeed1c9bda129d6a0ba401149b0194df6c01c47516f0","run_fingerprint":"8be0be9ac29fd521d7066d62759f2d8f485e41573243cfb233fd19f1ee8cb136","score":18.813716,"score_display":"18.8","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2b05f8827831fc092f12f06f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f54aece242f5a0cdad4a01fe4a9fe2266879e60cb313c0dc66376909d352c293","measurement_key":"c81110949bd460a25c010b8dbe2b1d5d9e8f56c96e1f6c0230390fbc4ecd197d","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"911666b5a072bd9578610804e5389e232c10328537b47c55174931588443da54","score":63.9369880952381,"score_display":"63.94","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4ffb600ecd36bbcb9902a5ac","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"51f31cfaeaf7d98a9ab2b87d6a3054db565801f407a1d7201d589d84f2e8fd77","measurement_key":"42c480e21313d63b442ad331bf3617cb69299c4f446f097dbab36365f274beda","metric":"pass_at_1","protocol_fingerprint":"ca9fe315645eda54af70f86577254ffb901dff50419cbe4356e6470170c36926","run_fingerprint":"1a2a1deb2e6b68f2fe66f4a45444deceea72148719acb9945cc3660a50d312f6","score":79.014,"score_display":"79.0","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4ffb600ecd36bbcb9902a5ac","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7545fe023e680cd7fbfc22170f6c3d1048905f1ebcce0a4fab3114a1f9039c36","measurement_key":"0f699355da17e80635db6d850a51128c9b12c17fac0459e5f7448083f209e487","metric":"accuracy","protocol_fingerprint":"d89924958304a9eebafbfb87a22248d405abd0873e58816a47bce84c5cba35fe","run_fingerprint":"215b545ea3f12af12a5c92c33e3b3fa8bbaab3d46f519d22c8829bb106ac5bda","score":85.836,"score_display":"85.8","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4ffb600ecd36bbcb9902a5ac","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"652362f44bf83a77eb349cfbc5a25d1fe51c6eb9f54f47d8f0444951840cb231","measurement_key":"0668663094e03d74f083ff492fca07fc130ff1bced79bf06d9362e86001753b3","metric":"accuracy","protocol_fingerprint":"05654b4e3ebd298ec818a7e1cfb6b89a15bca8e14b648030b13070f15d3d6e1a","run_fingerprint":"26d8978253e18f2a86d1589f576663bd7666fd0cba79c17f75c166450a5ff25e","score":83.584,"score_display":"83.6","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4ffb600ecd36bbcb9902a5ac","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-06T22:35:36.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"33e7c34eb631a8cf0aa484d840a374ebbbffe868ea937e996d8a0e20a5fd0968","measurement_key":"ca6f9f15a1685bdcf8098c3a4404d40c5c8c416fdbe5cf2ab74f4ec5e0b740a9","metric":"mean_score","protocol_fingerprint":"f7647352e260863b823a88cb30a738a5bb8bc76b558091650db4b364c51f5230","run_fingerprint":"2c03e51daac3816c0dd5741a68c904ae14335644ac2a11c7a53b8a9a1948da65","score":71.11111111111111,"score_display":"71.1","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4ffb600ecd36bbcb9902a5ac","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f21add701696e052df7aa01cc49a452fe40a2b7edc039211620c4c7663a640c3","measurement_key":"5912ff28e0703a8722d51e1b88838a09f74e4e3e6ea62e1ac4f44f5e9c5ac5d6","metric":"fully_resolved_rate","protocol_fingerprint":"9abf9eefe0749ebfbdfa6c4c8991b89cab0db509f96c2ad07fb75e3b96163dfa","run_fingerprint":"841e031abb0e83b0b58981b0548c736ab2fd3674fc67eb1d7d6ba87351a7c49b","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4ffb600ecd36bbcb9902a5ac","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:15Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d6531c184215f77cb855bc350f8c852174b91e7335f4e3563c1d57e0021d8c87","measurement_key":"6092b5aad38bb45f126baccd7a8dae2f30628dc678be10f262545e4b6f449140","metric":"subproblem_accuracy","protocol_fingerprint":"5c18565f82b5f82a99e1759dba12b495cc395a3909714746dfb5548dfff967a2","run_fingerprint":"8da0a21f26c70355ac3df220ea2fee6a632f6052308dbd1620459e88813aaa69","score":41.3194444444444,"score_display":"41.3","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_5ebede4cb3502b6a8f56583f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_ccacd6f679c9142b534364b4","benchmark_version":"task-v7","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":101,"at":"2026-07-23T02:56:47.235286Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"181b50a814e7dc7f9d86514074e89947dd00afbb64cce2706ade0f862ddaa0f7","measurement_key":"50108c29fe61cefd333c3559a249940f50877d847915c18cf57279f889ff8595","metric":"accuracy","protocol_fingerprint":"82f77751ebf4e0e1bdb747f60520ab845ac1968d26418478e88298d4c1f1b07d","run_fingerprint":"21ca1d3e894829c9d31b3be87b5a932962f299a76c251de4a40e69e1784a845f","score":33.081190115985876,"score_display":"33.1","source":{"id":"simpleqa-verified","name":"SimpleQA Verified","url":"https://www.kaggle.com/api/v1/benchmarks/deepmind/simpleqa-verified/leaderboard"},"source_authority_tier":"A","split_or_window":"verified","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_995ea331927f1b2b53b092cc","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fd4238e933416eb9b77b07f09d54994cae91cf71ebe116fbad15ce81658ed7a2","measurement_key":"f39e6369eaab261288dd0fd9007f7300facc1e59fac410f8af9d113ddf0fb97d","metric":"resolved_rate","protocol_fingerprint":"aa9e5fe5595971340220fbe22e04bc88af750823bc50e2ef1279d67b99b763b5","run_fingerprint":"87e54aa74fa9fc63817933306ab9a21515cfabfbfb6759b7a393b47750cee0c8","score":75.0,"score_display":"75.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4ffb600ecd36bbcb9902a5ac","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fd4238e933416eb9b77b07f09d54994cae91cf71ebe116fbad15ce81658ed7a2","measurement_key":"f39e6369eaab261288dd0fd9007f7300facc1e59fac410f8af9d113ddf0fb97d","metric":"resolved_rate","protocol_fingerprint":"aa9e5fe5595971340220fbe22e04bc88af750823bc50e2ef1279d67b99b763b5","reporting_origin":"organizer","run_fingerprint":"87e54aa74fa9fc63817933306ab9a21515cfabfbfb6759b7a393b47750cee0c8","score":75.0,"score_display":"75.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4ffb600ecd36bbcb9902a5ac","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5debe262168dd44de0fcddba32f81a57be781d2fc75c5b778153ef34ece73ad3","measurement_key":"525b3fef17f82e502321b5801841249c2f09bab8993e0a6b10fe25a4dd7374c8","metric":"pass_at_1","protocol_fingerprint":"3c201b2860ac1f5c9ad90c3bcf78311507ecb897dfc7b7b46841a6fd00dc5189","run_fingerprint":"c35eac79b163d4c679c30ddf540615168b0b84ac2e41c2d1875db00328826677","score":17.525773,"score_display":"17.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2b05f8827831fc092f12f06f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"19d8528ef2b2bb69218dce143bf36a28e3a317f411e1569022467c5233ccd020","measurement_key":"ebd8d9451af671e30d24450c95b5b01c445bcd2a2e75ce5e730925a40562642e","metric":"accuracy","protocol_fingerprint":"d845ffefe50ab4a3d375a7c3e115002ba8f871c41bce3736426fa2357577f157","run_fingerprint":"f574795f4dd0a374f74aa4fe0797e7b931566b5fe4f43fb745c5dff258e097b5","score":50.187,"score_display":"50.2","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4ffb600ecd36bbcb9902a5ac","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_b7d9ab744ffac0cb856e114d","benchmark_version":"Terminal-Bench 4.0 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:17Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d5c467da9776a576f47100b625718c94ae269b0a4bb9cf18f60d16818c79511b","measurement_key":"44bc12a93fd06d89daa1f4ebb830502259bba4210d78d40af3c6a1999670412d","metric":"pass_at_1","protocol_fingerprint":"bc2584ee2b1d70a51115d84c9443cb0c62b455314bf6459d923694f68755b74b","run_fingerprint":"eaebc47cd50ae0a465bc7aa6fc2d04ab5d16cfbb1b4002db6adc0f4ebca8082f","score":1.010101,"score_display":"1.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"mini-swe-agent-66-tasks-500-steps","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2b05f8827831fc092f12f06f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a6f8667f649864b4dd928154687d5ac8d3c294642349cea4d8e3eb7d60f686dd","measurement_key":"f7d74a00415085eb191ff1be4c6a7ed7a72734752e64aac1cb4343371b06cec7","metric":"score","protocol_fingerprint":"b73ab4c87960bb7c86dfe9122c3ff611cb904a916653756e25d59c036870a98d","run_fingerprint":"f55e5d442e0f254b0a80a9e97e3da0202204db86e439f86b52129b51b623f412","score":37.161,"score_display":"37.2","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4ffb600ecd36bbcb9902a5ac","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2bb4653b24b55c578958fa7607df3233c4003dd2ee6b941483e911148f1f4ea5","measurement_key":"fcc9565df83a51b7a7c3ee2158e395e5cbe93bf35b143727af56c22d079a8f8f","metric":"arena_score","protocol_fingerprint":"2d298ea6c3afaa5a6794d24a79f426abd0eb6c0bc9b0191bce3b01e6ac94f245","run_fingerprint":"924e4aa65450bd400b72adde232e1890a10448658efc7a10dc7436b6b85d71d0","score":1434.0835335612885,"score_display":"1434","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a7f1f18e36f8a6a9774d349f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4ffcf323b94c054588f77379e240a666f9f0ff8b295484025885f542c73264e0","measurement_key":"cd718d3c6fbdd4ca1e49dc7968736b795ce3e9d8e611bba044faebb13d95e35b","metric":"accuracy","protocol_fingerprint":"e4e6c29684eeb5a121905f301b3c516feb86f2bdf63f3e2b92e356eebc3124b2","run_fingerprint":"e1aa43f8f7d0882e6ae650522438af572dc13aa697ebfdd4a78e6de06a44d778","score":39.0,"score_display":"39.0","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_4ffb600ecd36bbcb9902a5ac","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"google/gemini-3-5-flash-lite","model_name":"Gemini 3.5 Flash Lite","parameter_count_active":null,"parameter_count_total":null,"provider":"Google","selection_rank":69,"weights_status":"closed"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2be7f1bda3d055a992860409e0e321bd2bb0206f088dcc2972d401c065b0d932","measurement_key":"fc8ce16d7fb5d76e4bd65fa8f56acf9c7198fc8a3b43083d95c1cc0db9345aa8","metric":"index_score","protocol_fingerprint":"3bf450b2dd1feff000934cf551b37b7f81711a3a0a5ea6ed60c74ec7ed05b81e","run_fingerprint":"080845a64d5974db2183dbc5088fc76e61a547925dc866d406fc777cde09b608","score":26.727698,"score_display":"26.7","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_85514b3a25f5a223df6b29bb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:15Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"324a04a93cbbc9576ee03383be7c15183778d436679ea42b9b01a5dcabecca47","measurement_key":"4541d5c716b2cd9e27aaaf683ed1bc301339e46a964cce7713eaf243113de7eb","metric":"performance_rating","protocol_fingerprint":"5a6b3a426453768deba4d814ffb61d584a908b763ee38409283890dbad9a453e","run_fingerprint":"8d30b63c729ac2369ac4dd3505ec5edd7f024ec67a92805a1bbd7f18c2a9d06a","score":1244.2,"score_display":"1244.20","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_5490b7be6211e893b364b100","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a47cb7a1aa6570d18ba1e650dc843ffafa55183c7c8c6921eee4c4c7842524bb","measurement_key":"7a0b2eeaabf1d98af77eb53248dfc630ce3fe76e124d8ebf5195d271d23c3265","metric":"ips_score","protocol_fingerprint":"c80fa6143e1f9af5d878a5781010e2f6af34c92e5532c8c158c4704ac6a00f35","run_fingerprint":"b706554cde71f784e0076da8a95c57ad7d4983ccd2ba8fef81a0ab56ae968e05","score":0.010018747709004657,"score_display":"0.0100","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_424a25c5919bec60800d439d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1e0bd8b76b1608902fe84d623edd17df924615246ceea99a8c8d6b2ebec960c9","measurement_key":"b3a36655049471b8dfcff6ed8be01408d6ec71e18f87bdd974c6af49d4d437f0","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"79fccf891070abbf4d6a53557d63ae09de3645acc87550ecd803faca9406d714","score":1447.5919518386747,"score_display":"1448","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_739d929af0ee1a5fc9f85891","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"02c446c92dfd371c670fc90cf8e5da5bf16b9e999e82dcf6f3b0e83ace5cbd2e","measurement_key":"ae4e9e874dc2d9dc328d5b8d0718f1d3b6e80b8b60db88eba9578047bbe6896f","metric":"accuracy","protocol_fingerprint":"1050d57b8c90ed84f807e77aa6b64b932ec998855a4d549f08517dc3027004c4","run_fingerprint":"5ae5f6577c022433e40eedda54c3de746ecb0486628b7c84fcb891498f6506ac","score":12.0,"score_display":"12.0","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_bfb973c8007511c06bf8df90","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a4147b7b426c5b38a071d58f03e5613bd076ca3434a1b0ed1932f92931c84460","measurement_key":"672b147c5d8e161ab1a03568bc4351947ac93c10b401afed4aed267c3c2a1547","metric":"elo","protocol_fingerprint":"e85ee6b2d9029d8f4ce994bea4c51ffbee42fd97dc88b4abdd92ef41bbff0892","run_fingerprint":"b91c296b80710f445a63194adfc9592bca1732f15fdc78910d40e09e23fc80ba","score":1613.56,"score_display":"1614","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_85514b3a25f5a223df6b29bb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-09-30T18:53:23Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"04eddba024850f557c65f4277992fa6257f961b280fd458a5bda6f263c823f1f","measurement_key":"125aafc4ebcbcda61bf622b714cf6316a09800ef222615afcb4eb29e06c8eae6","metric":"accuracy","protocol_fingerprint":"aea26be14761d30a39ab6b42b63bb46cb2fae5b0fd9b650f34348b2703c4c087","run_fingerprint":"4d92729d52d5931f2ebe4f1ad83280c3729b2f55f06aaea675a6af53fc8e9039","score":35.078777,"score_display":"35.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_85514b3a25f5a223df6b29bb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0cb9282fc63e3e90337bef30b1fed29bec111af2dd186bc1efbb8287283e1bda","measurement_key":"c6472831c3ebfe1b96159907952d14aacdaf4c7dcf5d7fb52331f962fad8ac5a","metric":"score","protocol_fingerprint":"816d6eae1ebf10635f84a86541436e36d196b04b5c5e2a0a99cd146a7d60f7e2","run_fingerprint":"c4e179d789daf3229b50ea57c4ddc1fa2492a714b2e4d8958b870f36ae24ec95","score":47.667,"score_display":"47.7","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_776318aa95331442d0fd0253","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":31,"at":"2026-09-30T18:53:23Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7774e0b99c9c62dec712cb62fafe9a63ef95e086b6f3aa5a70e39545942500e3","measurement_key":"5af7e555861067f14e01b15063019e772c32842ada1077a76fe13fa17439ab99","metric":"accuracy","protocol_fingerprint":"cf2ff18e1b5ecba733442cfd8e208da258dc1a2f6499599c3c76451eb940d3ba","run_fingerprint":"463f97d62c75a15bc48760067072079ad7f3ac4fdc1c19ee691e95b7702f8b79","score":73.063584,"score_display":"73.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_85514b3a25f5a223df6b29bb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"485bb0c3bb26790c8e37fc8f784ebf3048296db8d972b442b7ee2bdf18790c78","measurement_key":"41bce2b019091985d133ab31269c32f72a4389208a81590d86321d507c57186a","metric":"fully_resolved_rate","protocol_fingerprint":"d9f60bc8654ea0e1628e7e3289c8331050f3f8f48b817fd4bba45e839b47f4fd","run_fingerprint":"0867649a356cd073bc02e83859258af19824d0f234848fd0b34a84abca9aeb34","score":0.5,"score_display":"0.5","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_eadf3af797290d105cf76c8e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":23,"at":"2026-10-08T22:23:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"05b1db6d8f615a037140f214b2110fa18dd3a5c1269edbb0f8562c0fe18bce01","measurement_key":"b04854561ca0cbd106ebd49df4299fde2add9350cffb89a7734c7eeabc624ee8","metric":"subproblem_accuracy","protocol_fingerprint":"9e501f129cf1e1080e78fd9cb2d033d7a045901f2cf39b03ca8edd6114573b8a","run_fingerprint":"4b770f6a6f37209f82eee9fcfae9260a186e55ca8d67527e4699926fd4da4d1a","score":51.273148148148195,"score_display":"51.3","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8e4d9e7ee373f6ab1750d0b5","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"sre-bench":{"benchmark_release_id":"release_a9585b1cd27a4b33eda715e1","benchmark_version":"Vals SRE Bench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4e52ce2bfed51e18b77df8baa7b603d4356041e91afdb65e7e12423d1ef34d98","measurement_key":"42cc6dc6fdb259cb376afc0b5edc20d85fb8de43136a87cd2b2faf6d2b265d23","metric":"fully_solved_rate","protocol_fingerprint":"aa4e3ed0a0beaa2f06a2c3ca5954433150da479237e154a773904b2ec6ce4efc","run_fingerprint":"d0eb2a5d598d9270fd3d2e8a5235592f2406ade2fc78fe2d0f348fd9a724f1e9","score":4.198,"score_display":"4.2","source":{"id":"vals-sre-bench","name":"Vals AI · SRE Bench","url":"https://www.vals.ai/benchmarks/srebench"},"source_authority_tier":"B","split_or_window":"vals-sre-bench-262-instances","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_5c611f9309d05bc666dad304","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8e2e6e77474abed64a3c1e7cb6e35b7034e7b64f9a90d4364aa3e95f4b03a76e","measurement_key":"afd65aa22f3eda924da136538c7cb0a2d2d8ed7f5a942507ce2b91a03bf66585","metric":"accuracy","protocol_fingerprint":"6fc864e40cebd502d9f799e4542b5511049d094fa47b1498196d1633ec0e87c8","run_fingerprint":"6884861417ff9e151c07721716944b360c60dfb5b49fe2b6265cc8ae9bfce33c","score":76.404,"score_display":"76.4","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8e264e308d488f525e186738","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5db187ccf612b7aa53f51eb657914cc2f3819c21b9e6067333eee2f58ed02790","measurement_key":"aa74ed4edee309bd45343b938d3890cbc5898e1fb8008ad2dd1ad9869133ba13","metric":"accuracy","protocol_fingerprint":"99bf38ddec6145befa84c29e0243621e4d84ccbcb32e938073dcd741f245bd25","run_fingerprint":"c5a25741dbbd99b2e7091b76950a28d2584ab5df57b205e53192244665bfad22","score":24.242,"score_display":"24.2","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_38513e9f4527d51f190d8a5e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-science-0.1":{"benchmark_release_id":"release_80cc5f4700134aa978bd968b","benchmark_version":"Vals Terminal-Bench-Science v0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3428f07102013f2d0b878a6ffa109eba5af21d784c603beab21033bd6a320a38","measurement_key":"305ff2565eebaf1a777b6d133a36fa2943642a09b13f2861168115e8d09ff231","metric":"accuracy","protocol_fingerprint":"563dc32a594b288031d313c17cc3020c7b37c9e9534771c7976ddea246877458","run_fingerprint":"5e38a6ea2a8bed1e649f56a18037e6027ae8f15503cecbad01c52373f2044b78","score":4.286,"score_display":"4.3","source":{"id":"vals-terminal-bench-science","name":"Vals AI · Terminal-Bench-Science","url":"https://www.vals.ai/benchmarks/terminal-bench-science"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-science-0-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ab8ab28546650c918ceeafb1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1d1e5c8fcc5f6016d714f32a5314cb28d89659b2f125e286877f66c160f334f2","measurement_key":"6a6bc62234f7705bf678692d206fadc73268c26bf8a85552e37e1d5ba7d02881","metric":"score","protocol_fingerprint":"67ef5e00df3a20560d2e2b5b4a98f178727c194f4d899c4f4b2848b1dc0005fa","run_fingerprint":"526682c16d72182ecb799a5694e6a1ca0ece9d90707cdf70d973ced5ae765d44","score":78.96,"score_display":"79.0","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8ec17d78c34548ea7a909552","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"63a76c9fe98f80f327034007759c7940cdfa95fe3786ab9e8a7125f34c3409dc","measurement_key":"d790def8e0478e4728b2c345eb0e670d610af331e65a2110ea6341552bf09486","metric":"arena_score","protocol_fingerprint":"9640fb9738a199ce26e690d635ffc5df763f7c504ad2a0bee69d72f5b54ab48d","run_fingerprint":"16e94eaf93f04bb9dfd53ef559eb7cca17cc84a41b99ccc1dbc657e5d1b5fc7b","score":1637.1737027632755,"score_display":"1637","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c68b1d0ccaccba0c7b04181c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"xiaomi/mimo-v2-6-flash","model_name":"MiMo V2.6 Flash","parameter_count_active":null,"parameter_count_total":null,"provider":"Xiaomi","selection_rank":70,"weights_status":"open"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2195b1d82563cdef379e6c73e7b4b7da83b295c1ed9a6d13ec931501a8f898bc","measurement_key":"a86224330c452e914bff79fa842eea0c9c15b8020dd975c652246e58076278ca","metric":"performance_rating","protocol_fingerprint":"dc65d046db4bddc92135c312fd5d0df89094887ab9bdc53dbe4190c45af29f24","run_fingerprint":"85ed3fdddd49caf8644347352c69a8dd7e324eb391a85a28569b14f42145694a","score":670.15,"score_display":"670.15","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8201aa5a717e76400d712e5b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6db2e4c0b75c205cad47948b05c7478f2d2462588cb7df347fdb39e1da3ce82f","measurement_key":"19e4c60007c1c80023d7c126627ada77239f80e4cbbf80ad877373b488bf4cca","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"52f8f6428ad7edeeb8c21317794d0da63e57c453a542f3716e1520945027dab2","score":1443.001075193124,"score_display":"1443","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_53cc057b7b9f88727dc017ac","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:38:57.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ece2c1078453cdc56274fcc3e6e9c03ef193284008b7b983e508fcacb575c7eb","measurement_key":"c7e7ec5eb51cb99712169c33a60b2021aa9ae43a54e34165f537cbb9f1de16bf","metric":"mean_score","protocol_fingerprint":"625f589d59546247992766c32ec916010e01510c1e75947f19a35a981bde75a8","run_fingerprint":"4369eb1beb6453e80c670f381cba1eb9257be19cc1480161bcb09f098226d8e5","score":14.000000000000002,"score_display":"14.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6d51b15144d16df42f8e1846","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:41Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8e2dd85344d203d1c8063989831ac0cdf403c1692385ff6eb4578e87fb7953a0","measurement_key":"09fdf632c16495b66580ed45d667be45b2dac12865bb50c4e67e2ec22f3efe48","metric":"accuracy","protocol_fingerprint":"e5a3c77a8b1382af9e48713c15079fa8b4cd1a9317f97f925927aa6a2fd6702c","run_fingerprint":"556234f97b445e87578369da9171ef40be5c6908a2003d27adef4fec47d87cbc","score":2.85714285714286,"score_display":"2.9","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_5525cd61422623d479a15e5d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"374e00b2f94719a74c0fbf25e65e8148bab12d7939c925e163850051d12c35c3","measurement_key":"7f72b0909e275217cc2990a45b1a498051fae2ca698e0b5e79f2c55dcebf6dbe","metric":"eci","protocol_fingerprint":"ef07353eef6530a9cf40e4dc0d4acac8027769e0fc1fada569f77caa5c04d9a3","run_fingerprint":"1fe4dd90890cf64f7d6cf824d6af25b48c649bc9d07d6d2d07252039e4afb449","score":147.81,"score_display":"147.81","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_bb2a46687273d3b0b9692880","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T22:34:20.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"80dcbcc064d1784d33e500ce32588d5783b1ce138bd25c04bf661d5a76bbf74b","measurement_key":"e5f5d9c29362874fafa4f9d65fd656da7a02550dc140f0c80a2ca7a08b7e8ce9","metric":"mean_score","protocol_fingerprint":"fc60dfd114311ececfc1f57f9d9205b49465b7c6848b8e45b6aa556afb02d848","run_fingerprint":"a5584439798b8a1826c9b282c7637b55769ae99fa818406dc6d79fe541578cea","score":38.24561403508772,"score_display":"38.2","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_776ab91b9e881c9d284f77fb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4c94fe0c920f269d51a625f07e2dd0ddc9d41b89318f123bfb5a7a718370b57f","measurement_key":"bf3a077c42b64242a2c6712efb57d5a72670b7beb9acbc1e2020a79dfe881c41","metric":"elo","protocol_fingerprint":"d926e830a31b5e8774d52502ae217973a9811c692b83f29a9da3a7daa9e45093","run_fingerprint":"da16ef72b9365ff2b94f6a1b3f465fff534501a1e93da9800784e7bb651d81aa","score":996.87,"score_display":"997","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_93750ce462b5c95291c9db8b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"92824f82351bb62920d946fb658fd3b2ad57e39a8e0c0a509da3527cdc84089e","measurement_key":"528ddb5ef4b86757523e12718f5608bf7d21ed38d83137ff0f9a2086ca534d2d","metric":"accuracy","protocol_fingerprint":"7bde3626bb1ca1b7fd4527a66a8dc0174c2023686d8f492a075ad644ee2536fb","run_fingerprint":"6a2eed6137d926a61b1c76646dbf8dd7cc821c304399a22755557d0f4486e462","score":87.374,"score_display":"87.37","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6fe23e846fb827f588fa93e4","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5ebd0aeca5b826665902c372ab1aa1bb2ac6acba5bd119500c91001a9427c4c6","measurement_key":"a2d0f22e630fa1f685dc193511bca8e3bda73b9bac98136a9dcf3c3e2cca2d1d","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"1300e420057d2c7b8768e18b03574295ffb041c90a8b614d941cb5aea3c8fc91","score":68.90613095238095,"score_display":"68.91","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4729b1465639558d924d0a64","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8ccc5f7c0bcdb696533c66a3028da13f1cb906dec51a9bdd896d9177b319902f","measurement_key":"9e2cb614c9a597fb0e908cf2ba1f8c44b6ef67b4359cf33f06dbf70b257db390","metric":"pass_at_1","protocol_fingerprint":"94896bd28a2a3a213dbfa0a9341561acd80c8f6055acdba6975bd16dff04cafa","run_fingerprint":"cb5352f5174f71fe5b541f45a5e9cf7b0b35b15b868f67ff4f1474d7b96386b3","score":85.952,"score_display":"86.0","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9a3feb733930bc036f1939eb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":205,"at":"2026-04-10","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"4b236baf1ae6754ef95a1ab755638ea5b86b7ec5f45e69bbc4586167d71bd289","measurement_key":"2f1e586e7dcb766e0b31c5cad6bd6701bb3f54af74ca0cbef8e9faaeeaedeb01","metric":"accuracy","protocol_fingerprint":"b3f97980e3465f273004c3504aa3842a9c9b397360b465e24a2b1808facc81e2","run_fingerprint":"8e7ad5410865aa57765c8158f1ad2051cb4819a8c3647145314217fd1c69d533","score":87.668,"score_display":"87.7","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d5fe971d7fb213c8c9957675","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":205,"at":"2026-04-10","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"7c0a10aac17377d108c94158e17151590f37b2d4117ac24947235a6a2dbc2aca","measurement_key":"15baca10e4d1a36841d2685ea12f7aff8f4c6afc27c3422f20d9e75f6bf6e488","metric":"accuracy","protocol_fingerprint":"804e392a224d67dcc66657f293d7d91fe50c590d7a0c1e8144a951bab51807ac","run_fingerprint":"8ef56babd01235f7c46ea7a82b111aa764ad6acf39910dfa91aeab7696fdba23","score":84.162,"score_display":"84.2","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_cebb40ff99c3605ea64ee86f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-07T00:16:48.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6f182d30207aa04692c8094ae0c0ada7aa5f1f061a074554d982d5e10192dd89","measurement_key":"92dd0eac0efa834b6cce9d97939acaeebd38f43f0f134b2bf55a159ac74c647b","metric":"mean_score","protocol_fingerprint":"a92fa1db59b2ffe3eecd89b77e8dd6e5b3b50056ab0da8fc1a68ad306cc3c8cc","run_fingerprint":"77302c95c97a068a8673bcc1c3713e83534866b642ba6244c1d8f170a99e3037","score":93.33333333333333,"score_display":"93.3","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_edf2f7cfb47d9da6a872a4c4","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3622d274b0a66efc84716d2a2d2ad8a4423af56aac286fc525d50245aca22ec4","measurement_key":"d10c9684c648ac5231c2b66160658507faaba712832bf86bcf3b9a2b0853f8fb","metric":"fully_resolved_rate","protocol_fingerprint":"7a7622be0fecc552d5290f0faf34b0d5840db914a4ec59f28e683d3e02d037dd","run_fingerprint":"040ac6afe604e27bdd35400e536e551ea10f6c08c8e15534a19586c86f36692a","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7262336c3c21354687157662","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:47:54Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c3436ddf182a85ccfac5881c279fbea0f769190ce7a97c01cf9141fba9cd9990","measurement_key":"ae0fd6ac525142422480bb4a753330d1f24eb7b015b825faa4ad48dd0b8fafe5","metric":"subproblem_accuracy","protocol_fingerprint":"51e091bd6dcb17b0442880d3b04b67d9a6262a3c333e620a64de850ae5139c31","run_fingerprint":"2dbea69cc8b3041085a2eb03029be1760c9add2c96af6bb9462258ce217d52bd","score":40.7407407407407,"score_display":"40.7","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3af555d70a9697e425c2e5eb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:34:06.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4f15e8d0567ea7a6740989fdeb91c3bc2616ac675aba8b81a207beaa62054948","measurement_key":"e5cb4be649cecbaf77252d984a1768a32d268392e04a77bb2497a3998e0f1adb","metric":"accuracy","protocol_fingerprint":"dae7bde98b5cba1f6aa19f37811b32f4fb6cb69223e0e46edb2d865d8fd12424","run_fingerprint":"fb73350cf7df919d666c71ee5c0ff5ef47ebe54ca4f5a344e947e5409b38a162","score":44.14414414414414,"score_display":"44.1","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_dd42b471745c5d39f5d66180","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"80691ce72343ab2759a36d2993051aa17d4ab6a4a10b8fe1b86f4d23af804e26","measurement_key":"9130c1a28529590dcd94dfa954562272369ce4f4bc52f2e634d5f286359c8172","metric":"resolved_rate","protocol_fingerprint":"907788d9df3db26e653033826be48c07bfa237e8d0fa10b2aec13ffe70cd459a","run_fingerprint":"ce8bb10b8ae09e17d95d828a5ed14a2c0604ac686e73111cfe44fdffb9954ed0","score":73.4,"score_display":"73.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f708ff27ef338fc68c717da0","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"80691ce72343ab2759a36d2993051aa17d4ab6a4a10b8fe1b86f4d23af804e26","measurement_key":"9130c1a28529590dcd94dfa954562272369ce4f4bc52f2e634d5f286359c8172","metric":"resolved_rate","protocol_fingerprint":"907788d9df3db26e653033826be48c07bfa237e8d0fa10b2aec13ffe70cd459a","reporting_origin":"organizer","run_fingerprint":"ce8bb10b8ae09e17d95d828a5ed14a2c0604ac686e73111cfe44fdffb9954ed0","score":73.4,"score_display":"73.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f708ff27ef338fc68c717da0","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"af10fcf479f2343c3f51d41876fb032af9aeaaffce85956b06ddbf699529788c","measurement_key":"62ecbbc894720efd2b3489126141586ee94350d7d0628f1acc7525565cf3bff1","metric":"accuracy","protocol_fingerprint":"18e2faa06b936154a282d0e5ff9fd9f9464985db78629b560abc8ceedd77e37e","run_fingerprint":"fcc667f47fc14aa096c9ed2f826e92dae3dfce6d9090de4b8199e9cf93fe847a","score":53.184,"score_display":"53.2","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_08482f26f2f92123fd7df7cd","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"03a39a41b4064033c928afb509e30860d1160ffec8c549dde9d55b0f8ae5109d","measurement_key":"a172c7e5364bcb79982c89e6ccf8a1d2bc7c5c9cb11370df3f8c19f80c5ed17e","metric":"mean_final_balance_usd","protocol_fingerprint":"5245d7d556f59316a3b62d871bfdd955706a9c52ece3c9601115f737cc29975e","run_fingerprint":"0d5ab237e59bf326dca3d0de3b005b2b2e55e64c3a67e6198d7bf99c8367b32e","score":5114.872000000001,"score_display":"5114.87","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_953234b43d2b7322c944aebe","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0214f2c9ba91166b78b9c00f895740434661f675bcd6dd562f818c27c71f9a80","measurement_key":"b459e52b3514d9e96dea8029d7d614e79b87071f5d1a13d28d16889fc609e2da","metric":"score","protocol_fingerprint":"34848578537378eabc04b9bda4b996f653c89e78bc3e007cc85dceb41649e004","run_fingerprint":"e5b0b021aecdfeeb3fdc8b19538648492f9eafeaf80e81173ed0f3650e37614b","score":25.565,"score_display":"25.6","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_54ca3d703000d3359b931ea7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"312aa74f6228324cb45b0a5ad7d87a917d162ef7439379a3409018571e73b6f2","measurement_key":"28e419212a5ce24271cdb1e2e2338bef785d81ad4456ebfdcac676baaa04dc4a","metric":"arena_score","protocol_fingerprint":"ec99a19a49606a7a2aad51887ce8ced6450b614aa29c7d4fca1f610d443abee8","run_fingerprint":"05e1f648fc05fa85e2692cf4950c6f727458609144ba87120d044e519e23c80b","score":1461.6254246112119,"score_display":"1462","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7a85759823e37f67a2277eb6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"alibaba/qwen3-6-plus","model_name":"Qwen 3.6 Plus","parameter_count_active":null,"parameter_count_total":null,"provider":"Alibaba","selection_rank":71,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"03fa75b21e9af4523e1b49d4338c584f786e63dc4c988787d29006902667ff20","measurement_key":"80d52436ad094eef1838230d33a62520f8d038c4e3c5b6b3458ccfca003eb3e4","metric":"performance_rating","protocol_fingerprint":"87ad9863a296e4d0ca4c603bd65bf083b55cd7df19331b42c8fbfb054df34ad1","run_fingerprint":"b687f0c978a6d1f5d465afef355789599f6858b6aa88931b6b344dbe3bdea52c","score":887.1,"score_display":"887.10","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_30b8a704bb9675a95ba357fd","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"723a1729387414f2d2394dfd782945c6e54be553c227d3687d27b9140bfddbb6","measurement_key":"4f0daaaa35435e5bf137a968a2aa0e59f1ee49f0c15c38c0e9cccd8f4d3ccebe","metric":"pass_at_1","protocol_fingerprint":"06977ea746630ea040a4af35202a813d0c631d9475e8aa985a38f6fe25b0b6c8","run_fingerprint":"22186f9b791ca5ed1608cef5524fb11335a973a155f9dbf813d82dfd991aeb26","score":40.9,"score_display":"40.9","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8040d78652f9243c2fd1388b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b2e72103d434a16f480636ef875b7a3e23db56561ce45c6e005ea64df6cd5986","measurement_key":"c8cf7a3a9af2985aef789955542dd7791b8a7c2d570a5d5d8d784388dea07fd7","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"3352643e7473ed0b2fbca88b81152c5045bd6a1bef35a96418789626f5597344","score":1465.3780546778316,"score_display":"1465","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4f6d1e7644946448f8c862a5","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-14T06:28:37.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e584ae9cfa2cb54916349e932535505dd2a10ab112a9e0f78a34a59f904c45a2","measurement_key":"97f2d884ca7c3c96ca49e5566065ce2194e52aa0ec20eb838d101a8f3178f935","metric":"mean_score","protocol_fingerprint":"badc78142d3907a4565b4334b12c13ce70fa9481bea32404fe76d9811f034a14","run_fingerprint":"cc01942685bbee342d2836b02daf092a3776b1bca984d4d7d0ac8a8e420da115","score":20.0,"score_display":"20.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c0691b96512398ad384aacdc","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:41Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ff42a035ac4eb39c83aef8a3112d7c45d2fdbe454acfdbe1e060ae416279fcb1","measurement_key":"a5317f964c0f31d2edadd646cfc94d91538460384d7bb51ca5dd595ef1d862cb","metric":"accuracy","protocol_fingerprint":"c001b94d23a5145180ef0494950146d455b821d9c6ac0adb93a4a086462d965d","run_fingerprint":"9070b2a9d2fa098b64532949e213726c5995d8c7419c39ed22c88eeff7af4481","score":4.57142857142857,"score_display":"4.6","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4527a4a9bd084290f3d0c928","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"43307987b144ab46462fbfd2c4df0a605de767dd758e459fad7125afe0105a9a","measurement_key":"69958a9ac17b2229e308db5f3ed626a1d6aa374e1d0a67cdb8a9613f30eb2593","metric":"eci","protocol_fingerprint":"d5726cecc847a0e03678d6fc8bfa1fb653963a4361a3a0d9b875e42678de5d0c","run_fingerprint":"dbac47a73e495d710b66e9119fdf4eef40acf11b2f0102722c3ed34bb3a24681","score":149.88,"score_display":"149.88","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_dccc52ab99879471547d0fcb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":63,"at":"2026-08-29T11:06:22.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e2df9098dc7d7896b003d12d11d570686794c12c7818125a689ef70f3de5253e","measurement_key":"bd366742581b00612ccf05919d8be577750383444b9b4254fcf7566815dfb53f","metric":"mean_score","protocol_fingerprint":"98dcfe9815fb35e05957550b906d55eb847952b2b3400aa5542360e7fec9708d","run_fingerprint":"2efb077e7bdee66b5351ac2dc407c18029f1c6aace3e11d62bfdbfe869dcb21b","score":36.84210526315789,"score_display":"36.8","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_48e96ad44abb27180373f267","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c9d85bfad973125dbca32e3ca36c809d138b9f95b6aa8ccec97464c65cd80c85","measurement_key":"2cb681782b1bc95c9d72bbcff042b412850e1396cf10eaf970da5948befed818","metric":"elo","protocol_fingerprint":"e690e12dda0a8732479dab4d46d4e4368bbf2ef00f28e3f1c0a716acd2775ad1","run_fingerprint":"9d2d6cdb025fdbfdb4b399e3f21be8482ea68e22cf7110b6df3ca6cf40d47d73","score":1125.15,"score_display":"1125","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_41edc6ecadbdb6a4fe4eb5b0","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a67959861cd1ca9fe16ae9dfa2d9b52938177b796db8f7ae6dbc72a3d4c73c79","measurement_key":"1d84b3e530acf05571dbc49787a2591fe82c4e79322a6a75ee0a52c142eeabd4","metric":"accuracy","protocol_fingerprint":"0ce04b3140e47969c05d67c732517161fcc6a639bf4aaee03928f17e6054e2e3","run_fingerprint":"6da3d76d82f034f970689072dd0d3001aab6a647c3c53e310869db5d230d741c","score":84.518,"score_display":"84.52","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b1fc7c73685381c163b9d8b8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_5f3023448c2ae4632fe1a43b","benchmark_version":"reported-runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":208,"at":"2026-04-07","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"66ec7986f4c10236c40b538bde7f1b2212821b7bb5fe9064ca96432e688c301c","measurement_key":"ab6a60a55d038226fc49bc072407996f951f7cf551efa33608be0bb4d85613be","metric":"accuracy","protocol_fingerprint":"ee783082ec47e7a371a58d8a675a96b1f52ecfbbc63322f29a55942e98f28297","run_fingerprint":"927de019e81ab3926f263cb59e3050d0e831664ddece7352561c3ce0221d58e1","score":25.63,"score_display":"25.63","source":{"id":"evals-report-hle","name":"evals.report · Humanity's Last Exam","url":"https://evals.report/benchmarks/humanitys-last-exam?tab=scores"},"source_authority_tier":"B","split_or_window":"public-multimodal-mixed-run-configs","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_431e0630dbeb9073dc747d67","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"evals-report-official","verified_status":"evals-report-official"},"unit":"percent","verification_status":"evals-report-official"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6694987c2e071c76dcfbff8d13451e0ea4c153701939c65afd707a1b3aec8459","measurement_key":"2ca5c63a93b396b40212da03ee0519b61f12cabb7ab3f971bd69f8e4ff4625c2","metric":"pass_at_1","protocol_fingerprint":"83562bbb61ccde2f666ebdf8b836276a198e6e19fd9841ce8794fee35764629a","run_fingerprint":"a87670b99f4e01841ed3b2ca68e398df6b08e1fb9e5167eac8596a90d261fa26","score":81.38,"score_display":"81.4","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d4071b8077bf3ed5a584e7a0","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":318,"at":"2025-12-17T17:20:04Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"cf08aca8f34609340a5f2a8fbdd9fb418c4b7151fb4a350676478702a00e7f56","measurement_key":"9e00c617226dceab5838b04d42f49084719edc7bea08ccbab648d33fb5ea372e","metric":"pass_rate","protocol_fingerprint":"26828b99a7ad1e4c76d3470865685ca3dd65de0c8cb95c23da986fb2c2cdf842","run_fingerprint":"aa941928b931435263583e241a06fc84d1434d5765c762daca965b8429a36201","score":75.6,"score_display":"75.6","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ad3fab65029bdb5cc6f0ca02","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7d7cd1d8af004a34c292c450779686871f809369293f419a0ad6961ebc503180","measurement_key":"feafc0fc111eed72fb0c4e1a513fec4cf6aaaa05d8ea82ec5e1398b3bc0b09a6","metric":"accuracy","protocol_fingerprint":"b012d9c93bdb3737331c40dfa9ca7e905f4229670db3d3495886856c07a61823","run_fingerprint":"3f07c5d6be3b0afb38f44331c7f5b516a9309e4ca2b4af138c72b85bcec910ff","score":86.9,"score_display":"86.9","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8758124509145d977399bb3b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":82,"at":"2026-08-10T17:44:52.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e2a332ceb605e4e4540ba97ab63d6a9c1b271b25d27e7c0c7688663357c1bef2","measurement_key":"596f13456cfcf92e184971cee8cf0de5205caecfa7cc0d58b4279681a3922603","metric":"mean_score","protocol_fingerprint":"392497471e5edbe75c8a86361b5bd275c44d0a931cbec936fb5c638af6cadaae","run_fingerprint":"c2269daa80f6f9075f81a0bf0e7a832a06edd9779eb5581234717f4a1c00f43b","score":93.33333333333333,"score_display":"93.3","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b4a08efe49d38b527af1c6f5","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f8dfaa0a67941eb5bacd798ab67b5caa2789e74f4a699b60a21d15d46fd2aef8","measurement_key":"1571b3e4da2ebb8727a838e41812861d1e9a80798097a5d83a017b5335d9abeb","metric":"fully_resolved_rate","protocol_fingerprint":"e9c329ccb4fff8bfeeee9340118a4196d0c40e57e837ac4c5784d89b4f24d272","run_fingerprint":"4741286bb31e5d3cdfc37c9de5ef86e471052b45c2bc80cf9ebd671a51ce1264","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_88158ef15864c64c4d9e67d6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1479bd3b44632ab8d9222a1adc832c6960faefe76ca9e2a12f52a39cf88678b9","measurement_key":"6e4877f8e721fcc64684d9cacb6174296680ebf1ef7a10dc6f7b00ef30452438","metric":"subproblem_accuracy","protocol_fingerprint":"255b918a3964d48cf69d2ac2b7c2427870abb9538b96a76deff23a505934f694","run_fingerprint":"153043d7ea1b7528f0e12f72fa661a4ec65aeb5ad8cb5a123bf455a8320e6a10","score":44.7916666666667,"score_display":"44.8","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1a321a729524c98a8dd06766","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"680688d97c68ec50bff4b30c6a5568b1b0deec3415e81c9ca334700daf42a282","measurement_key":"4dd23b1d11b7cc5c8873ef15b1d9fbb22c6cb138cd3d576bd37aa2f9d6469b42","metric":"accuracy_avg_at_5","protocol_fingerprint":"4e1356ea08402efb38774ffe2ae9e2d6cec6e73c9c6b46736562da724a69ee60","run_fingerprint":"74c2950e6348aba3b8b44117f2894018bec7f8d9bb86a1d1084991eeb749cc77","score":55.1,"score_display":"55.1","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_843141e4bdc30672d535a46d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:36:21.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d701a88aa5f8d57cdc69fa3f4a50042a645deafd3f778068cdff3e74ad53df19","measurement_key":"0b016df3c1b57c25a97ac511d3d2524b70186acd96631275e066477a472bf32a","metric":"accuracy","protocol_fingerprint":"c82c0b1cfbc31d6ae84f5ace46374d5aec7d3ac6893533ed29941bee1c4deb8e","run_fingerprint":"32fd2e92293b85ae3c5bf81fb9cfab0673d105bbe2d3e3658550085e396832db","score":34.0,"score_display":"34.0","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0284afb597a0b16d0dfbcb57","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"skillsbench":{"benchmark_release_id":"release_093b45b8b752b3f08534f6ee","benchmark_version":"v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":138,"at":"2026-06-16","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9f892f7e5de52b1dda5e89136236d83cc2ad0e8a37423b0fd422b0e97bf5752e","measurement_key":"78753ebbf25248ddd8ea7529ea30cb0d5b7746f32cb157b261cfa1371e2f40a3","metric":"pass_rate","protocol_fingerprint":"c2ed2025e534826e5e627446f4493a128269710491b35eb2122abbaf19d56304","run_fingerprint":"deb148730c332174819980f9b06a681381a2cf295d78afeafd7e77c680984db8","score":58.4,"score_display":"58.4","source":{"id":"skillsbench","name":"SkillsBench v1.1","url":"https://huggingface.co/datasets/benchflow/skillsbench-leaderboard/raw/main/leaderboard/skillsbench/v1.1/official.json"},"source_authority_tier":"A","split_or_window":"official-87-tasks-with-skills","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7b5a3c7d436cb995e1ba2cae","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"69f0236b001f1fae53f3e58d75fb159c5683f3a756708644ef6eee0ab571bac1","measurement_key":"e8e7644f9e800b68d2a569d63db5f7db98356b59f51ec48e11a739f7ca10f512","metric":"resolved_rate","protocol_fingerprint":"b49e3996435128974d669abd88890cc57aedad5426c26ac2fc6673ee7cec67ee","run_fingerprint":"3fc23a0cde86fa1b1f2fbcb57a4033bfdb386c99b64a016c0241a9a0df049b4b","score":76.4,"score_display":"76.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ecd426e90f3b64f9c038b350","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"69f0236b001f1fae53f3e58d75fb159c5683f3a756708644ef6eee0ab571bac1","measurement_key":"e8e7644f9e800b68d2a569d63db5f7db98356b59f51ec48e11a739f7ca10f512","metric":"resolved_rate","protocol_fingerprint":"b49e3996435128974d669abd88890cc57aedad5426c26ac2fc6673ee7cec67ee","reporting_origin":"organizer","run_fingerprint":"3fc23a0cde86fa1b1f2fbcb57a4033bfdb386c99b64a016c0241a9a0df049b4b","score":76.4,"score_display":"76.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ecd426e90f3b64f9c038b350","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_1f8553cc12d8235844f1a578","benchmark_version":"rolling-v2","comparison_lane":"supplemental-post-release-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"53bad1f8d9084c8f2f6208c2bd80f77cc837084939865ec6099ed7667b143920","measurement_key":"3d7b5db71d0b1f5e5b1c6cfe160e898db9fda7c3a9b20eab8d52bec0c735b73d","metric":"resolved_rate","protocol_fingerprint":"adc23987b5b7dec5bcf4893f7ec22af1b131cb7476d633bfc720fba4b5732bb6","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-03-01/2026-05-15":{"benchmark_release_id":"release_72d764965dd7baf34f983249","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d0643ee1502267b6db81010174e601fcd511c29c3fbd71649c32a0a7ddaa1b86","measurement_key":"9127581b433f0d9d911f61f1763e2a1dbc34f64fc97c3c79784d551caa429311","metric":"resolved_rate","protocol_fingerprint":"84265b74fdb8984a2c9eec93d651ca3ab644ea5df2ef4cd31ce44c3f5978dc49","run_fingerprint":"725fe81d0676d8ba6903d9f67d0d3e8c1d550b5be063d239c5bdf69e18d344ea","score":50.72727272727272,"score_display":"50.73","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-03-01/2026-05-15","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b8e62d13cae9686240097b66","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"},"2026-04-15/2026-05-15":{"benchmark_release_id":"release_1f8553cc12d8235844f1a578","benchmark_version":"rolling-v2","comparison_lane":"supplemental-post-release-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"53bad1f8d9084c8f2f6208c2bd80f77cc837084939865ec6099ed7667b143920","measurement_key":"3d7b5db71d0b1f5e5b1c6cfe160e898db9fda7c3a9b20eab8d52bec0c735b73d","metric":"resolved_rate","protocol_fingerprint":"adc23987b5b7dec5bcf4893f7ec22af1b131cb7476d633bfc720fba4b5732bb6","run_fingerprint":"28bd29daa57451d9be9db498c142c26167d65448a40340d04b936d5d06775743","score":46.666666666666664,"score_display":"46.67","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-04-15/2026-05-15","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b8e62d13cae9686240097b66","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"28bd29daa57451d9be9db498c142c26167d65448a40340d04b936d5d06775743","score":46.666666666666664,"score_display":"46.67","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-04-15/2026-05-15","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b8e62d13cae9686240097b66","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b7fd27295742960933c65736e48d963b0b24122fa4fc8425c219e69164ce0984","measurement_key":"d5f5b59254c3812c734bd2837a959309b5b8c96dad27c68c28c74fb58044d103","metric":"accuracy","protocol_fingerprint":"4f2ab12755aabcb57b111a9dc2c589335440f79b13c6bebabf4e8c5cbfec30b1","run_fingerprint":"41e0a01ad13fcc2969c339f2c9d920c1ac1efcd06e4cddb74abef801b9bb2b7a","score":56.929,"score_display":"56.9","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3e84dc8d0f289a1a0746e436","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"630be6f28e4957fde711fc8c07b3efee4132f91a671a8eefd8f1de7428cd06fa","measurement_key":"cfb87011df470559abd5fcbf155cb5b964316589e4fbe8177bcbf6993652366a","metric":"mean_final_balance_usd","protocol_fingerprint":"9a9e32b0068f5fb9b0b566ae38d4d1d61625904821eac60cb0d101ea97d1ad67","run_fingerprint":"2de635465465b016e30308f149eaed7fed4be3c5ae7e9597033eeca74020c2d5","score":5634.406,"score_display":"5634.41","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7ec5cca37db5e5d05e3414c7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5e86535df85f52e03d60b09f1abeb5bc10ccc3f4bd4ccd8649c9482bae33319e","measurement_key":"760a236dac6362d60d16c15421b8fa9af53856b219a4b9c292fb90d142afb2f7","metric":"score","protocol_fingerprint":"3af1c2b5962b59029fc2521e9dfa4c99c359d2b7bba03a08ec8d1d29619b1534","run_fingerprint":"1911669198cad1ae029728622f562af431402502925ae0f70b04157250a9b44f","score":31.456,"score_display":"31.5","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a3ad892dee5035b3e24ce86c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8f2f978b6a5b4946419a4c39a91386968f26e9f6e539d6b900e070c704872771","measurement_key":"db0c8ae96819f518ff77506dfae1bf856e3bb11fd683f9f8bf2583839f206056","metric":"arena_score","protocol_fingerprint":"e1a41faa44a628fd84f89995f23648ed3cc92441054140acac72a58e8ac145c8","run_fingerprint":"4ec65f90e377f68ac798d27234ce93b4976992c9350a679e55989bcdc6ca4c0f","score":1507.854558177699,"score_display":"1508","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c3270c0606da8408f8bddd6a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9b6c4e0b761a5a308cf5fc99d85af06d5661bf6edf8740f57c3e2e4fd3d5cafe","measurement_key":"ad8c4e5c2e73ff401e0ed941580a94673121f2d1b8160d82318b0917b8a8fbe5","metric":"accuracy","protocol_fingerprint":"c0b0aa6e7a0042316f3fbcf1b37e0959dbd6fc34c9e041d04a2c348019e00d3f","run_fingerprint":"71bb7636474deeded6e50c1604a157c33e6fec47ec4673f52d365915c0ffaa5b","score":57.10000000000001,"score_display":"57.1","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3d8decf657d2d47a2ddf04aa","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"zai/glm-5-1","model_name":"GLM 5.1","parameter_count_active":40000000000,"parameter_count_total":744000000000,"provider":"Z.ai","selection_rank":72,"weights_status":"open"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T17:25:13Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7e5ce32a6b2c1b48dbf8f66bb1b95f6f549f3f39e2af003f07cff01d2bcd5c70","measurement_key":"e95d7521f8d08afa52e7f0a3af4a3dc78cda3601f337d40ea606b1ee209325e7","metric":"index_score","protocol_fingerprint":"72a3614d7ddb6e869bd77dd10693bd086e6917298dd2233d44e3097391d5d4af","run_fingerprint":"2c4913503eb4a4fd9488885036f493363a2fcf8c1082470dd19f207ef53f5771","score":26.024995,"score_display":"26.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_fe87d445715ee13ac9066924","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:15Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"907c24379dfe69d8a9a45c6ff6b69df9b61f79ee88a06e59db5c29136f699a66","measurement_key":"90222edb89009ad82bc44f538d4b5e03a1659f5dd825dc70a78c939a3269283c","metric":"performance_rating","protocol_fingerprint":"b434bbb3739ad1d8f985a32ab4b38c418a3f26d047352ec15b12da16f2eccb3a","run_fingerprint":"9d99760531a4e57095490296fe4b3ec5c8ced0eae495da900d7fe0097638fb74","score":1213.15,"score_display":"1213.15","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1db8ed00113ebd56b6eeee71","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:02Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c549ae40adda49247b560f77c906e198b346c8998ad274a0dfd7f703a53f20e0","measurement_key":"f19654f0706ed4844ac836a2ab5fb41c791553e9c7f4ce6e313fbce31948b89c","metric":"pass_at_1","protocol_fingerprint":"5353b965ce0464d23483a370879260efd1c355ee36b6d809cd75053fd03d0386","run_fingerprint":"0db61f09ccca218bd6b746536fd827d20db8a5f9c2a823466789614518091dec","score":51.6,"score_display":"51.6","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_fe87d445715ee13ac9066924","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7cdf1a898f11ed2925838820071c1ce3981ac3c0cc3754d490abdca503e3d605","measurement_key":"a79986e126f5c54060427a2b9ed2ed2f72314b03e60bdadd7e2fbed362a67934","metric":"ips_score","protocol_fingerprint":"870170970b6c7d3adc20c896a113851ec636c3334c80cac9804d9777d55fa332","run_fingerprint":"3dbdeddb1789f4d4bbd5b78a9eaae84ed97de07b7ee9c793f1f722e6819af246","score":-0.060236922606071455,"score_display":"-0.0602","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f8e780749bceef18fb954bc5","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1d108cac9a15dd1a570dd7dfe6f5ac2042b9c310878e29f03de511663e05c4d8","measurement_key":"dd826ec4de05e0bf1c619567fdcc53034df79f7f1feb3a32ba7809ae860ed42a","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"6484dde58a8d3eef2bda213d7254c9cdf35f1be132772f35c72df3f891907cf3","score":1432.0109534562546,"score_display":"1432","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_637360ad7de092d772e4aea6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":16,"at":"2026-10-15T22:52:59.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"721079f32e93e686993718ef160a17b8641a197656e03822a1db0970b4246881","measurement_key":"cd17cc6a6afcce79fab5f740d15908a4b2de031f106ef5f183b725b0fd13abfc","metric":"mean_score","protocol_fingerprint":"b8c53b8298bec11a963684a3cf22323500bf4bf8174dccc074053a250bfa8dbb","run_fingerprint":"95dc5a961a6acf3652e828cc88a2972c2b55ea99d5034edf13cc90c0cb75578e","score":33.0,"score_display":"33.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_fe87d445715ee13ac9066924","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T17:25:13Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"98b90b7b1ac94aa7d4d5eb63bb8bf8b6455dc6b6d257a9b7b6d3e29679c7c009","measurement_key":"cd41ad0380a1c9a2816f2ad688eaca379388aa10cc6c715cdd1a9d4841cf6be2","metric":"accuracy","protocol_fingerprint":"0bdc837c4147ddba40158e898fb66d212bd9f88c687f807dbd1e8cfb555c4ec6","run_fingerprint":"7fa4a6cc114e0c18030d11c5efbda9f31f526a76c3c492f3f0c4b7dd0b3aea04","score":10.0,"score_display":"10.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_fe87d445715ee13ac9066924","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c43bad158914ce8de1018bcc6f965a1289a8a750e32a86341a52ec4c531145ff","measurement_key":"05668fd67fe5bf6f7ca8285d96d8a90a4ab8688488899eab6b4cf1de7a906280","metric":"eci","protocol_fingerprint":"f328f08ee95979ac682c4abfdc01b6d601bfa4f68198239a044ebd3b8863a15f","run_fingerprint":"af635dbfd51ab7e359c441ac5e73f247219a6f93d991fb54e34cfe27a54e567c","score":150.59,"score_display":"150.59","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_89fbbe37639d7d4a810fd6ba","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:11Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f1c409beb64f5cfcc23fde951f5eb22cd8815262dba5f5f313a9e9fe6bd58f7c","measurement_key":"109896ad2e8a77bdc4bbace2a50e4b6c1b00e42bd0a0fd84b3e040d91ebc7333","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"f7096b525ea21ac7ffd4c2fc717fbe3301c3b8a9436a008a9fd62b2700ae40df","run_fingerprint":"9de29ea87e8c75d59f6fb523b5718f1b97ba8497e7db7d8aba7494b842956d25","score":39.43,"score_display":"39.4","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_fe87d445715ee13ac9066924","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":19,"at":"2026-10-12T21:38:35.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"07d414fd4e707515284889de005d78a73708bc723b72e8c4ecb48eae0977a0e7","measurement_key":"ce7e75e2269e8a71904de1e4d0c8607ffdca2588e7a4feb7f4200054b348e5e6","metric":"mean_score","protocol_fingerprint":"78c058eba9fd821332e9a4a7b28f1d8c50a9a62f08ba0d2089cc3f363f89533d","run_fingerprint":"d9893cd3fbd25d7a7c99f476d59797f1338a50dad3b83c446ace7db191f465bf","score":58.59649122807018,"score_display":"58.6","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_fe87d445715ee13ac9066924","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":19,"at":"2026-10-12T21:38:22.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ae2cb3f698fc0740e083caea8d98269899be843d37d0afcf1a1f8bd390e18471","measurement_key":"ded94d27ae7e3468c178a5e9b2cbf3dbe79cc1aa5f7d113e4c12dc8a6ad7a3dd","metric":"accuracy","protocol_fingerprint":"eafa1188cb8307e531713aad7cabd1576533adc4a375ffe5ab13104266b6879d","run_fingerprint":"c6952e92284fad78c5e5a0f08671ea65c9e9f4fc2dbb6baeba299096c2923834","score":88.06818181818183,"score_display":"88.1","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_fe87d445715ee13ac9066924","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"34b13a89ca118794ea24311a32ca981408cea845039b88c02bcaaa38ed915853","measurement_key":"4049a5a83c429b761e6bb1c89d2990c5a731c025c484ab2c7f120e6dfbb344b3","metric":"score","protocol_fingerprint":"484705d2b4288049f4fc41628f0cf70c35e5c4d49b2c206029d7ff36b7d081c6","run_fingerprint":"2c078e27d3a6d376c12464f86e85627ddf42cf77b01b2ff3df4b45772d74e586","score":45.278,"score_display":"45.3","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_fe87d445715ee13ac9066924","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":19,"at":"2026-10-12T21:38:35.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1bcb9409713653c59711712ed8277bd1c690afe4293e4b3320eb72c5c8046016","measurement_key":"d595dbb31520bdc3dd68286e91056ccc56cecfb8cadccbe1a5f97ab4fc1197b6","metric":"mean_score","protocol_fingerprint":"b73e84034c057e1964e23734c4f295ee374c8ea2c88b3daffb33c99109e09075","run_fingerprint":"58a124551c0d68a31993881937c43a244e5a5502e1a88246176cccfd2e895810","score":98.33333333333333,"score_display":"98.3","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_fe87d445715ee13ac9066924","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c9452c458a5a6d5cc947f517fb62a711a1d8111c062bb87acc6ab45bd33622ac","measurement_key":"c95da79e4f80fbc71c8bf64213faa439df26f5d79441348d3cf0a2d2bb73e592","metric":"subproblem_accuracy","protocol_fingerprint":"b1976e7b09f83d3a68ac82cc1e91e0ea6ec9185f818ae7076c6e7b9788600687","run_fingerprint":"608e2ddbab2c365d396cf604974f1d2ebe329b3e1ef0c56c0e54d2ba9d265a89","score":54.1666666666667,"score_display":"54.2","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e7a36457424cc102e321f255","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":22,"at":"2026-10-09T14:12:09.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"741853d219db1e23f185d1ef33c633eb7b09cfd40b3f5a2347890d93060a526a","measurement_key":"9feec7b0c8499a35a470ae003ca0ec1e64abb9eb2bb50b7aef677a7573948853","metric":"accuracy","protocol_fingerprint":"71640f6fd6a6993f9d26ad035ff322bc310711b93b8bb32a0c23711884bd4e96","run_fingerprint":"4ea37ff47cf79fbcf43360ece9bb8594e3aed692188339d371f4a3faf0676a6a","score":20.0,"score_display":"20.0","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_fe87d445715ee13ac9066924","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7b89d9060ab7d274f7105947e4399f72c0184bc99b3ca92b2ebb2d547cde08d4","measurement_key":"43b4cecc946debcee2fd241244893ad7d14fa5409a5e894a55cc5673d4386b44","metric":"accuracy","protocol_fingerprint":"65af58ecd810507f92b01f8880c00b6441494dbadbb4c76a53cad2ac93e44978","run_fingerprint":"8b17f1bd4ab3d381d032c6d7cc69b2e439df6548dbcde4ac09afa2c4b102e37d","score":27.778,"score_display":"27.8","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_fe87d445715ee13ac9066924","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8647c6388a0fb44738afbd40d0f0e45bd8687487420731fa10b69f8d50f4f646","measurement_key":"16fce2d40547cffb6976f4d1e68303210af93321808d34076b674ee4533aa962","metric":"score","protocol_fingerprint":"6a21e284b909db3b1ba9694bd1a9e6546fc7199b35f791b899a7981a0a8e943a","run_fingerprint":"682c1065bf78036563ae5469a8df1d8af960fcf82ec709878691977b5aab426f","score":78.403,"score_display":"78.4","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_fe87d445715ee13ac9066924","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bb8365699b930544710d1bb8ae6c20dd5b2d865b06cd831fd2d72c306c463687","measurement_key":"813c81881ec8d87f043e101ceb32a1412f1286ec3e4342f97cc2de9efef120ac","metric":"arena_score","protocol_fingerprint":"d4b74c2755b7c79e15f7441580a179646cd8e60590f682265f512bb043b56080","run_fingerprint":"e8f7c940e05da8ee21e3d5d97121850bc56081c6f163a181d7e51b3fc42c30cd","score":1544.3103315032786,"score_display":"1544","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f6a46b105d68760c1113c3fd","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml-v3":{"benchmark_release_id":"release_d03eb71d3ee6d672c5bf0012","benchmark_version":"WeirdML v3 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":10,"at":"2026-10-21T23:21:03Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f209950cae598fe475c81aa56831ada218000def757e51b6c3f84728fef29189","measurement_key":"d0c30b0397522f979129859b0b3cc4dedc6885e772ac266f5642275ff9483f37","metric":"token_efficiency_weighted_score","protocol_fingerprint":"df59242b561d30dcd9bd87c81bb11c559ed43c2096482a2244fe965b9aa2f05c","run_fingerprint":"1efa74646bde0785625c29d9d3a10cc34f0e2fc6cba26c0ba992b926821b0bf1","score":4.445937272727273,"score_display":"4.4","source":{"id":"epoch-weirdml-v3","name":"Epoch AI mirror · WeirdML v3","url":"https://epoch.ai/benchmarks/weirdml-v3"},"source_authority_tier":"B","split_or_window":"weirdml-v3-11-agentic-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_fe87d445715ee13ac9066924","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"mistral/mistral-large-4","model_name":"Mistral Large 4","parameter_count_active":null,"parameter_count_total":null,"provider":"Mistral AI","selection_rank":73,"weights_status":"closed"},{"cells":{"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a8322998eea0c8018ebae58a08b281197183b9ca6d7641348efa8c5ef49dd1d9","measurement_key":"aebca59acdb9365a5d2d23227e082e317900e9087d5d1abd1402d8f8bdc45ae6","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"ac287559c91840868e0eabe3ba5f28046adf05e9603aee2b11306598a915ce3d","score":1473.1665868835428,"score_display":"1473","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_330cfe6b7fe94f55d14565b7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:41Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b1d2d62db1f0482100c7091ae412c7d5b335461b384aec4e99e70ababd23904d","measurement_key":"a5fcbdc78246bd1cf4891611ca62304d441089109069082b4d74735b777dc010","metric":"accuracy","protocol_fingerprint":"90739739f322573cf0934f54aa88a344a4e4bc9723803153be1bae1ff77537e6","run_fingerprint":"0e10ebd0ad29f9a6b4aa1b1770a8a6b7964ee3eb6e425b0754039dfe00496582","score":0.0,"score_display":"0.0","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_002ac6ea591ffd737ee3511b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b844ec1fd9f4ac018f7288865fe75a4853fdb1c11c76897f0602e387e0121e6f","measurement_key":"d9a8d099f9691d1794202c60c5f4253f35a4ec143603ceeb134f892b6b920a44","metric":"eci","protocol_fingerprint":"4e8d563a3d60bf54d8a07428016e82b4e8d2cf4d778b5d3d1b5e513ce8981914","run_fingerprint":"f2c7a76d15fa184fe406faac191ae35747c207a474df2e503e63fb7894fc95db","score":142.49,"score_display":"142.49","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_68f21033bf83c6f8fbdc9a46","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":91,"at":"2026-08-02T03:23:36.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c47821518b62bbf17a4a300d42b01ea13ce748e8be5294c969992443f32ccabe","measurement_key":"88e6663307f8622f69e240dab83600d29bfd2902f7b11f367febf87cb70fb4d7","metric":"mean_score","protocol_fingerprint":"d88f5a819f66f4d19b051f0d673bb006c3c4fb4295841672338401037a42a31d","run_fingerprint":"864943e5920d3dde3c696b02e678608aeca62bca31aec83938fe033895681898","score":26.31578947368421,"score_display":"26.3","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_bd5c6fce5440443fd1b5a873","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":91,"at":"2026-08-02T03:23:36.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7525d0d53c5f8eb01c50a7778d83ac4db9c109c2c5bb1ceb22445dde4a450e01","measurement_key":"67ebe45f6d1d2b9e748f9e73e05565471c689ee75cdf5564aea94cb54055103c","metric":"mean_score","protocol_fingerprint":"3f9de5475de6ffee0c5290dd7ce2901ff8918a8cf5990eb39af29fc63d5fd6e3","run_fingerprint":"c2ff5af20fc9ac53ff4703ac1a38e23b7bccb38c4c6ef7179279b7b534370640","score":2.4390243902439024,"score_display":"2.4","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4e913c37f9e4dc8418e49c97","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":91,"at":"2026-08-02T02:46:37.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a575577c2f683043e42d9c0dadaafcec84030ac21344ce946ec5a94943ed30c2","measurement_key":"22f4a57c245ed68454e5c88effee0fa14c9df4efd2bdfb57e1613f3eaf11dccd","metric":"accuracy","protocol_fingerprint":"86d538da57fca9d7c91572c668d7e41e63f4c09d12c1080a6443217a5173c20c","run_fingerprint":"a226ff0abc0c9dbb2d7a66934fd3669cf8dbb60bcf6ff0f607f013dcd950817d","score":82.51262626262627,"score_display":"82.5","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e642c9d37f1af0ef22ec3a14","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":91,"at":"2026-08-02T02:46:37.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5725450316f3a2758ea2a962d31caef7a2e25137174529c770502978d8b0d47c","measurement_key":"bb0de5f28036607268070a1fee1dcc2d8accdd2a97590dfc6871af5e7ae7daa1","metric":"mean_score","protocol_fingerprint":"bd58235a562a986d5655b9fa3d5e4e24e5185b5caa9dee91090a4bb9727082a1","run_fingerprint":"091d3b1f751ed927d44d7b1def28c085b9be3cdc4342c243db9892a63a98493a","score":68.05555555555556,"score_display":"68.1","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_13b94eb3aaf17b8576fe19ef","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"54deff0b38f6d2079b25c0524ea0dc594c3cd6b76b0904ef8da1f016986a83f9","measurement_key":"b2eccc2546b5c36bacbdf2e5b25f1cb5fe09ecd3a743002af69df2338d61b643","metric":"subproblem_accuracy","protocol_fingerprint":"d7550c39386d0afd190a112feab5a43e14e1e141f83a7ea3a2ce06073420e723","run_fingerprint":"c3edc34c876595e11537d352b2691f4c146be0d546c16c79a04ceac516f16e4c","score":52.546296296296305,"score_display":"52.5","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0e35a90242db3ebf58471e83","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"openai/gpt-5-5-instant","model_name":"GPT 5.5 Instant","parameter_count_active":null,"parameter_count_total":null,"provider":"OpenAI","selection_rank":74,"weights_status":"closed"},{"cells":{"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"338126d5df2db3e179ace7b83b90d1370c903c7a11fdae82154daf7bb4583d5c","measurement_key":"ca52e0e70e9ca660c34380633529e437a1f06a0eb943ca4ac58be9f1dfb7b531","metric":"ips_score","protocol_fingerprint":"85af7362c973244df4f06de3900d5d0eb524a91f230df99f3103437aaba240e1","run_fingerprint":"81924903f5e921de5f8f94dcc7cf29f08e45bb259c2f368d932975351511b339","score":-0.07368242078467599,"score_display":"-0.0737","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_73a5d0395f902cb3229076c8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"adbe62f47d1fa97011a896c094efebe4804da53943a3f4dfa15ebdf4bfda50be","measurement_key":"c601c2d88b8d75e6065d8bf15de0ed052258b53d1a4933be2ff45563812ac3eb","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"804c3eb0ce49003c6218653f5d6fb7e82c5393823ceee7469112f27c7f9e6558","score":1455.6645763163579,"score_display":"1456","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d371d7d5e0e9099eb888b168","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"905642a876ba77ce829c929e1838a54bbd99a1e530927ca3c1eea5520d1d1253","measurement_key":"4d564ef852b15960fe1b18669a722f80de82060ab41c53245ecd7a381cbdbdb1","metric":"accuracy","protocol_fingerprint":"36bb2fca4bda91f25f07762b9299161b7c6d16724b0441a070a7833378cad47c","run_fingerprint":"a9694b1edee589e53d411f6b1e1e1ab359b358ccb874f5045e2b1dc9657cffa0","score":9.142857,"score_display":"9.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9bb3bf508162eaffa0f3e019","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"deepswe":{"benchmark_release_id":"release_0f94a5c34a87744f357d4816","benchmark_version":"DeepSWE 1.1 · Qwen comparison run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":79,"at":"2026-08-14","last_confirmed_at":"2026-11-01T03:42:36Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"04c6230f42bf5eeb21096cc35d3653cbc80dc6f63dbe5b4d251b4d22cc409245","measurement_key":"fdc2114f61dfd3f8a4c0310787ecdde94a1b86e56a8a787d2f80b62b2c111faa","metric":"resolved_rate","protocol_fingerprint":"148322bba9aa3bf90b760832066a5d74c8fcb793a80517a108761e22a6184493","run_fingerprint":"ff3f043b1fc70ba355e54f57fc599fe01c8a4d46b8dbcd9e845c073e14db80d4","score":14.2,"score_display":"14.2","source":{"id":"qwen3-8-27b-card","name":"Qwen3.8-27B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.8-27B"},"source_authority_tier":"B","split_or_window":"qwen-vendor-comparison","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e292d3c46b34a34fb650826a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"015132484441c1c193d6b0cf207a3bec8cdc020e9e099b69da161d06b83609f3","measurement_key":"5cd5dc49851742ca98d69e137d4e1ddf66acc737bb7f9ffbbb74511521296d20","metric":"eci","protocol_fingerprint":"0b8859368d7f1e58273fe53363cf70532bde2c845127c74c49351561dd558c26","run_fingerprint":"5bd1eeeaf318f771bdf414cf9b4de3a5c597ba3611acccdc5d52dbacd87f370a","score":147.11,"score_display":"147.11","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e1a173ba85474b81dd96d886","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2be691c5a540d669dc655ec36caa5218baa78c9639bbaeda2405aa51b005cae0","measurement_key":"9ef7a4c57a2125da3eca669a797daea00bf30f4ed143c03f15d46d38f831f4e7","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"6503e291c9d7c606598f28e53137bd9e936aecfbc73279fcbd53c05a90ffbc1f","run_fingerprint":"fe763f9594fc928b24b12205a2fa8e254babe8ae1baa6528b9af42874d0076c2","score":10.2,"score_display":"10.2","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_6823403052eb3e76b6245e53","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":63,"at":"2026-08-29T11:07:26.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"de80b63df64c00f7c027742ecdf9647da0377bdedd08e4ad1427cd8e95f35c2c","measurement_key":"ba60b9263c1fdccc9664927f6302d36b74e0caa2b459a58a484e913099638d8b","metric":"mean_score","protocol_fingerprint":"089d994dba8fbbb9a94adeceadac997c7a787574abb88833801d8debec0ea2ea","run_fingerprint":"0a129c4b1b1f156ca6304bc753948b64c43d806942841e14800443cf64dcaac5","score":34.385964912280706,"score_display":"34.4","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_6823403052eb3e76b6245e53","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"81ab6c4bc698b774599bbdde4e323607eabc524af05feeb11fd42fc4b46af6f2","measurement_key":"cc422aa386b6c56ae04f8832a11283dbc9c35f42ecb310363f0e02fdef238400","metric":"elo","protocol_fingerprint":"60d632058a17a8edd1e7e153f58ee1e9d007adabe41421ebf8b73ee106bd891a","run_fingerprint":"becc7990aeea94c564187e5bd8c96882f43f639057af3b156a068bf244be5046","score":774.8,"score_display":"775","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9bb3bf508162eaffa0f3e019","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_f83cfc2a9e19b8d654d7b58e","benchmark_version":"GPQA Diamond (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ff5afe58e124214134aa3ca6afa85fdbab4fb6ba41ea6fa3b584973124938636","measurement_key":"c2c224d6e9bb728cde1957f3e750a62bd8a211ed63b14e1c8f040d0e45d9d670","metric":"accuracy","protocol_fingerprint":"6da44b0ffa3849ebd85733410cc4bd90109fa36e5cd86f6b89fe10710b3cb3e9","run_fingerprint":"675a8cea96514341f94e531b88be9a4d58c0563e2e2acf5ddd9f05d471eb2b13","score":90.0,"score_display":"90.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"diamond-198-zero-shot-5-repeats","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9bb3bf508162eaffa0f3e019","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_5b5563cd48bd10c552a97181","benchmark_version":"HLE · Qwen comparison run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":79,"at":"2026-08-14","last_confirmed_at":"2026-11-01T03:42:36Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"960bd119403589c91a595638a9e0e2598df9a1517ac1fd38d926899b2043b92b","measurement_key":"2bbaffe57c601e0255b7d1433de89b1f3367c6a2ab8ceb45d7b4bb0608add4a1","metric":"accuracy","protocol_fingerprint":"47241df9da3a012c78b147fc8290f4a7b8b00a7dbd528fd5149c65419be8495e","run_fingerprint":"dec78fb32c956d9452986860f5f511acdac52f778060d512cf40081c0362e35a","score":34.7,"score_display":"34.7","source":{"id":"qwen3-8-27b-card","name":"Qwen3.8-27B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.8-27B"},"source_authority_tier":"B","split_or_window":"vendor-card-protocol-undisclosed","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e292d3c46b34a34fb650826a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7d87a55512e1cbf8d1fb1c9a05964c8950fab8822f709ada66baf7e7aa5fddbc","measurement_key":"2e496ae2f60455445003ca65f29e5ff9a04c51daf7f6078b7551b28ab23dac3f","metric":"accuracy","protocol_fingerprint":"9a1d3939d25507da6fe362b6321d1987c1e52dbebdec771d3a536e0d28035732","run_fingerprint":"e8a8ce6a0ae935d0132ad4646d6915e2923331e79cfa4b22905c6eb15f607ba8","score":35.634847,"score_display":"35.6","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9bb3bf508162eaffa0f3e019","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ea72f44255017aec8f021db36a12e664c3af1f0c44665d9e835a7a77d2d1c3bb","measurement_key":"07b8c3ea80fe3ae5fe57396bc296b7d8fad78f940793ac0d86f3210fd4da6f62","metric":"accuracy","protocol_fingerprint":"f93809cb1601fb231715a1087a0f48409f3053a93ff6588860a4cdbfbd0cd653","run_fingerprint":"63f1f87963095c9d356f59120a5f92cf7747a3adee519d867d035dac18d8db0b","score":80.462428,"score_display":"80.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9bb3bf508162eaffa0f3e019","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"osworld-2":{"benchmark_release_id":"release_15c5525fe39f33bc181dfb69","benchmark_version":"OSWorld 2.0 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:06Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f6fbfb1d0f305a48fc085f1e7aff84e90a5fd031b792235f1b64eb165836724f","measurement_key":"6d558230accef29f7caf2497746f220cb2d7216673006876645616e5fdd34b94","metric":"binary_accuracy","protocol_fingerprint":"6148a7636d450b51ea486e87b225d1c3a61dcb0e7064ecec4c1bbcf6458770ee","run_fingerprint":"fda3dcab3f13e511899df1218677c78d201ece39bfd1d7d347855a0873d48807","score":2.8,"score_display":"2.8","source":{"id":"epoch-osworld-2","name":"Epoch AI mirror · OSWorld 2.0","url":"https://epoch.ai/benchmarks/osworld-2"},"source_authority_tier":"B","split_or_window":"binary-accuracy-500-step-budget","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_d4e18270aaf1ff5ea39c0e8b","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-07T00:02:57.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"91de644b35cab3c2d6a1ae3005dee0aadc723a7b48a8d496b48bbb5a327f87d1","measurement_key":"f432077c7e5ae26541c5b2cf6c54c3215e7269b01fc65a23f8d0f8b27d9e241b","metric":"mean_score","protocol_fingerprint":"c11db80caa95e906de1780744c86ce97eea2a244063e2f0d567b927e1b89146d","run_fingerprint":"3d5cd8a8db31ba38d7033ee2ef4588b9f0968eba1b77e3a4aa4884937c9ae463","score":93.33333333333333,"score_display":"93.3","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9fbc57d50cc30579ef9b8901","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9a3a15b4b9bd1ebff198c4c1e39e1be0acf2805f6c9a450e074f1ff3cd38fec8","measurement_key":"5bf165e6b140e0c1e1eabe71a3231839995e636cd2d352f89a2ac11a8eeef702","metric":"subproblem_accuracy","protocol_fingerprint":"1ce3dab97d66b987eadb8844d61f963f5b913af59fd9d397acf55723fc781a87","run_fingerprint":"ab7f87cdc6d98f47b7d218fb49d2ffc0ffd77a4be82f6de2dd50d611e5f88959","score":46.064814814814795,"score_display":"46.1","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_480536e6d05172cf6b264394","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7cacbaf31aa24c35a6a642290761d31baa1b2efc2c445ffd1962265f37350c6f","measurement_key":"42f7f9fea7b4b28b765ca5a161198a673a10c1835f106fadd050137de819675e","metric":"pass_at_1","protocol_fingerprint":"1d2aded4db688e734f1df56f297ba2ee088657007600375a37ac6d3fbb4d7682","run_fingerprint":"0f42e09782c1a462fd01d2a99bbd3d386d88c873182de4faa14311beb9357ff0","score":17.525773,"score_display":"17.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9bb3bf508162eaffa0f3e019","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2bc8e9da90aecb61f4ff868e78a50d82b6f23b5d7fa8f15196e1948930f2bc5e","measurement_key":"c58b39bdf7ba9e48ba2857b76c02e6e5334b97c996e68f951bdb131880b8bab5","metric":"accuracy","protocol_fingerprint":"ac185b03ab001eae7f5132118ef2c4a7313adbd2950c4f51516f792c1cdfc1bd","run_fingerprint":"0f971e94e5c5e5e5cb542f5024634434b0be1316744aa9050fa8a45ea4171bb8","score":52.809,"score_display":"52.8","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a276c3b003828a116e9aecd3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_b7d9ab744ffac0cb856e114d","benchmark_version":"Terminal-Bench 4.0 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:17Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"587608a517425c07c55c8851893ad010b81ad062abbab39078b4ca9e6cd7be44","measurement_key":"dded39bdfb9325971e53d5db666e92b4b52bf13096fe8eaf2466569f38bfefe1","metric":"pass_at_1","protocol_fingerprint":"7be448a07df209b1aa0aa5481a894480f413697d05279f0575f1dec13ee36064","run_fingerprint":"d434e0a869a8d76eda5546d399f8361bd4413e97ccb8bce2d7aff23132cc859d","score":1.010101,"score_display":"1.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"mini-swe-agent-66-tasks-500-steps","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9bb3bf508162eaffa0f3e019","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a783e59a5fddb32b643d8f818035108fb6395f78215b4453578761b9b5ad0a45","measurement_key":"b32357f7f6a398205f7f7d2a8e2349403c9b2a8f1555dfc74a9ae471bb13d7b1","metric":"score","protocol_fingerprint":"e0e882b0ab35fdffb55e468beacc03755573f89707e73a0c80aaeb6aae20733e","run_fingerprint":"9abe8065d30e888b98de1687c93757629176491038684b4b3745887b82f908a2","score":46.391,"score_display":"46.4","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f76a19fb1cd57c1a8d315778","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}},"local_open_weight_essential":false,"model_id":"alibaba/qwen3-7-plus","model_name":"Qwen 3.7 Plus","parameter_count_active":null,"parameter_count_total":null,"provider":"Alibaba","selection_rank":75,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9e7fa0a79d208a3b11da755e52db9751e31b3f65899f87157f527521f88373e3","measurement_key":"5e08716f6539e2ab75248a462ff2c16bc01cc28fe883ed92958ccf6953ab578b","metric":"performance_rating","protocol_fingerprint":"5540096dfcc8c3c297c5fa426d9e3ce6369532054938f8a51b1175afd64203a7","run_fingerprint":"6aa3c5885c8dd82617f4b3334d8167817a34894de56d82a53aad84ca1d604b56","score":1004.52,"score_display":"1004.52","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_5bec2cbd214ab2f1bec419a3","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e54a988e17fd99fe0e6d4509efe70f9ca0a2a261f64d9334fb08e1852ed22042","measurement_key":"0f1a373b647f97fe915741b4978b5057373c7a9950a872407a896e88f8286fe2","metric":"pass_at_2_accuracy","protocol_fingerprint":"6639afb33b297a63129ad1db4133d6f05051363ec0cc4f04a095f163e8058946","run_fingerprint":"7c28fdea7056a624133cd1d3b1f0cfdd3b9cb0f807eb1e36a27898bb91f5a111","score":51.5,"score_display":"51.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_0bdad69e8278c95ccb05d676","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ae2748613ef4f3b8530aab376b93e3c4e306d2b3f789a2edfe3ad1a600d3d0d5","measurement_key":"3c15e05987fb9c7ed7aa66bbbab61ba7d923ac7900332643c53be3512a9056cb","metric":"accuracy","protocol_fingerprint":"01ad944d01ddecc00a82f5739b0aa8928b7e1d102db1bd4cb03edeee749afc04","run_fingerprint":"b926d879a1dc3646020f7f476c4d3126ef9801c7e23b59fac460232046f2b08b","score":5.6899999999999995,"score_display":"6","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_0bdad69e8278c95ccb05d676","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b29f11101ff98f6a523f2a2aef712828ddd4a5730105ec5f8df87245194c37b5","measurement_key":"b136643fc0e9ca5861a58da0796e4c9dcd089f202d18b162d2c23ecb8cadae50","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"e3baa678b37e481d7abefac54911144be5d55310caa02cd2ffad117b523c4c90","score":1401.1879805288152,"score_display":"1401","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_5bec2cbd214ab2f1bec419a3","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":17,"at":"2026-10-14T18:22:26.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f064e73ce4c0c92db4ecbd59bfc545c902610390783f571e9af2b661a6baed6c","measurement_key":"eac6023be85b6f63d94984cf7a3674785f4362c1f09ca0b8f76956e1047c55c9","metric":"mean_score","protocol_fingerprint":"d8e54fed013e0bd0c52121f1764e7f068ff5e831139177664102a571d32eca74","run_fingerprint":"a0455a27f71865ebd6076f79ff9d91725bce68b6bc1711e30105176404e324f1","score":45.0,"score_display":"45.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_0bdad69e8278c95ccb05d676","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:13Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"933fecb1b0cf543972b6b46177adf9cb05f47d2458c60269edae00508ca9f3d9","measurement_key":"ab7b1e6da47950327f683426408a8683d958c2bf069244134ed4446401d04016","metric":"accuracy","protocol_fingerprint":"faa9cc272286e3acb5520699808be0fab7320804012d0d12a9cebf6ce040f54c","run_fingerprint":"3f9ce7853d3fa9be8436e8c126e796cd618718b3d2be2abcec84e64f53b8fad0","score":9.253061224489791,"score_display":"9.3","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_0bdad69e8278c95ccb05d676","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"308320de518bb48fb10f2e9b57235f3cd0c7c469b59f62897a8541584252efe5","measurement_key":"85b60576f64c3b999be8385e83a5f37236905a31fa3fe9055ce7e861574fda07","metric":"eci","protocol_fingerprint":"9d153826daea7706daf0e976628c6cb0d3bc6ae4277455d4f0386b86785301a6","run_fingerprint":"dd5801125398c6442e1fe026a7527c4c3023515f4b621b0903411ec16698ce7f","score":146.14,"score_display":"146.14","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c58cd8aea3620eea4e04e0b2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":141,"at":"2026-06-12T16:48:06.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b08c78c0affd578b0d0b52f461d5c6870b6f881c016b4c6c60ad8e6990a921c5","measurement_key":"e7e3965344be9bc126be12e2b685803e5a9ebc405c20c5df689e64e304202ed6","metric":"mean_score","protocol_fingerprint":"93d550bd4f0659ec8d3b3eb5c3b3db2737270435e50ab1c146000095e38607fd","run_fingerprint":"f43f3780db22ace19bb72071bebb55434b8c0dedc1627c68d06919adebc90a8a","score":44.91228070175438,"score_display":"44.9","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_5bec2cbd214ab2f1bec419a3","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":141,"at":"2026-06-12T16:48:06.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3777058552c5eba6b0432042b5202b18fcae18c021e988cd8eaeb3daf4d1eca2","measurement_key":"09d0a60b77eacced0edaa23839ea757cf8343bdb7ede9c5a43531b55a9f2649b","metric":"mean_score","protocol_fingerprint":"d893fe105e20ffada7ffbe0fcf3bab7fdadcc1d84a7dc9423bf50cae4db895aa","run_fingerprint":"11e51bd4855b3049a3eb207c5e93fc485c30b6572856242ce9a16fe0eb0a3884","score":12.195121951219512,"score_display":"12.2","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_5bec2cbd214ab2f1bec419a3","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4e9868a18bb92279d99121a1fe9263da2ad06df167376b35548f7a6e9ca17138","measurement_key":"6dc14dc793bbce2d770f0eab76493a0372d24957d14d1d6494843ad834b844b9","metric":"elo","protocol_fingerprint":"cd57b3fbfbf16855b17f40a847e576c77b934f17ff4ff7addd0472cda93ec8dc","run_fingerprint":"7701cffcc546c451b5df8a307afaa08ceb0031f4ef8c129d7591faaa8891200c","score":954.72,"score_display":"955","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_0bdad69e8278c95ccb05d676","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cdee10adcc02edc1e10e77ab668e120bd0b71fa0f972e8eb4ece0747089d70ef","measurement_key":"de386840b25c31eb9bd3ad27131b0720a7867efe596708c2193586ab3b1146e3","metric":"accuracy","protocol_fingerprint":"f72e26ad04d2580d59f2a069a20b7b41c4b42747977e5f47fc8fe47a4a27f21b","run_fingerprint":"1a6a4069437078abff2e3b6bcc79f740c450c3a7e807e4413b763b8a78545e6b","score":77.526,"score_display":"77.53","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_5bec2cbd214ab2f1bec419a3","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f1880b24c6df4d78d0082b4f8cda1b1605f2c9c20f83cda842992841b813ab14","measurement_key":"c5cbd80ad26337cfe6024a230823bc0033afb842a9688f7ca5dc9a4562174e79","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"5b78052bd5a6cc1a6beba5cb663dbb0f13fa5290967f89673714c08c64435383","score":69.57636904761905,"score_display":"69.58","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_0bdad69e8278c95ccb05d676","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1223c0c1ddcaad4645fbbce980461fac4c92fd2782dfc537f96c6235cee3ae6e","measurement_key":"3dc5d20c122fbbf6eb7a8ebee99b3feedb12de3b5a8468c4e80a5ae9c0e6607d","metric":"pass_at_1","protocol_fingerprint":"63df3ba2664e1731dfc6a1e5cb7e5005e4878249c8fb64edc6366ad405677264","run_fingerprint":"5c2cab297461f68f5597e41ab6a3a7c9777ed4babfd0828025cab8099f5c8738","score":84.009,"score_display":"84.0","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_5bec2cbd214ab2f1bec419a3","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"640d532f16269fd6058dc28c8001da5a59b3fa56aa2916086e76b25d5d1ac6e8","measurement_key":"eae7d8eaad410b10a9099832110802dfe4ea2bb0e0fc3cc1620415daff137968","metric":"accuracy","protocol_fingerprint":"623f1a4152e4efdb2d991f16352ac0fe2f8087a90806b85a6854d6a69e38c31e","run_fingerprint":"09073b0edd3295b959cb637db371a4dfdb5aec656877b8bd7b5b9cc90b32cca8","score":77.172,"score_display":"77.2","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_5bec2cbd214ab2f1bec419a3","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:41Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1ed72de538a194379a952580d0d29e39fe192d104737e91854d5f8e3c3170d21","measurement_key":"d29a82a1a28dd9b7b2290c4be25637d673e332ca4896958a30f0365ac704d624","metric":"accuracy","protocol_fingerprint":"ebe1766a0644371b65ce86b721bcd3eaa876d6dbb47b5e38f43bb8e668fd1379","run_fingerprint":"f4f0768948193a4755722c4fc40529e0440897914522e622d4c350333c0f0892","score":73.584,"score_display":"73.6","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_5bec2cbd214ab2f1bec419a3","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":200,"at":"2026-04-14T15:08:33.525Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"f555649ba4aeb1c844035bebe58cfa39d9b0c0de027e0772f9693fd0e0fc9ed7","measurement_key":"7c5679bd3485520bbb233e61c4fc8939ba8d543031959ee6ac8ca91dd5c99ae5","metric":"mean_score","protocol_fingerprint":"533f1ef8c0aa7368cc8ce278ba524911f1b9cdf50e3b24c5b3d290e6cbb3e9ee","run_fingerprint":"78354ff77b0bda88f5264c545ff8be27f42a8df59e03133d4f8009fea49c8b5b","score":87.78,"score_display":"87.8","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_5bec2cbd214ab2f1bec419a3","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0cba08a1664d1bd3610b75bee27eb288e6c66817f89298ba4cd1b65fa90aa978","measurement_key":"58e53d55769078fca0f234eeb137fa03c5324f50c0815df6486aaa6e3abfdc28","metric":"subproblem_accuracy","protocol_fingerprint":"774cb81eb6f5c92014a6deb628bdc0c97e393e7196f28fee7da197c267d5d6c7","run_fingerprint":"70bcbcb12b672c46058d9ef22a2558bf1133252b287cf77e5b61a1d433d2ee62","score":47.2222222222222,"score_display":"47.2","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_0bdad69e8278c95ccb05d676","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:28:50.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"feb65bca9e3644603b0d1dd802c04d67b3a7d52040fed21145d0e2def65700db","measurement_key":"e6d23308566f1b4b9b2238fe86839ef35c59512dd6efbfd5e432b3b081c63788","metric":"accuracy","protocol_fingerprint":"40c85021eb5d68a8360d0cf162dc8111f4c27837683acd2c7671760bb97b1290","run_fingerprint":"d111f5e5ef96312bfcd04b4a5bd268bca9c360097f2b705e5ea4d1a3a55f8c83","score":11.700000000000001,"score_display":"11.7","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_5bec2cbd214ab2f1bec419a3","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"63c847df4cc78c57c3d4b5c8a573c545ff87bc1ffca257502fe71ad5d23a6599","measurement_key":"eda7486eac7e2ae86f91a48bbb843322a1800983d36ccc4daa64b5326f4d7f4e","metric":"resolved_rate","protocol_fingerprint":"e34f8d70308d221225c6a6b5995d36e4ea38c50c1fcb94081bb19e87afe195bb","run_fingerprint":"9da4bfde58e7cb364ab410113642ce4ca16ea5ab710ea81d3e4709595ff9f9d6","score":69.8,"score_display":"69.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_5bec2cbd214ab2f1bec419a3","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"63c847df4cc78c57c3d4b5c8a573c545ff87bc1ffca257502fe71ad5d23a6599","measurement_key":"eda7486eac7e2ae86f91a48bbb843322a1800983d36ccc4daa64b5326f4d7f4e","metric":"resolved_rate","protocol_fingerprint":"e34f8d70308d221225c6a6b5995d36e4ea38c50c1fcb94081bb19e87afe195bb","reporting_origin":"organizer","run_fingerprint":"9da4bfde58e7cb364ab410113642ce4ca16ea5ab710ea81d3e4709595ff9f9d6","score":69.8,"score_display":"69.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_5bec2cbd214ab2f1bec419a3","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"71736e1dad4375a3e431f68be081a30ce2640231ce0bdeb42d569e6e9fb68ddb","measurement_key":"acbbcdc8d4e49e1151a306f466f722ba8aa422c185bc1b6003e995ebfd689b32","metric":"accuracy","protocol_fingerprint":"7f8387c87843a1438cd189e32941eea7928dd353e750953be9998bf4afa47e2e","run_fingerprint":"e395d250532b08a28d1f4022364e03bb0e4046f171ec1fabb5953c05532a3f76","score":41.573,"score_display":"41.6","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_5bec2cbd214ab2f1bec419a3","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4f0457b8001941db69a20406e61f16cee0dc2273d0f12de7efebeb86d1355ef7","measurement_key":"a16226652dca864c09eae55c66a412b329b3518b714070848c716d9fd8c3b365","metric":"score","protocol_fingerprint":"bdd04c7612461a8e24170cd07c97e96da8a9b2653374baff5b15904723879c90","run_fingerprint":"1271d0c3cf5168a82a5449e11163bf86ee17ee748b64773f25e6149a8aa27e54","score":26.097,"score_display":"26.1","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_5bec2cbd214ab2f1bec419a3","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"263dc56d121746f73279ae75ce123546680d1a82ab2b6a290700332984a7cbc8","measurement_key":"f648a25623d0043c934e1dcc4850c60fcce491e093e6a3fa682f8c0ebc78c796","metric":"accuracy","protocol_fingerprint":"50acdb50a06c35f2d73d3d2a986a6a213b3ef2d53afda42f0f791ddd3fadee20","run_fingerprint":"3be0a09e2564322cedec1e980f51eaac94d724612268327f285978e75fc782c6","score":49.23,"score_display":"49.2","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_5bec2cbd214ab2f1bec419a3","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"openai/gpt-5-4-nano","model_name":"GPT 5.4 Nano","parameter_count_active":null,"parameter_count_total":null,"provider":"OpenAI","selection_rank":76,"weights_status":"closed"},{"cells":{"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0999662c2a65baf4e3201c041f91d8d892abc3fc1d86ca49815b8f9f2120c9bc","measurement_key":"ac70a55658c1c82ad75f3f6083e8b20e41aa8837a66daa44ae2d952384be7aae","metric":"ips_score","protocol_fingerprint":"df183e60ce4fe8b2852c7212f45ae1ff2aa3f20ca770862225146185ac43e1b0","run_fingerprint":"60934a3e4a0ad2c25534453b7e8b6605c7a27d7aa1837a3d49414b7180c0c0cd","score":-0.07319108163660436,"score_display":"-0.0732","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_98914b89929791d91bf8e5de","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cae77396fe9596c576e2b89a0225885c7e63bd6f2d8ba44686098508d0277586","measurement_key":"70393dd1fe24a0f6e41fb997731bd4dc5d68ac3b36e615fa0aa92ca127675096","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"7305984d0004fe014cd7982916eacd297d4fe3381fc2fa36702bc489c3638229","score":1454.4774865775755,"score_display":"1454","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a509997ff81cf41e490ff500","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"547dc635535bd401d4db1082711946bd68fe099e02a0fc3147a83f267a0d9677","measurement_key":"41d845dba57e019de973d11ee6a04f9914e61e8b90a68f886364a7da58741e28","metric":"accuracy","protocol_fingerprint":"557294d53731dd4ee147720dd4cc5020da030224bfdc018e2e139a89a5772a2d","run_fingerprint":"d8fb57dac56449f1a2902155e77125960197e1ee403cf2b7c8ad501d51130092","score":4.857143,"score_display":"4.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6c679e74ea315691491c34a6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"34224114512140765deaa0c42e860ff66abffd4ccf5168ce198c56214ffe80b7","measurement_key":"83e32fa7d556cac6dd698473be32c9b0b8306a61f25b776ca6705fa43d730a9b","metric":"elo","protocol_fingerprint":"804c8ce66603cd95625f80c49ab297e8a54461e9369f479c96b81c73ea192dae","run_fingerprint":"bef0ad728b0b9eb59dcd01897a8bdba14947150e1599d5f613ec27f5b2b238da","score":1070.64,"score_display":"1071","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6c679e74ea315691491c34a6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_f83cfc2a9e19b8d654d7b58e","benchmark_version":"GPQA Diamond (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"69b65fbffb5eaf7c17783abf1aa4e9e0cc108f1e7d390e8ff0d0fe36e88a9ec9","measurement_key":"d3f7ce57ed19e9cd14d255fc7dd6aea701e56f1ba4c2acfca08707ff5ad3f3aa","metric":"accuracy","protocol_fingerprint":"968a1aaa9a52dab88e7556ea31cf218dddcbb7cd59f724c61f9671a804d1e469","run_fingerprint":"a084ac1f910f76478412b3446990065399ae7ed2776457c7399b18771e529ecc","score":89.69697,"score_display":"89.7","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"diamond-198-zero-shot-5-repeats","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6c679e74ea315691491c34a6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_fa9e908ac04b067eb00182d4","benchmark_version":"HLE official leaderboard","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":63,"at":"2026-08-29T23:52:43Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c8a127e30c3ab6e3ed54a2c690e500388967fa6b7167692b5449c719d3eab7fc","measurement_key":"3adb89c5af2c1075ee1d1b6bd1c155e3fcee693ed1826711b9c4db742ddd35e8","metric":"accuracy","protocol_fingerprint":"e1f956386a97e6ba42a3c396757902d19f19cdabb10fcc91e345af5c771a2890","run_fingerprint":"abb0f27ca6c91deeef5c2def315b862e46ae528af565053f16c9b6ee6f3f9f63","score":53.2,"score_display":"53.2","source":{"id":"hle","name":"Humanity's Last Exam","url":"https://huggingface.co/api/datasets/cais/hle/leaderboard?limit=200"},"source_authority_tier":"A","split_or_window":"published-leaderboard","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f4211279c9136484fa19f66c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"C","evidence_rank":5,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"self-reported","verified_status":"self-reported"},"unit":"percent","verification_status":"self-reported"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8b9c7a1a6bb2ba14131a6cf9f920ccf1f8d8b4f168c49367d0d3d7093f13861b","measurement_key":"ca054d4378044a5979de3e559b42bbfba9b0de1a24ea4139e29fe8f6acfa40dd","metric":"accuracy","protocol_fingerprint":"99e293e55aea33c8da4281cb1f0b4953904152d4dcfebc447c94533136e55b89","run_fingerprint":"eaeb1c7497ab461551f02de356846f0fdbaf6b5e8d373a26267cb1f4252cd203","score":33.456905,"score_display":"33.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6c679e74ea315691491c34a6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_de40c66bd40a7b5483b40f9a","benchmark_version":"SciCode v1.0.1 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":56,"at":"2026-09-06T00:23:09Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fa1eb6e10d4b5fd557a7b042c1b251395f2ef06b28be96b69d7115df562140f8","measurement_key":"dcb50518de57c9bb7775aeb90245c09c9bade3873a2ed4811de4b8d5d6834337","metric":"subproblem_accuracy","protocol_fingerprint":"8069bfb27e3b6e2131beda5c8418ee8f0f925f7d5b1f588604dee47a34436e6b","run_fingerprint":"68abdf82eaecc737ea971d984491ec8b183a6f8411fef691db226d4ed0b1f1bb","score":48.611111,"score_display":"48.6","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6c679e74ea315691491c34a6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8f2e8377a8c9d3693792b0a4d92011216f1f1b7ed774a62b3490bc0f9b66b1c1","measurement_key":"f945b22dccf6141c2f7d5959cee74ea63a6d2feab0bd44b8074bdaff9110c45d","metric":"pass_at_1","protocol_fingerprint":"901c1c3599875db999a6318b4ba524fec4cb69a2681dfc9635e7d05522a6a9d8","run_fingerprint":"427ab27e8bb9d597fd52ca33697d7bffe8dda0f956232e9500339f3f3edecb58","score":22.886598,"score_display":"22.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6c679e74ea315691491c34a6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_c53c830678318dc1763793c8","benchmark_version":"Terminal-Bench 2.1 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"566f3c6b23333229453439381201e086ee26b02992d3011d39a4f49ae64cca1d","measurement_key":"c1dc4c100c0facea273b019e8533e0d10da584455033a61ce7c2c4f135e66e8f","metric":"pass_at_1","protocol_fingerprint":"50d9f98c8f53af161f65126accb9fe71cf1c7cf6a5e840a31b81beedd97361b6","run_fingerprint":"b26d81f12c9fa887383fc55cec363b1690f283e40c421973158f1443d8b8d057","score":64.419476,"score_display":"64.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"terminus-2-89-tasks","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6c679e74ea315691491c34a6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_b7d9ab744ffac0cb856e114d","benchmark_version":"Terminal-Bench 4.0 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:17Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1b54687bbb293f0f261c5447839a16e0e51e108544df597a4cd55c65e1b46bf9","measurement_key":"eca8178913ea0e886982474c2653a432bece59df1b137fd13ca1bc7accdb9425","metric":"pass_at_1","protocol_fingerprint":"f2d7519d685297661d499a7fc637adf730f530d3a9dcb0771a8507f792579d99","run_fingerprint":"77a6a8e24a0a32fe2fe5748cf07f8f9c1d69f52776f1106db385d5c91797a476","score":0.505051,"score_display":"0.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"mini-swe-agent-66-tasks-500-steps","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6c679e74ea315691491c34a6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"679f694b4269aaec3a56c489bf009ee40dfa27e3d94d16f5e771bf15c721c465","measurement_key":"cb604bac146eae810cf1af11d9e5f03d14ce76fcab18647f4b488935881c5a1b","metric":"arena_score","protocol_fingerprint":"3062a6cfc0dac05b72943619088607bff4ea22b102402c9cc8be4543140815eb","run_fingerprint":"59805de91f39259d8974ef6b42012118e45084830d663dc9c8bb17e395d6ef67","score":1505.4337074624896,"score_display":"1505","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_debe9c2cc9379011d1013ab2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"tencent/hy3","model_name":"HY3","parameter_count_active":null,"parameter_count_total":null,"provider":"Tencent","selection_rank":77,"weights_status":"open"},{"cells":{"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"66e13ad60058def31fea513b1e4270be3fcc7b7983d1592cc4712d19b2f1c408","measurement_key":"6cab746b1964c3c4169fc6fbf4f9773295ae8addfc921857d8f529e73af67c74","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"57f371335360a4f161c0d9e39361cecafa33d588bd6fbab701d79eb1f93c468b","score":1465.0468418320115,"score_display":"1465","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_308a2315a1ffdf31f407f589","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0adbb9be2843771fc31bb99824befd28ea01c139fd40627102b8c1ccd04fd160","measurement_key":"bc41449bacdd9c06f3dfe7cbe3cf34604ca421bd479261798838ba4fb08d1e5d","metric":"arena_score","protocol_fingerprint":"e9e202e65e7b57dcfcd00a5ec44dc3dd0764c8ee1c04c0c8c5dfa2259d312a92","run_fingerprint":"c0ed80ce77e0329eab86818623dfdce67e2e616fa0ecb29c2bc6c1304cd4c40c","score":1214.468784837361,"score_display":"1214","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_308a2315a1ffdf31f407f589","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"xai/grok-4-1","model_name":"Grok 4.1","parameter_count_active":null,"parameter_count_total":null,"provider":"xAI","selection_rank":78,"weights_status":"closed"},{"cells":{"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"af1d6a67e7531c0f8c7470ce59b87e458718fc7eecdf26edf64adc657a6b2442","measurement_key":"b8ac14741c155469baf765976013e6f2bd26b86ac70e573307d61317d61f458d","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"0611d496790f1811621a1034cc1151d90f61fb1ea545dda26c9fec7e004e8680","score":1346.8185340713344,"score_display":"1347","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3aa37c0df95a457752b0f86c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"bfcl-v4":{"benchmark_release_id":"release_7d2560723dba9d549cd10b25","benchmark_version":"v4-ede5081a24bc","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":64,"at":"2026-08-28T22:03:18Z","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cd33793f9ebd5eb7f1920add92d5603dfea50457d9123964e7e5b97d8d22bee7","measurement_key":"8c6280b2e007c078877ca053cd7a3395e689059845280eb5e9db03a11de7b20b","metric":"overall_accuracy","protocol_fingerprint":"6a9c99bccbca11748bdf70a2bdd6eb864726c94bf4a029f84ab95898fe96d192","run_fingerprint":"3a2a5707980d70897715555f206b9c658905ff52e75014ffe7230cd45ed5e559","score":48.71,"score_display":"48.71","source":{"id":"bfcl-v4","name":"BFCL V4","url":"https://gorilla.cs.berkeley.edu/leaderboard.html"},"source_authority_tier":"A","split_or_window":"overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_85ab9abe2438a5cb1fc4cac5","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:41Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0f91fae05dba326ada869c485e4fd7a9d8149a8eb01735bc2a523c1de7ef6460","measurement_key":"1c768ad5b0536187043199c9bd72b89dd1accc2a53b7f19c305985a3c0a83ad0","metric":"accuracy","protocol_fingerprint":"eac59e785a258c2e38d55b2af57e244a9a7b33dcf9cfaa45c3270de9367d03bc","run_fingerprint":"a62f5885bd0cac2b69539b5650d1a634651ee4f51e6e6c5db78909d6b3a16084","score":0.28571428571428603,"score_display":"0.3","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_5eeb27f9b68bb2dd1366ce55","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"df2c32a21a554ff00885c8252541ef7efb7d2e52cf771686cc493c154668e0f5","measurement_key":"9d34c1e1eb86cf0daa255be08cd0dbeffc3192f230f209ff799885ab0e5c6ee2","metric":"eci","protocol_fingerprint":"bd447d1b8a6d17ef80da168963c315dbe54affa185e70019a1908f20f73a53c1","run_fingerprint":"d62f8e3a8244d3034194ebe5a50b9061b3265aa6b1da081daa29d9ab0514d6dc","score":138.48,"score_display":"138.48","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_cebf1706df3e3613a3a126de","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"72df5610eaacb1b218bf979923218a4143d4bf405b65e31f39b6c054e276eb68","measurement_key":"467e8cd33b356b8eaa4083b0021211f22b45f79382ec6f6a086bc38a16c628ba","metric":"elo","protocol_fingerprint":"c4a2978edafe5419f8b06f382adfed858b2b8d8592b93c058d010bc999d0ad30","run_fingerprint":"b23a652c87c3dee026bb49fa8ded929583b9002e3866494b3ff4121d1a1cac0b","score":40.84,"score_display":"41","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_d3418e26019f2a26b71ed3db","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T22:45:08.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c578cdea3d58140408d5d4da790a56540deb3d3cfe0545d76625472161466e01","measurement_key":"d216747a89242cf63c37fb41017cf1adc3f3d11f53426fe8ab09ead1692c8e47","metric":"accuracy","protocol_fingerprint":"9f415d65db681547f574fafbfd1adb7f8ea722f85b42ef092c6e4a25fd9cb7a9","run_fingerprint":"691c23e9102bd1e86c1a6cdebd12a8fce26c0d2c254c7801b98a09a44a45fbe6","score":54.10353535353535,"score_display":"54.1","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_cebf1706df3e3613a3a126de","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ifbench":{"benchmark_release_id":"release_4adf348ac2f76539ed7ccb10","benchmark_version":"swallow-evaluation-instruct","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-09-30T18:53:19Z","last_confirmed_at":"2026-11-01T03:42:24Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c87ee84344739cf66d96a8f54cfe116d10f02e915868c57822fde2fcabfa4af1","measurement_key":"d15f725d02999ed5f488126f84ba6d0172763e1e4dd59e1cfd42ddded3a6da7e","metric":"inst_level_strict_acc","protocol_fingerprint":"ee7e2333dcebcd23fdc8d1d794d58c4e202e42da23d768519a4735d0c3f880ca","run_fingerprint":"0f220e63f7c9a937537f26f094eefde7fb7f7a57bc8630e1cca5b98681770f95","score":29.4,"score_display":"29.4","source":{"id":"swallow-llm-leaderboard","name":"Swallow LLM Leaderboard","url":"https://raw.githubusercontent.com/swallow-llm/leaderboard/c58a13a852eba061d639af7caf4ddbdff33b36e3/swallow_leaderboard_post_en.js"},"source_authority_tier":"B","split_or_window":"ifbench-test-300-prompts-344-instructions","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_d3418e26019f2a26b71ed3db","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T22:45:19.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a56b56716bcf2f4555dd9e7fc7d0a954bd1a530c656633433041c1317041d760","measurement_key":"8eab303dec89d89fd9b75f3157505cc265ad3ace59d879435c3e60809c8500b0","metric":"mean_score","protocol_fingerprint":"7b3ac10f47270801e3a35e6dace9a96bafc344848517ae97dda76973b235815b","run_fingerprint":"c5f89d278b050168600020b469a199b0e07f3955621040c08d98d8b5cd43b204","score":23.055555555555557,"score_display":"23.1","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_cebf1706df3e3613a3a126de","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:47:54Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5dc15a58f66a0e5ec2623c0cb36cea07fabf18ed9c6a1568b006fc195e1055d9","measurement_key":"de75d543663dc1c7409d6bfbad98b5aa6e44993d6b152a4f95c65fa241b16541","metric":"subproblem_accuracy","protocol_fingerprint":"a8a54d7bb5464445029ee47794e5942fd4724f3060920e9fe4a6a64e74e5cfd0","run_fingerprint":"ad7fd25da6f6bdd1182b7f6884f481b87c67249d551f11f9cbc7b1d81babc840","score":35.4166666666667,"score_display":"35.4","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7b558a43320ab043f3b5f3e3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":true,"model_id":"alibaba/qwen3-32b","model_name":"Qwen 3 32B","parameter_count_active":null,"parameter_count_total":32800000000,"provider":"Alibaba","selection_rank":79,"weights_status":"open"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"62669d48b84e7eedc5ab6ae508a7709e5a2fb54da28a647694f6fa2294374c94","measurement_key":"f14f95ab369e781bd17078c6aa92d2eb8604d7ca89228af63bf76a0f13a6c384","metric":"performance_rating","protocol_fingerprint":"11a3f9a7201ffbf5ce021e153c092dbee9b3c852f72843e74bf3a6f6832cc58c","run_fingerprint":"366d79a456cfa56c4b5a234914e8b7329d369e0f3af82929285495980ea9de5a","score":349.45,"score_display":"349.45","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d51b4d24a4d78655be5fdb73","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"238903a13c04278fc44b1c6190ef3920f97034a6c23ce7a32be718915fb058b7","measurement_key":"f31e0337d505b4e33efe5ce86e9774d0229d63f1ccc0f0fd8a0e1e8312735afe","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"cd6a6ffaaea84dfb29e580f17e56d812dd882f91d45310a6cddb8fde90e8f2a8","score":1408.8059895114475,"score_display":"1409","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e7d27865cc833f004dcca283","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"bfcl-v4":{"benchmark_release_id":"release_6b9456463dae72f95fadf6b3","benchmark_version":"BFCL V4 · Qwen vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":250,"at":"2026-02-24","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"81b4ebffb3d2731b02c754f4c014f149f13ca4ef67fc13f096dc738a4530ad27","measurement_key":"2d2e7fdb7181a89d151c2d8fcd5f6925837850bb0b3a0c91850aac4b0ae6f295","metric":"overall_accuracy","protocol_fingerprint":"9aca4b26ad4c1fb4b38873d2a78f94206d521bb77b8fd1c6904a2c439362580d","run_fingerprint":"7c59d77b1784d000e4aa71ca70d868f07aa757e7e037d317225c8ab8b7fbd3b1","score":68.5,"score_display":"68.5","source":{"id":"qwen3-5-27b-card","name":"Qwen3.5-27B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.5-27B"},"source_authority_tier":"B","split_or_window":"vendor-card-protocol-undisclosed","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f5f4005af8cee78d3b3a8a61","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"gpqa-diamond":{"benchmark_release_id":"release_beac9b3474dc330fed0ebc77","benchmark_version":"GPQA Diamond · Qwen vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":250,"at":"2026-02-24","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"90735b1194831c86757ca422ccf5424507f9e5630c1b91d28279b2b73b685146","measurement_key":"0c755d8bfee5eb9a5cbfeb3abe878adeeac4d3ff49773f1b837827dbf28c345c","metric":"accuracy","protocol_fingerprint":"1ff9ae2ef8d730817a6d761b03392d3f8a0e65ea332abf727e3e7f33f3bf7ac6","run_fingerprint":"2a4db942edad015be6422bd3339808797367937820040ec2457a325b9b3d6352","score":85.5,"score_display":"85.5","source":{"id":"qwen3-5-27b-card","name":"Qwen3.5-27B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.5-27B"},"source_authority_tier":"B","split_or_window":"diamond-vendor-protocol-undisclosed","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f5f4005af8cee78d3b3a8a61","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"hle":{"benchmark_release_id":"release_2f3c6e21d0f3616fdb78f627","benchmark_version":"HLE · Qwen vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":250,"at":"2026-02-24","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"aa2dc90a9c9803881d44c1b50e12eb93581ecff4c046d127ebc0056bdc37de1e","measurement_key":"627cab1ef11fd778dfa8e0abe5198a624d4b206d347b4bacf8b087f8ee4e9e48","metric":"accuracy","protocol_fingerprint":"5193c99f2c93e1107d46b911094f08dc7f18c6366de909d53f5f747daef3985a","run_fingerprint":"8f70acf791c9f0e0ca3cce26e0c9aa8213dd72869af99935664bd2fc013beeff","score":24.3,"score_display":"24.3","source":{"id":"qwen3-5-27b-card","name":"Qwen3.5-27B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.5-27B"},"source_authority_tier":"B","split_or_window":"full-multimodal-cot-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f5f4005af8cee78d3b3a8a61","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"ifbench":{"benchmark_release_id":"release_4adf348ac2f76539ed7ccb10","benchmark_version":"swallow-evaluation-instruct","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-09-30T18:53:19Z","last_confirmed_at":"2026-11-01T03:42:24Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"364a58e2266ed75054278deaf8f86b1c610d9ae7cea42a038eb22903f5e917ca","measurement_key":"80fe711b48cf3d68b63210ea82c4e45004710b4b8302dfdf731a5de85eb46acc","metric":"inst_level_strict_acc","protocol_fingerprint":"9b012eb36f1c2f4cf17e351131da2df24841c3192da533ea9c19d25ddab91dc8","run_fingerprint":"0787a798a6bd1c7f7632699f20bd8d9b6332cdcf8cf1433473fa15196b9d1d9e","score":64.5,"score_display":"64.5","source":{"id":"swallow-llm-leaderboard","name":"Swallow LLM Leaderboard","url":"https://raw.githubusercontent.com/swallow-llm/leaderboard/c58a13a852eba061d639af7caf4ddbdff33b36e3/swallow_leaderboard_post_en.js"},"source_authority_tier":"B","split_or_window":"ifbench-test-300-prompts-344-instructions","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_de190b968e73c379f7673b4a","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"ifeval":{"benchmark_release_id":"release_eaa2f0262bb0264860cb2c8e","benchmark_version":"IFEval","comparison_lane":"source-specific","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":250,"at":"2026-02-24","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"0f60a9e8e68f08820766291b50b9518c5af029b98299a55e1948489249a8077c","measurement_key":"54ec5bef9decfcc5115733d1b134ae0279113b0a5bedeb32e38d25d29e87e52b","metric":"accuracy","protocol_fingerprint":"e9e17b8e0074098f32daf83a5b38ae12858d3337cf27da604f333e45a9c74efb","run_fingerprint":"ad0b1c0431eb2137759034f5a08551f176b3e89a51a66e8fda903018206a14eb","score":95.0,"score_display":"95.0","source":{"id":"qwen3-5-27b-card","name":"Qwen3.5-27B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.5-27B"},"source_authority_tier":"B","split_or_window":"qwen-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f5f4005af8cee78d3b3a8a61","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"livecodebench":{"benchmark_release_id":"release_b530ca4da413885c54f52baa","benchmark_version":"v6","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":250,"at":"2026-02-24","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"0848261135ac11f532113ccb5d135ef04f91e250deb1ed16917089f7f9d62430","measurement_key":"7ce0031b213b0f23cf6a6a7c6a50ae47f59b0ff5f8481fca7c9f7cf927620efe","metric":"pass@1","protocol_fingerprint":"95d681e3f443f8d5d265d19ae8a8ce03ce12f86cdcded5df0926c1f3f815adf1","run_fingerprint":"fd7def26cab509f4c29b7e65b1d40d9eafed6a385cda7450ced51f753bbd948a","score":80.7,"score_display":"80.7","source":{"id":"qwen3-5-27b-card","name":"Qwen3.5-27B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.5-27B"},"source_authority_tier":"B","split_or_window":"qwen-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f5f4005af8cee78d3b3a8a61","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"mmlu-pro":{"benchmark_release_id":"release_95dc04609d027072fa229d3b","benchmark_version":"MMLU-Pro · Qwen vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":199,"at":"2026-04-16","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"4b1a0029e4c8a18e268217ed3357c4445e5b77badd12b3419dacf9f5775144bd","measurement_key":"c16b361beb78139346ba5d1319f480c3a80c736ab3beaa372f2908fb5b22d6ca","metric":"accuracy","protocol_fingerprint":"70c7bbff02e177f65267ba3c33be7b6f38096fbaac03c9cc970c7210519303fa","run_fingerprint":"95819c8f70ac3e6071dec87e6d9ced7a537bbe2f8ed5ec3275fddf3faefe5799","score":86.1,"score_display":"86.1","source":{"id":"qwen3-6-35b-a3b-card","name":"Qwen3.6-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},"source_authority_tier":"B","split_or_window":"vendor-card-protocol-undisclosed","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_acca955d8107d22c457bcb69","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"mmmu-pro":{"benchmark_release_id":"release_1dbdadbee92bb7f366d1025b","benchmark_version":"MMMU-Pro official leaderboard","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":187,"at":"2026-04-28","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"f8a0eab458435dd1ccea8a8a95b5116cb156dc04d239b28dd7404d9b45c3ecf4","measurement_key":"295e93b1038b099c8fd0ad1b42ff5e3c04d15e9efa51bc60aad566c6b1279344","metric":"accuracy","protocol_fingerprint":"9225c08e521da63df44b0ad31230f50489ffbee930c8fb4aaf2f0f8dbf6fce3f","run_fingerprint":"fa14cd2bbd4c2bf6348145a31d98fac7273764f4cbbfbfec27f4993ae38d7f68","score":75.0,"score_display":"75.0","source":{"id":"mmmu-pro","name":"MMMU-Pro","url":"https://huggingface.co/api/datasets/MMMU/MMMU_Pro/leaderboard"},"source_authority_tier":"A","split_or_window":"standard","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_acc078689edb6302f6ab810f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"C","evidence_rank":5,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"self-reported","verified_status":"self-reported"},"unit":"percent","verification_status":"self-reported"},"skillsbench":{"benchmark_release_id":"release_5af9fe5a9d5e275323798c8b","benchmark_version":"SkillsBench · Qwen 78-task self-contained subset","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":199,"at":"2026-04-16","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"14efd825387128108cdc67e04c9ca2bf2bb4a9545f39549fef3d6f6ce0c51d6c","measurement_key":"3208f8b30ae95d39467ae3e2e522d8ed14ca96325ca6a4ec5c81c11ca310dffa","metric":"pass_rate","protocol_fingerprint":"1ef4df8bbd26617f6a97c4748bab4ad0b89cb62c839ee783c7a5b25a8ac69428","run_fingerprint":"9fc927ca1b0f86703221415ca3933b9017d9c039297831285860f5a1b4913174","score":27.2,"score_display":"27.2","source":{"id":"qwen3-6-35b-a3b-card","name":"Qwen3.6-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},"source_authority_tier":"B","split_or_window":"self-contained-78-no-api-subset","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_acca955d8107d22c457bcb69","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"swe-bench-verified":{"benchmark_release_id":"release_9162beb27813d52a46a20a9f","benchmark_version":"SWE-bench Verified · Qwen vendor protocol","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":199,"at":"2026-04-16","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"508366e715fd26527334c243cb1c9d1856db291f10619131db2dd0ff3c3ae8b8","measurement_key":"858dc115c60792f0ac388030c16d67e4886574cfd99a22184f040171de44df96","metric":"resolved_rate","protocol_fingerprint":"dad3fccd5f7c7052561a2997a748ad0d5aa39550e8421c973d8656bf054626e7","run_fingerprint":"bc9c93323c34b402a644ae0f3990f4a838e51c6cbf88e2f8be9773f05b0ae477","score":75.0,"score_display":"75.0","source":{"id":"qwen3-6-35b-a3b-card","name":"Qwen3.6-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},"source_authority_tier":"B","split_or_window":"qwen-internal-agent-run","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_acca955d8107d22c457bcb69","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report","views":{"reported_system":{"benchmark_release_id":"release_9162beb27813d52a46a20a9f","benchmark_version":"SWE-bench Verified · Qwen vendor protocol","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":199,"at":"2026-04-16","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"508366e715fd26527334c243cb1c9d1856db291f10619131db2dd0ff3c3ae8b8","measurement_key":"858dc115c60792f0ac388030c16d67e4886574cfd99a22184f040171de44df96","metric":"resolved_rate","protocol_fingerprint":"dad3fccd5f7c7052561a2997a748ad0d5aa39550e8421c973d8656bf054626e7","reporting_origin":"provider","run_fingerprint":"bc9c93323c34b402a644ae0f3990f4a838e51c6cbf88e2f8be9773f05b0ae477","score":75.0,"score_display":"75.0","source":{"id":"qwen3-6-35b-a3b-card","name":"Qwen3.6-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},"source_authority_tier":"B","split_or_window":"qwen-internal-agent-run","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_acca955d8107d22c457bcb69","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"strict":null}},"swe-rebench-v2":{"benchmark_release_id":"release_7449132b5f078c71f23c26b5","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":245,"at":"2026-03-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"5581ce3391010b25d03a445cf11f0cf35ff41327c8188d317f59bb10db49ad59","measurement_key":"989ae818df6809071e2c608ca7a3dd523265b0b68f039bf54292d41da33f37ab","metric":"resolved_rate","protocol_fingerprint":"8fe98e6ef0f26358cd9945f72ca92647ad82c74b572ec206946223c4d5374ded","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-02-15/2026-03-01":{"benchmark_release_id":"release_7449132b5f078c71f23c26b5","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":245,"at":"2026-03-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"5581ce3391010b25d03a445cf11f0cf35ff41327c8188d317f59bb10db49ad59","measurement_key":"989ae818df6809071e2c608ca7a3dd523265b0b68f039bf54292d41da33f37ab","metric":"resolved_rate","protocol_fingerprint":"8fe98e6ef0f26358cd9945f72ca92647ad82c74b572ec206946223c4d5374ded","run_fingerprint":"7382af3cd1986618c6ac7bf6028f899e6656b4886399aad60256fe182f2457a3","score":54.81481481481482,"score_display":"54.81","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-02-15/2026-03-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a806723737ab8f1e6f695e6f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"7382af3cd1986618c6ac7bf6028f899e6656b4886399aad60256fe182f2457a3","score":54.81481481481482,"score_display":"54.81","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-02-15/2026-03-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a806723737ab8f1e6f695e6f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"tau3-banking":{"benchmark_release_id":"release_c6e5abafbb7bffc0975932de","benchmark_version":"TAU3-Bench · Qwen vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":199,"at":"2026-04-16","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"529e6c579b42eab22051cd0fc44e159ee11b9b89abe1b206d8498e589d6bab93","measurement_key":"b16bd4bacf6832db7c7f6513e351712d757ac22236a8d7ddb881819c30ebf28b","metric":"pass_rate","protocol_fingerprint":"ac033ae84d9e8c3792065e58a44a15f3d80b846134d957b52b2b43ded2458ebb","run_fingerprint":"3d45b9e0852085f6c506238cac53c43f1ea267ab7296f6e5abe6b9880db62feb","score":68.4,"score_display":"68.4","source":{"id":"qwen3-6-35b-a3b-card","name":"Qwen3.6-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},"source_authority_tier":"B","split_or_window":"qwen-official-user-model-bm25","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_acca955d8107d22c457bcb69","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"43733dbd9f95bfcc9da0c80d4ec45c08625326e07a3e5f2558c4bb96b6ce00f3","measurement_key":"fff3f31b72494a4aa2257537cf533db364243b12c5996db2522bfe36b15248d4","metric":"mean_final_balance_usd","protocol_fingerprint":"6c1f16e150ac8721678431423fc4af65a8198ef9c08fa3300f1696b29819e7c9","run_fingerprint":"a7306297d7550483ac8814a7406b5aa33c660dcdf32fda27868b7ef44c88f84d","score":201.97599999999994,"score_display":"201.98","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7f48d5054d4b2dc26d1818ca","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8315f6b4046cac03bc78891fa386f35062b54c70576da6809c0d9c066fc6f466","measurement_key":"7e5caf5db29ab2b53b385b32d7d1a7fb9f90c2988a3c77ac6a5989323eaf1e4e","metric":"arena_score","protocol_fingerprint":"e93b6280a139cab1759cd7e13e0e3e6a8c8d02ac2163ff73134941530c431cb7","run_fingerprint":"9edd6a9ad44cd23672ce2b18057adbd391c2df741413a80c54ec09ca55d8969f","score":1358.3092755979856,"score_display":"1358","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d8f6ad970b239a16860c4cb8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"83c4ac11c658be15f3d1fdf91bdaeb07479aaef2321cd23130b7928a68e4818f","measurement_key":"840b7ed0128d0d3e084968cc041accbfaad792a2f4f415ff300de1ab14e571fc","metric":"accuracy","protocol_fingerprint":"d3567b16c7cd49d2fa47f9c8fb940d89aebd07f44bfc96ba13c8315e6ba5b8b9","run_fingerprint":"fbc6dcdd8931bf48b2591c9dd6e4050bc0a72e182714eb347792c8e00b4d9110","score":39.53,"score_display":"39.5","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9393d6a5cff56c2e2f1c57a5","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":true,"model_id":"alibaba/qwen3-5-27b","model_name":"Qwen 3.5 27B","parameter_count_active":null,"parameter_count_total":27000000000,"provider":"Alibaba","selection_rank":80,"weights_status":"open"},{"cells":{"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"97be34cedbc840d4e721ea03b4c3837e247030a5dd1ec87723f5ba8d9141fbda","measurement_key":"a21e87e3083792db0dd2b0fa144b45281a55754e9460ede4bb0a23820fbd61b4","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"8c07d4ff5ee3d4cecb88cc26914c3d327c85a45a7a38a11c250163f712c484b1","score":1393.8308645238358,"score_display":"1394","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7bb891886f6b9f82e595d537","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"bfcl-v4":{"benchmark_release_id":"release_6b9456463dae72f95fadf6b3","benchmark_version":"BFCL V4 · Qwen vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":250,"at":"2026-02-24","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"ea0af1f6215972d71f3a4b2fd3d790adf4829ea0426ba4cf7d4ce7ee2354ec7c","measurement_key":"d7e111b6a0584c9df4e620599396508b736cc9e4b011c9001f4d6086129a86a2","metric":"overall_accuracy","protocol_fingerprint":"d2e5e4ded552b5be2636ae22be91934e3af5094a2c843dba75092617f97b0e8a","run_fingerprint":"ec02988d19fe94097e752e7d934900ce8829321a4996eb59f285dad0733ce83f","score":67.3,"score_display":"67.3","source":{"id":"qwen3-5-35b-a3b-card","name":"Qwen3.5-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B"},"source_authority_tier":"B","split_or_window":"vendor-card-protocol-undisclosed","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_acf8ff0a882897edb172285e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T21:27:01Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7aa70417927a98bd80a0ac504310bc4ff8008a50add71fcb85a5d3b1b6dad1c2","measurement_key":"b2cae5bdb661562610dc4bbd3c23be563fd5ce54fae53a57fb46aaa9d4f75179","metric":"accuracy","protocol_fingerprint":"5883adcd5901ca67361c21b62e568dafd4443eeaad296150e4b6a0027d4276ec","run_fingerprint":"998a7c4772fcf54ea828c67b94d351b21b1a004bb297fe5eec6686deba04512c","score":0.571428571428571,"score_display":"0.6","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_08198280c56f559e82197c5d","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0ecdf3db010f0702b6632f714c583396b9d2abfdfb71707f6c869543a775cac9","measurement_key":"e9a6e45bc5681d0201254f27cb729f21074465c97ff50ee915a821bd5f5b33a6","metric":"eci","protocol_fingerprint":"4f72bc1c1d8ee33cce785057e32ed8d163986dc9da68ff5581c177263ca5529b","run_fingerprint":"617f70f83f2eb2bf7ac3ccff4faf423b2ff6daf5a36333901a040c0e2dddf7a9","score":142.56,"score_display":"142.56","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8038866fb4362de4cdb57daf","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"189b23e6bfebe05642e7a75c051fcf70302dc873da828d09ee3433a7456545ad","measurement_key":"fa17bf4c1452f32292ce5760aa8f373855b93140859a8a515c87156912edcd82","metric":"elo","protocol_fingerprint":"db1e4b69951d9dde73f5e0e2f494836b4fbffdf4e55c6f8f59d9682fa30e8c01","run_fingerprint":"696ef00a210db809c193e622bb7dbb47f53ced41650c048ee913a29cb261256b","score":616.33,"score_display":"616","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_08198280c56f559e82197c5d","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_f83cfc2a9e19b8d654d7b58e","benchmark_version":"GPQA Diamond (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-09-17T14:33:50Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dbafdb064e7045945196950dd7f0717df937de1fcdbd99b435e74ecd4e4e7709","measurement_key":"0da010e6404eb1ad3afba0de8e179943ac8199bbeb39913086de8fabdb4771eb","metric":"accuracy","protocol_fingerprint":"b73e5cd99b7c054fc9be875f4120b9f11e2bae8cc6e3ec141337a49314ca1bfd","run_fingerprint":"ab8c732c2cb942be11260bf0c77f94cdbb39b3ca9ead81c3688a43075fdee3c8","score":81.919192,"score_display":"81.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"diamond-198-zero-shot-5-repeats","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_08198280c56f559e82197c5d","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_2f3c6e21d0f3616fdb78f627","benchmark_version":"HLE · Qwen vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":250,"at":"2026-02-24","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"171536dbc27ea4f24a2de988e75a17ccf2194b216ef1ecf4d6a9b649af6e1373","measurement_key":"7bda6d7dd09284b49794e6419d6c28c6ab5242125b994b94fd211a4e74d28ccc","metric":"accuracy","protocol_fingerprint":"b49926e35945bdfc4bf990d42caf170ca771797b88a16f10251ffb64499db7de","run_fingerprint":"cc316e55ab5d1340ddbd43bdbaeaf712dc551414a11ee5b85c4af871634ee7d6","score":22.4,"score_display":"22.4","source":{"id":"qwen3-5-35b-a3b-card","name":"Qwen3.5-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B"},"source_authority_tier":"B","split_or_window":"full-multimodal-cot-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_acf8ff0a882897edb172285e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-17T14:33:50Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9f1345a2502865bff6dd80288260a6328318ffb94b336beee66f60a228473270","measurement_key":"21aea8e9e99188e3b2ca78fab0478c465c09302cd4d89e83afb7f4d3abbc0aff","metric":"accuracy","protocol_fingerprint":"c82f11f93ed09ee059ff29283f4a431b1a4d7e73b955c89638baeca630283a3f","run_fingerprint":"3ca6d672d608f8242ce99f58ef7c4e7c28db27d74857a7e2d2839b51e39d6909","score":13.438369,"score_display":"13.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_08198280c56f559e82197c5d","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ifbench":{"benchmark_release_id":"release_4adf348ac2f76539ed7ccb10","benchmark_version":"swallow-evaluation-instruct","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-09-30T18:53:19Z","last_confirmed_at":"2026-11-01T03:42:24Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"eca7d6e060781481802685d019969481f5e9a6ded322c4f48bd9c379a2cb490a","measurement_key":"ed84d0dcd7c2db508377a2e00546148a28362997cf7660b94158c461485a2ffb","metric":"inst_level_strict_acc","protocol_fingerprint":"637455e9814ebdb49cbf54e163208050c724c6ab8f9e5de8f6d8bcd522d407e0","run_fingerprint":"877ddbf051b5bcab60fa8f7770661a20dea8bfc844c555f5c0071e33cf73b5e2","score":59.9,"score_display":"59.9","source":{"id":"swallow-llm-leaderboard","name":"Swallow LLM Leaderboard","url":"https://raw.githubusercontent.com/swallow-llm/leaderboard/c58a13a852eba061d639af7caf4ddbdff33b36e3/swallow_leaderboard_post_en.js"},"source_authority_tier":"B","split_or_window":"ifbench-test-300-prompts-344-instructions","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_f3e955ec7b7b358b2d54c536","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"ifeval":{"benchmark_release_id":"release_eaa2f0262bb0264860cb2c8e","benchmark_version":"IFEval","comparison_lane":"source-specific","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":250,"at":"2026-02-24","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"9acd3fb07b5b7882ec632c448c9b55d601504cc1242ba9ea16104334b021827f","measurement_key":"3813d7429befc6198abcae6d0d043775a144078d3131d96a4002f1a9239469dc","metric":"accuracy","protocol_fingerprint":"75c65dff8a4ca072f7779ee663a82f005dc599d80742e995c92e9efe54e12762","run_fingerprint":"f93a5f4172e3a754eb1c169b80f3846b83e4860f8578764e449d162e948239ef","score":91.9,"score_display":"91.9","source":{"id":"qwen3-5-35b-a3b-card","name":"Qwen3.5-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B"},"source_authority_tier":"B","split_or_window":"qwen-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_acf8ff0a882897edb172285e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"livecodebench":{"benchmark_release_id":"release_b530ca4da413885c54f52baa","benchmark_version":"v6","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":250,"at":"2026-02-24","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"58cf9274dd79179aadedb6d26afe7a4de1155417f03ad69f5b7a8715badf18d0","measurement_key":"78e1abaa4a87b37fb6d8a8e455cd31a9463f17cc9cc4a5f2b0233eaeb39fad4c","metric":"pass@1","protocol_fingerprint":"db4e6883454c44a81391e2be412d53f1f000436285ebff88bf47b93dfaaf4dae","run_fingerprint":"cc1229feb272d3d3078a3cf81e8c6c7dcfe54db5f95098084c9c40be82424d2d","score":74.6,"score_display":"74.6","source":{"id":"qwen3-5-35b-a3b-card","name":"Qwen3.5-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B"},"source_authority_tier":"B","split_or_window":"qwen-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_acf8ff0a882897edb172285e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"mmlu-pro":{"benchmark_release_id":"release_95dc04609d027072fa229d3b","benchmark_version":"MMLU-Pro · Qwen vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":199,"at":"2026-04-16","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"b4c0ba1cdf51a27be1e0b529016fcd72f3682b596b5c039e60a3167eb288b08f","measurement_key":"babe396e30ea29c69466fb57bc695f910bb3fc73af3f2af20f74c5ad7bd0bb67","metric":"accuracy","protocol_fingerprint":"70c7bbff02e177f65267ba3c33be7b6f38096fbaac03c9cc970c7210519303fa","run_fingerprint":"0f5d4241e89874f8a37a8a560aebce700d8b24e146f66a4887a677bea0b699ef","score":85.3,"score_display":"85.3","source":{"id":"qwen3-6-35b-a3b-card","name":"Qwen3.6-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},"source_authority_tier":"B","split_or_window":"vendor-card-protocol-undisclosed","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a489b097f55632aa33d8a051","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-09-17T14:33:50Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f51eef7e551e68644a7e09265baeb6f1d78e202eaa1eee6cd7bcdee1763ad09d","measurement_key":"64544f0a2679fd03f0617528554f1098eba01ed9944aa3862f2e11dfa05c0064","metric":"accuracy","protocol_fingerprint":"f5aae5ac6ff3c3614cd499cc0dc6857e5b4b834398f1722f1b9ecd67fa0f1ef0","run_fingerprint":"55170197b63105bc97e67f4d77dc0a3f977f968eeb7a3b247fd2ea181ca9beeb","score":69.190751,"score_display":"69.2","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_08198280c56f559e82197c5d","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T22:45:56.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c0c5d7d90220ff77ed08b70921760931eeb63ca407a9494f4dc86949cb5034ab","measurement_key":"f6e3823a11e27e25b4dc98bd0d09c0c7570b06d20058e6bea07636ef5b8e264e","metric":"mean_score","protocol_fingerprint":"91930fa35f725ad3c356dbd7a26c502c4a1cd60c9d733a134b49eb2cf966042e","run_fingerprint":"cf2353eb0490029b74386fc2b701efde22553dfdf975fb75a5d2dd5d68922310","score":70.0,"score_display":"70.0","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_08198280c56f559e82197c5d","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T21:26:51Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b6959f75892eb9c90c9a42614a2d015bc5f107edfb4b849d3e9572f522db3e97","measurement_key":"78d054abbb3a5aae7044688792fbd5cbfb9c1eec2689657b85e7bb600134d90e","metric":"subproblem_accuracy","protocol_fingerprint":"1a198886d4fc358ff800abfc9a5c92e2bc8dee83167d73c119f59429dd9b55bf","run_fingerprint":"30d06fff619f7110d2e123ee855ff152d741937bba31d080f7c2e0a8d87c6532","score":29.2824074074074,"score_display":"29.3","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_08198280c56f559e82197c5d","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"skillsbench":{"benchmark_release_id":"release_5af9fe5a9d5e275323798c8b","benchmark_version":"SkillsBench · Qwen 78-task self-contained subset","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":199,"at":"2026-04-16","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"8d3661f56a87d13740247d4a672dd945c65110093cf50964ec5fd737a16e6507","measurement_key":"c000580d7042741c8ee25512fceb573da0dbd3ab3d3fbc9aa0c422c5106fe815","metric":"pass_rate","protocol_fingerprint":"1ef4df8bbd26617f6a97c4748bab4ad0b89cb62c839ee783c7a5b25a8ac69428","run_fingerprint":"320dbfb4604193a6eaeef0ad21a11f9eecc81e9dc1b7e148e0f22154b166cfc8","score":4.4,"score_display":"4.4","source":{"id":"qwen3-6-35b-a3b-card","name":"Qwen3.6-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},"source_authority_tier":"B","split_or_window":"self-contained-78-no-api-subset","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a489b097f55632aa33d8a051","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"swe-bench-verified":{"benchmark_release_id":"release_9162beb27813d52a46a20a9f","benchmark_version":"SWE-bench Verified · Qwen vendor protocol","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":199,"at":"2026-04-16","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"31a81390ecd810045cdffee48ed7e139c4c8244a463f2acba0952d929c8f2fb8","measurement_key":"f452df0106ddd494795cbf76ac6d2af0f0d8222b9eedb8574a6108b1bef4dcb8","metric":"resolved_rate","protocol_fingerprint":"dad3fccd5f7c7052561a2997a748ad0d5aa39550e8421c973d8656bf054626e7","run_fingerprint":"b91ad4b09950831548895f062638ccf94225cc8fcb4af4646b49154793c68906","score":70.0,"score_display":"70.0","source":{"id":"qwen3-6-35b-a3b-card","name":"Qwen3.6-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},"source_authority_tier":"B","split_or_window":"qwen-internal-agent-run","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a489b097f55632aa33d8a051","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report","views":{"reported_system":{"benchmark_release_id":"release_9162beb27813d52a46a20a9f","benchmark_version":"SWE-bench Verified · Qwen vendor protocol","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":199,"at":"2026-04-16","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"31a81390ecd810045cdffee48ed7e139c4c8244a463f2acba0952d929c8f2fb8","measurement_key":"f452df0106ddd494795cbf76ac6d2af0f0d8222b9eedb8574a6108b1bef4dcb8","metric":"resolved_rate","protocol_fingerprint":"dad3fccd5f7c7052561a2997a748ad0d5aa39550e8421c973d8656bf054626e7","reporting_origin":"provider","run_fingerprint":"b91ad4b09950831548895f062638ccf94225cc8fcb4af4646b49154793c68906","score":70.0,"score_display":"70.0","source":{"id":"qwen3-6-35b-a3b-card","name":"Qwen3.6-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},"source_authority_tier":"B","split_or_window":"qwen-internal-agent-run","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a489b097f55632aa33d8a051","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"strict":null}},"swe-rebench-v2":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a00999461d5a15b2c4520d00b039f525824db79177232cf2feab5f7fc9d7b05c","measurement_key":"da3911eab060f5fd77f8b9bf1de2271447cd67bee7259041a0b78a9317d9c175","metric":"resolved_rate","protocol_fingerprint":"6e5a0da2f64d15a75563cdfb237ee200ce210a778081a94c786af397623a1536","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-05-15/2026-07-01":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a00999461d5a15b2c4520d00b039f525824db79177232cf2feab5f7fc9d7b05c","measurement_key":"da3911eab060f5fd77f8b9bf1de2271447cd67bee7259041a0b78a9317d9c175","metric":"resolved_rate","protocol_fingerprint":"6e5a0da2f64d15a75563cdfb237ee200ce210a778081a94c786af397623a1536","run_fingerprint":"d222bdb3496ac12279d1b3ab91a8ffa1a6b2ed382df032656260aa96da7694cb","score":17.117117117117115,"score_display":"17.12","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_be91adc28b2c36400b8ba1d2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"d222bdb3496ac12279d1b3ab91a8ffa1a6b2ed382df032656260aa96da7694cb","score":17.117117117117115,"score_display":"17.12","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_be91adc28b2c36400b8ba1d2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"tau3-banking":{"benchmark_release_id":"release_c6e5abafbb7bffc0975932de","benchmark_version":"TAU3-Bench · Qwen vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":199,"at":"2026-04-16","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"a67f709ca26801d56ab6e79690408d0807c344540de4f486e3ee4ca2d155f896","measurement_key":"fa6af4eb40516a71e49e8f064601da97589eb26cef5d065b39288db0aff99361","metric":"pass_rate","protocol_fingerprint":"ac033ae84d9e8c3792065e58a44a15f3d80b846134d957b52b2b43ded2458ebb","run_fingerprint":"ae5081bd124fd991bdcb417a116f31652e02bb443d052ed2c1a9267a1559fa4a","score":68.9,"score_display":"68.9","source":{"id":"qwen3-6-35b-a3b-card","name":"Qwen3.6-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},"source_authority_tier":"B","split_or_window":"qwen-official-user-model-bm25","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a489b097f55632aa33d8a051","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-09-17T14:33:50Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cbed354149d05525d2a63b62a921e1ca8df059e6538472bd47b483d71a4a75e8","measurement_key":"1f9ec9c4ae2dd408987946d3a0e3d2b1792ebdf142f9d42f96a0966880e9f3e5","metric":"pass_at_1","protocol_fingerprint":"86784d5fdedb2bd1b029547fa4a787eeca76d6b99e30a3c187610a4b91db16e2","run_fingerprint":"ee503dfe9dc12847528d3e6c09025b18de8b273bc5aa31d6b72eff9373ef3a47","score":4.948454,"score_display":"4.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_08198280c56f559e82197c5d","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_c53c830678318dc1763793c8","benchmark_version":"Terminal-Bench 2.1 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2d4cd2d145692b94d37f064e33bcc90c0bc22705f9326d7c22ad7987935e1527","measurement_key":"c01fc0e2046ce8e4937b550966bbf69fa3d2d88a3b62bedf6eafc880e0dacaea","metric":"pass_at_1","protocol_fingerprint":"f2b361ff5b17541ab507cb160241fcafa9a6674485d1d00f853a48c327a53570","run_fingerprint":"e44eac0e9b0094abcec8e3cf11840e92cd0c5297f012db7c5b1e65179e7a2b6e","score":40.82397,"score_display":"40.8","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"terminus-2-89-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_08198280c56f559e82197c5d","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f779127ce143ee784c219be10be47fee20fe16613c27f22ad7c17e24bad34646","measurement_key":"0d254c489ecd62b32c90eb95c49f5a994930dc6aa0bbf92a50a514f4cfa0d70d","metric":"arena_score","protocol_fingerprint":"54eb3afb7281c0b80a19a2e50b6b9c81cae95f8e45834f75c1d2452ecd57614d","run_fingerprint":"b801c18bd8ed26e4d2b24955fb052d9e3b13e050e3a94310928ddac7db10e2a9","score":1254.1583882182388,"score_display":"1254","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_629f0be1378c8068b93135c5","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":true,"model_id":"alibaba/qwen3-5-35b-a3b","model_name":"Qwen 3.5 35B-A3B","parameter_count_active":3000000000,"parameter_count_total":35000000000,"provider":"Alibaba","selection_rank":81,"weights_status":"open"},{"cells":{"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T21:27:01Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"92a5b32e1ff83400fd1eba46c40ba069d591ad8cae12df6f109d0f2cd5bb1e40","measurement_key":"5bac5d26a6fb9701929653b181ecfcfff04b3c39ef4c26d30005083fc3576f79","metric":"accuracy","protocol_fingerprint":"bf4fee08f497620015d5779ccb4ad100f29c89690690d44b245ef61d62d3761e","run_fingerprint":"f7a15a8eb55df5306896d54a3f4a5f2d62b87d11164ddc1d94382c8cbcddfb0d","score":0.857142857142857,"score_display":"0.9","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_2cd29242487b8e61b4d8196f","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"deepswe":{"benchmark_release_id":"release_7334bb741d8de260846d3128","benchmark_version":"DeepSWE 1.1 · Qwen3.8 comparison run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":79,"at":"2026-08-14","last_confirmed_at":"2026-11-01T03:42:36Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"225f38242c6a8b98e93a3fd3eb006df87e5ee5cc491d361e8f189cf6e9171338","measurement_key":"f77c93933bea353dd8974341c3104ca5b7517df95b69879f6efdd4c47aee3108","metric":"resolved_rate","protocol_fingerprint":"a6e881fb08d7f02373b7ec6ca1562ac9c2dd115460a20ee27445ba6f54a80701","run_fingerprint":"5f2dbcd294170afb51f55ec88b0f7fadbc44535eb001ded628a4aa487fba635e","score":13.3,"score_display":"13.3","source":{"id":"qwen3-8-27b-card","name":"Qwen3.8-27B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.8-27B"},"source_authority_tier":"B","split_or_window":"qwen-vendor-comparison","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a26de80da0b74a12cbb6375e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"00e32546880e5acab9bb96e4ae2d690934ca158f25be76e8c35d776e38694400","measurement_key":"7c4dc18fd7cb6cb72eaf8604ad21a95bb3a0aa0ca7db6f6b05165290508fc37f","metric":"eci","protocol_fingerprint":"89be2d7e36c5e8e6ab174330a30c774555aafc6665973c1313c1f881b56528a0","run_fingerprint":"54812b79088fcf644bf944a35b9115be036a72e2e8b4df9427b77c1c95c5fbdd","score":146.32,"score_display":"146.32","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d79e65ecde0b2da0fa5b6c49","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":63,"at":"2026-08-29T11:06:28.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"36230e414a754c764a8f6a0d4917bc164a10e4f9ba2087d1216cff2d78ef0fbf","measurement_key":"4ba58678303793d85f0d711b0189e47f773be842d1691eac080411b867c5a84b","metric":"mean_score","protocol_fingerprint":"1bed8ed4070c75c3320000f0d35a74716111e019ba019ae7fde7b7195d434cab","run_fingerprint":"9a67054ea999024b818440d89bc7ce4169b8cc900f4bbf7be2c3c07f0773ccd1","score":34.03508771929825,"score_display":"34.0","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_2cd29242487b8e61b4d8196f","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a776ebcac947dde1a75991f538dd26602bf6ca8a79ae0115321d8dac6442770d","measurement_key":"8fb48ffa576c5509173e92129eaa5b3228032d4f9ebe25217caba36199dea59d","metric":"elo","protocol_fingerprint":"e3838f4a1e988f8f02ed6b6bfb9a1c6501bc2659ffab211ee4f3db2c168ef387","run_fingerprint":"0848e8979c386e51d4d5df0a4d9e447830def42eb0af805d33d6c0963d722bb2","score":992.98,"score_display":"993","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_532636b8035b61ccdae69abd","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_f83cfc2a9e19b8d654d7b58e","benchmark_version":"GPQA Diamond (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4abfe1b01429fec5cbe128c5e24f551452f84391f67ba297f3d40f2214add6d0","measurement_key":"84f8d13ab7db7dc3331218a1880104d7217aaebbd233f64faf1c8f5c5182fba9","metric":"accuracy","protocol_fingerprint":"fa2fbf8361f9daea6f1967f15ede01589b5889326a0d9e09a2f1c0752c0cbb64","run_fingerprint":"ec7728c28a745fb0284a471a4587a672bf81cf3c868472d90cdffc7a1fa66c72","score":84.242424,"score_display":"84.2","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"diamond-198-zero-shot-5-repeats","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_532636b8035b61ccdae69abd","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_fa9e908ac04b067eb00182d4","benchmark_version":"HLE official leaderboard","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":63,"at":"2026-08-29T23:52:43Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e78c69da452c465f374145256b5a44a8a2ac79246ec16e38814488e61b1fd28b","measurement_key":"ea7f654ac8543c6813b5d9b30b168b69a6b1295516cbb67eff89e351038d0daf","metric":"accuracy","protocol_fingerprint":"e1f956386a97e6ba42a3c396757902d19f19cdabb10fcc91e345af5c771a2890","run_fingerprint":"7877427bc2c85e0515619a1da87c6a63d1c1a3e24926bb1b2d6c48e7c0de4c70","score":24.0,"score_display":"24","source":{"id":"hle","name":"Humanity's Last Exam","url":"https://huggingface.co/api/datasets/cais/hle/leaderboard?limit=200"},"source_authority_tier":"A","split_or_window":"published-leaderboard","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3570f866437a50d449060a12","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"C","evidence_rank":5,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"self-reported","verified_status":"self-reported"},"unit":"percent","verification_status":"self-reported"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"38a6125304d827f8e64faff7c7c4e151bd16819c1891fbf8b82db64e74caa1a1","measurement_key":"f0a289aff31d96564d86463433d46e13ed4bf75edde4e55e3133925187252044","metric":"accuracy","protocol_fingerprint":"cf0c5313fdfacffc253255ba0019c8f3863debca16c6843efd7ca675067ba9c0","run_fingerprint":"47f9dc12d4fcd60444216b4d8052beb99e53fd429a26ed7dad35d82f4131ee65","score":23.076923,"score_display":"23.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_532636b8035b61ccdae69abd","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b0f2da3a93f7a311cb26f2fed44911ae93ec54dbfa12a9653ba9171ea8debaf9","measurement_key":"2e18ed28a8a6dc0e10b0d379c6d590c2c06c4ab45fa51715d2cd7d705d2b5c42","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"8757d60738d6dece6d2a7676301a88ab2e70a2dd3338207c8573daa2c0305f07","score":64.02713095238094,"score_display":"64.03","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9e9091d6396e29d6d8b835ff","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_b530ca4da413885c54f52baa","benchmark_version":"v6","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":193,"at":"2026-04-22","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"64c948e386bdb00ddb89d83bd46ac3dc25dd49bc6006afc7d0be38ddaa778605","measurement_key":"7e8d48075737951b157639721169a5d674dff6552056888a1d31258663cb89e6","metric":"pass@1","protocol_fingerprint":"76fab4a2249a73a0e1e012d538500edf88277ec3f4702daebc6bbf5614eec7c3","run_fingerprint":"c76090d044bead513df1b4f32d08f0b5ad027768854fa30d3d5a649e6ff6f80a","score":83.9,"score_display":"83.9","source":{"id":"qwen3-6-27b-card","name":"Qwen3.6-27B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-27B"},"source_authority_tier":"B","split_or_window":"qwen-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_609752b0f7bd8a6341aa27a9","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"mmlu-pro":{"benchmark_release_id":"release_95dc04609d027072fa229d3b","benchmark_version":"MMLU-Pro · Qwen vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":193,"at":"2026-04-22","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"0a3a26d152b241aa7292684e9295d46dc64da81b6368356d472be114ac9db40f","measurement_key":"6cb6ced408fc8f38903180cfa195e9af9243b15d0ceb5cf48f80b5591fc2eddd","metric":"accuracy","protocol_fingerprint":"44f56864a490bb7582461036c068400061930b80aee3b634127a43235a3bd532","run_fingerprint":"b91072c0a84c1a6fcf0c4add3474cce51465210c5cfc7de6f30fd732769ddd19","score":86.2,"score_display":"86.2","source":{"id":"qwen3-6-27b-card","name":"Qwen3.6-27B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-27B"},"source_authority_tier":"B","split_or_window":"vendor-card-protocol-undisclosed","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_609752b0f7bd8a6341aa27a9","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"83dea270b16c6c63c1b9f9459e0c9776ad67ba237bae6a58e6204b358214104e","measurement_key":"9228a0f019684cd451d3ffa8f4daaea39c995a28186fc008d5da32d0b36a4163","metric":"accuracy","protocol_fingerprint":"bcba8686eb1b301d47af1b852f210dbdb831a09d7f5f203fdcf6544309c6a39c","run_fingerprint":"f4ee2b33934f53bf5ca91cbc01956e5552390420924e43f0db084c0aa7b94b9c","score":74.624277,"score_display":"74.6","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_532636b8035b61ccdae69abd","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-07T00:12:36.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0718f636a083cc5bd5e319af629e5de137ced38e9543b8639adc560ab9450266","measurement_key":"835394c916cdc323197aedf683a3aebd54b73bae47d794337c7a66e4e91d8813","metric":"mean_score","protocol_fingerprint":"62c42b96674f98c0a3d367bb21907b85a8fd1fa83ec55da20c0692d255928e09","run_fingerprint":"0b967dd3e37d345780f9504fe6c7d8a5417b6965ec67077959f32dc4ccb6e5d7","score":91.11111111111111,"score_display":"91.1","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_de27cbb86e9c990231514038","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T21:26:51Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0df13a604e53a8430d370de70d7cfa8cdc7024fb5f99e669b5272a26962d5d9f","measurement_key":"55ee8d661e41c2b420330460aa4dd24fd1490f4aab40ed2ae92d13f64e20bed1","metric":"subproblem_accuracy","protocol_fingerprint":"8f32a451a8057bab01b362b93fb8208377ff04c6702857bd22fd3c2677f8247c","run_fingerprint":"9c35b67d7aad2943bf5923f74ec0dd7ec0731b3daa073f64d54daf2e87a9abe6","score":37.2685185185185,"score_display":"37.3","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_2cd29242487b8e61b4d8196f","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"skillsbench":{"benchmark_release_id":"release_5af9fe5a9d5e275323798c8b","benchmark_version":"SkillsBench · Qwen 78-task self-contained subset","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":193,"at":"2026-04-22","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"596c96a04adbcb7e836644982f0cf40987a22d7b317f5814b1a7c369d1847786","measurement_key":"273361bd9fa04ba4cfc3675d18697c43bd959388bf121a2a7ec0b9842454bb29","metric":"pass_rate","protocol_fingerprint":"0075a32b62b602932d1572b58a2560fe97ac92d58166e3cd33e67ab077a6bac5","run_fingerprint":"9aded900bc59f172374df6f9adce1e88e1babc87c4cd2e4cce3ca83eec8a1290","score":48.2,"score_display":"48.2","source":{"id":"qwen3-6-27b-card","name":"Qwen3.6-27B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-27B"},"source_authority_tier":"B","split_or_window":"self-contained-78-no-api-subset","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_609752b0f7bd8a6341aa27a9","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"412c088b236701cd25bd8bc7207cf2a2e23c1c8e4cb7bb853765852ab755ed8f","measurement_key":"8a582c55cc0bcbdcfd7e108ddd2a5d4976258746033491820e79fb1c48c8fbbf","metric":"resolved_rate","protocol_fingerprint":"26fefc2a52f913207707506ebc6c03be814a8c79092be52a1fc37512b171e006","run_fingerprint":"8503e17266e1a189664e45a9176b59aa1f6a69c48be8ae8bdcd540e940ba53f8","score":70.0,"score_display":"70.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7c98370c510777de07e3c586","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":{"benchmark_release_id":"release_9162beb27813d52a46a20a9f","benchmark_version":"SWE-bench Verified · Qwen vendor protocol","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":193,"at":"2026-04-22","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"d32711b53e463e7f56a1304da6f4b70b5a8c2c530683867deec03e33f105085d","measurement_key":"9731f85d08113609b20504539db3de2da315e45fb7dc7c7f356ec2910c78df9b","metric":"resolved_rate","protocol_fingerprint":"76ed278b99ffd1e5f9230954bc4ee5268b74c5c42a740c706366f11a530ecbf6","reporting_origin":"provider","run_fingerprint":"7422f92cc687dd578dfb640a8b7a351fd402360ca813d5e49b98b53d25657372","score":77.2,"score_display":"77.2","source":{"id":"qwen3-6-27b-card","name":"Qwen3.6-27B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-27B"},"source_authority_tier":"B","split_or_window":"qwen-internal-agent-run","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_609752b0f7bd8a6341aa27a9","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"412c088b236701cd25bd8bc7207cf2a2e23c1c8e4cb7bb853765852ab755ed8f","measurement_key":"8a582c55cc0bcbdcfd7e108ddd2a5d4976258746033491820e79fb1c48c8fbbf","metric":"resolved_rate","protocol_fingerprint":"26fefc2a52f913207707506ebc6c03be814a8c79092be52a1fc37512b171e006","reporting_origin":"organizer","run_fingerprint":"8503e17266e1a189664e45a9176b59aa1f6a69c48be8ae8bdcd540e940ba53f8","score":70.0,"score_display":"70.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7c98370c510777de07e3c586","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9128225220206b5af7f3d323af5efc1bc84da52fac6411591d0294df0598b8a7","measurement_key":"b1e2bf8febc31dd5b52efd7c89c0bf0f51affe284d7a12bf3f15d0af0d7443f1","metric":"resolved_rate","protocol_fingerprint":"bb1f0b8a3d0323016acc700587394c23b4e81d4ee438cfee2e8c57d43f6756c2","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-05-15/2026-07-01":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9128225220206b5af7f3d323af5efc1bc84da52fac6411591d0294df0598b8a7","measurement_key":"b1e2bf8febc31dd5b52efd7c89c0bf0f51affe284d7a12bf3f15d0af0d7443f1","metric":"resolved_rate","protocol_fingerprint":"bb1f0b8a3d0323016acc700587394c23b4e81d4ee438cfee2e8c57d43f6756c2","run_fingerprint":"a8ee5648c3d3e79f9d95cb5c90f39cbe20fa61ab8fa3ff19a3095c5652a3b62c","score":31.171171171171174,"score_display":"31.17","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_884552ea54f553fb70208863","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"a8ee5648c3d3e79f9d95cb5c90f39cbe20fa61ab8fa3ff19a3095c5652a3b62c","score":31.171171171171174,"score_display":"31.17","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_884552ea54f553fb70208863","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9a102e90821d90cf7a345e2c1cfb1fbd73af1a58b003415311de37275fe2cc28","measurement_key":"64cfb67003f3a3b5c90af479daac19afbcb8fa273fc9660bfd454154928e7d5d","metric":"pass_at_1","protocol_fingerprint":"498e8600e17e069a73abb7d078bcd64e4ff805ba73614f86234dd512307956bf","run_fingerprint":"b843dd6ef33f576977d995a9983c8c40a6470c4c3afaac0a90f6a3358ccefcfc","score":16.701031,"score_display":"16.7","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_532636b8035b61ccdae69abd","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_c53c830678318dc1763793c8","benchmark_version":"Terminal-Bench 2.1 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-09-15T17:15:32Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bfee6751585c5fc3cbe4a58fdf5cd9bed18afe2c12fa812b14594a0da2660e7c","measurement_key":"c1ea55fb52f20153effaf854382d33b37923558d3ed0459e8abcccd1d077fb39","metric":"pass_at_1","protocol_fingerprint":"662a44299f94415dfc1e341230d74ca6dcabbd11203965171268395946a14942","run_fingerprint":"945a0cdd4f86b0ec7e88d0bec3eba2736717861def6b10f9ead39f1f3239d776","score":60.674157,"score_display":"60.7","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"terminus-2-89-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_532636b8035b61ccdae69abd","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"36ff10ff8243e1102322dc2aa8602f245657fe7c12330d9923cf4ab99b52dcd7","measurement_key":"5d49e5fff956a9cffec791e36d6da2de9b441cd9a27dc9d367a403aac5750a48","metric":"score","protocol_fingerprint":"51c6603f5bb1fd0d8c9f1b3ab0d5024e4bbc0896e59cba3c2e578cdd46b57b3f","run_fingerprint":"95fe34c3bc435946ec4317a0449386f59448f16cd7192a7ed7b589edbbf71304","score":11.941,"score_display":"11.9","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0292f7dcc0ed61ad2140555d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}},"local_open_weight_essential":true,"model_id":"alibaba/qwen3-6-27b","model_name":"Qwen 3.6 27B","parameter_count_active":null,"parameter_count_total":27000000000,"provider":"Alibaba","selection_rank":82,"weights_status":"open"},{"cells":{"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T21:27:01Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dec612a45aed84b6577e8b7d5afb09899942d9351876d41b2ce4f6242d4c53a0","measurement_key":"d5fc1d41e17898898e9a5dbddc2de6fde3cabf84a0748e1d630c68e68a05edcf","metric":"accuracy","protocol_fingerprint":"6de27bf2f34049fa14234cab6a3d74f4017d0be8a98cfeb452d9261292b3e7b9","run_fingerprint":"d99a4738298837abbcc20ae816e0793a5ca04ecdc7aece66701406bc9bd6fba2","score":0.0,"score_display":"0.0","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_c69dc5716abeec6f1e0c8be8","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"57ffc7cf21895957a6ffbfbd145ec7461b8a2124a2184891969a6aea67c1a8d9","measurement_key":"d2b0b5e93171e9c198279e8c16b4cb5207baa26b6cb6efa905001c99d5b7b198","metric":"eci","protocol_fingerprint":"a89792d48b5dc942994340ac6ae5a601300922e7517257a79de090e954aea31b","run_fingerprint":"cb71423795d99ec4ec05af3ba68739df77856167daf90fe9c4032f6f806512ed","score":143.81,"score_display":"143.81","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ec15963478c8f005890aa25e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T22:34:37.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3b993b76c145599ce6dfb3e7bb2e0e2643fa18bc3c9f0b1aa7f5251dfcb4725d","measurement_key":"834a251b7dac12d958925913c30ad598ab7fd405ab269b979babff9d6048df18","metric":"mean_score","protocol_fingerprint":"b4690aeb54cab157351a24640565f368ae0d16229c6fab0cf18e044e124a89f5","run_fingerprint":"71bfa7e84d6757644a0ad5c45fb058d425a5a3e2c9fa4bc7775374f07411bec8","score":20.350877192982455,"score_display":"20.4","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_c69dc5716abeec6f1e0c8be8","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4481172c8ecab8af86b10b2544514a2e5b0f8d9ab7683e51a5500dbe8f19759c","measurement_key":"0b9edf037ef2ec731e047aa0bbcda2f15bf26045254097e878930063a594dd28","metric":"elo","protocol_fingerprint":"7c52cbe81c74dcf38f40cee2c97ab50726fb2468ae1e1df76082a1c916930c1a","run_fingerprint":"c527342f4cf715a1fac48c75dcc24534b6f8a6c29199ce2ed185df2fa923a9e8","score":899.46,"score_display":"899","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_fa62330ab4b31843f371c58b","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_f83cfc2a9e19b8d654d7b58e","benchmark_version":"GPQA Diamond (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"25f45c87c06458d5f804bb2501f1b2191572d67761528da97aa3e238f6d78866","measurement_key":"4cc9f9fbf97ddd555334005a663638c8c84ba27ca0ada4e862312cbe8671a95e","metric":"accuracy","protocol_fingerprint":"43eaf88ff9d29470bcda8b94c866270080c84928f10fd2c2061690b79a22d7c3","run_fingerprint":"337025d3ca924fa01952a4dc5f3b3feb3c95d29927175739c5d941d3ab57b99e","score":84.141414,"score_display":"84.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"diamond-198-zero-shot-5-repeats","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_fa62330ab4b31843f371c58b","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_fa9e908ac04b067eb00182d4","benchmark_version":"HLE official leaderboard","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":63,"at":"2026-08-29T23:52:43Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b21193e81d616300064c35ece117e7f54bf8d7447c0b4aaa4c2a741fd021cbce","measurement_key":"00942fc49bc34220721eea4792e0ecd2e0256d7a7f0a6fe09a97605dfe9b3a9b","metric":"accuracy","protocol_fingerprint":"e1f956386a97e6ba42a3c396757902d19f19cdabb10fcc91e345af5c771a2890","run_fingerprint":"05d26df8485e1bb6d2a57967a93f419a9c8f9261fc1d688f8b5723161d31eabb","score":21.4,"score_display":"21.4","source":{"id":"hle","name":"Humanity's Last Exam","url":"https://huggingface.co/api/datasets/cais/hle/leaderboard?limit=200"},"source_authority_tier":"A","split_or_window":"published-leaderboard","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e4a5a6dee408943601c0a8aa","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"C","evidence_rank":5,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"self-reported","verified_status":"self-reported"},"unit":"percent","verification_status":"self-reported"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7cc2ae8b7459db7b59b32c83b22c207433b056f9c2768232b3ae5a3cd4374639","measurement_key":"bc68f8bb13f3c4e082fc747d8eb20d33db1144e361fad84e0eaa3b62c46d81e0","metric":"accuracy","protocol_fingerprint":"7d249a0bc527bb3d21e418292d87d73bd092ea0ac3cbb03fc81ef2633cd19ac4","run_fingerprint":"dbabf752d251a308cece4269d7eef5939557386beaa126b75a7006a076a9d7af","score":22.242817,"score_display":"22.2","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_fa62330ab4b31843f371c58b","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livecodebench":{"benchmark_release_id":"release_b530ca4da413885c54f52baa","benchmark_version":"v6","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":199,"at":"2026-04-16","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"155dae3ff9ef5db154bec3fe3edff55835c072f94dbe16df72e696ffc9ff9ad4","measurement_key":"f8016237f5b43f66ab74515e3f9ab9ecd6dd0faf62bb0149166c64d8b0a88477","metric":"pass@1","protocol_fingerprint":"c5897a9b1049c59b6cd6b78df57d0085d6d80e4198b3402492e385b10f29623f","run_fingerprint":"a3203eca6c4217aa2021c6b546a8d783f3d9fb86d5e0fa8725630b7ccfaf72c8","score":80.4,"score_display":"80.4","source":{"id":"qwen3-6-35b-a3b-card","name":"Qwen3.6-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},"source_authority_tier":"B","split_or_window":"qwen-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_771e537906e49bf2223bf52f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"mmlu-pro":{"benchmark_release_id":"release_95dc04609d027072fa229d3b","benchmark_version":"MMLU-Pro · Qwen vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":199,"at":"2026-04-16","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"56025d5f422d3e5038eef6ead2713c289c780a06680a3d3945ecc5b5b549fd3b","measurement_key":"a580ad58906a2dd13db8d832cc8c277280deebc7a1749824d35abe0e8566c013","metric":"accuracy","protocol_fingerprint":"70c7bbff02e177f65267ba3c33be7b6f38096fbaac03c9cc970c7210519303fa","run_fingerprint":"b3f100c62868a333f56d5066df5805ed52221f39edcd19b44a6eab2ef379e226","score":85.2,"score_display":"85.2","source":{"id":"qwen3-6-35b-a3b-card","name":"Qwen3.6-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},"source_authority_tier":"B","split_or_window":"vendor-card-protocol-undisclosed","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_771e537906e49bf2223bf52f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9e5c24afe2e40d7efedbc391e9a7976a4f8573e4b54852b749e1857967d75817","measurement_key":"dd3bb3188ddc7f8269682b6bef06ffb5d4b66f7dd9f6e17c2086acaafc4b641f","metric":"accuracy","protocol_fingerprint":"409e11545fbffec5513b54c0e3b8bfa2516be53601cb2eafbaebfb23227c8db5","run_fingerprint":"f7a48aaa1c89cc1723ddcb1735b6aa5ddbbb9108cbed7664030e63632c2ece7a","score":75.028902,"score_display":"75.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_fa62330ab4b31843f371c58b","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-07T00:03:16.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1af8bbdd697a14e1d2e7541b9b95099768aacc4443330974b919a103914ff6b8","measurement_key":"d10b57657a8b717028c5a4d391b8511a4a7e6a05670382f29d607c83eba5d1e2","metric":"mean_score","protocol_fingerprint":"8b33069dabc4dc7d46ccd6d6ba796cc168c2e534203b12e04d74fff3b0ea4446","run_fingerprint":"318f534cb9713c7d6cb547575e8ba8d4be46c4cc1b94215f470a03ab237ce952","score":86.66666666666667,"score_display":"86.7","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_20fa5f508edb624d3a1dc2c8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dc92775b61568a35938a8683e22011f60d19b3f40a3cfdcdc69e4b9d8290cfcd","measurement_key":"0ff8115984e893964c8e0f91025a98287286da666d1b21ab372a12f9f7188748","metric":"subproblem_accuracy","protocol_fingerprint":"766e63482093f225aa48b8c9dcd6ae1401800e990b7a82beb625e35e35b8bbf7","run_fingerprint":"12083a6beec638d308dee12ffd2e61b4d27a6aa48fc0a9d37b9e8dc0b0b4cbc7","score":36.5740740740741,"score_display":"36.6","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9f8b471c8142f59bb8b69a15","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"skillsbench":{"benchmark_release_id":"release_5af9fe5a9d5e275323798c8b","benchmark_version":"SkillsBench · Qwen 78-task self-contained subset","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":199,"at":"2026-04-16","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"7c4f2d563f9e4f620d204582b31e1e91f63ef7c14f7cefb4c42bc5275d6c28eb","measurement_key":"c90b740298855db0191c66584af78274a209ae4e6488f36d4a190f2033cb655b","metric":"pass_rate","protocol_fingerprint":"1ef4df8bbd26617f6a97c4748bab4ad0b89cb62c839ee783c7a5b25a8ac69428","run_fingerprint":"ac46754bd3952d481779be1a27c2f62f553c72965f6be0ea0f7234bf91c87341","score":28.7,"score_display":"28.7","source":{"id":"qwen3-6-35b-a3b-card","name":"Qwen3.6-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},"source_authority_tier":"B","split_or_window":"self-contained-78-no-api-subset","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_771e537906e49bf2223bf52f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"swe-bench-verified":{"benchmark_release_id":"release_9162beb27813d52a46a20a9f","benchmark_version":"SWE-bench Verified · Qwen vendor protocol","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":199,"at":"2026-04-16","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"224c0cb53943005091adb7877073c5fe77eeb15b2fe1e90b5ca844041e515ec4","measurement_key":"3af38685ef14c4c3e23095dad6fa26460562b12a216881b9de87957a84bc4df0","metric":"resolved_rate","protocol_fingerprint":"dad3fccd5f7c7052561a2997a748ad0d5aa39550e8421c973d8656bf054626e7","run_fingerprint":"a4416af63b6b3d09d84ba5e68c68af087f3b48f44b4fccf015387f058218bb32","score":73.4,"score_display":"73.4","source":{"id":"qwen3-6-35b-a3b-card","name":"Qwen3.6-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},"source_authority_tier":"B","split_or_window":"qwen-internal-agent-run","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_771e537906e49bf2223bf52f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report","views":{"reported_system":{"benchmark_release_id":"release_9162beb27813d52a46a20a9f","benchmark_version":"SWE-bench Verified · Qwen vendor protocol","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":199,"at":"2026-04-16","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"224c0cb53943005091adb7877073c5fe77eeb15b2fe1e90b5ca844041e515ec4","measurement_key":"3af38685ef14c4c3e23095dad6fa26460562b12a216881b9de87957a84bc4df0","metric":"resolved_rate","protocol_fingerprint":"dad3fccd5f7c7052561a2997a748ad0d5aa39550e8421c973d8656bf054626e7","reporting_origin":"provider","run_fingerprint":"a4416af63b6b3d09d84ba5e68c68af087f3b48f44b4fccf015387f058218bb32","score":73.4,"score_display":"73.4","source":{"id":"qwen3-6-35b-a3b-card","name":"Qwen3.6-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},"source_authority_tier":"B","split_or_window":"qwen-internal-agent-run","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_771e537906e49bf2223bf52f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"strict":null}},"swe-rebench-v2":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"277f0c7209140553e497ec74810fd8734d884598d12ea6206e87ff3a4c868e76","measurement_key":"9ec8a1487d3c7ad140e2c34c1a70e9dee3ef72b0161bfcb6cd3164e9ec759898","metric":"resolved_rate","protocol_fingerprint":"a399d27e825618cb353e8e50bf75dcd706952ca7575dce1096ed9443bf37b7e7","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-05-15/2026-07-01":{"benchmark_release_id":"release_b25eae1fad6b7076bdf70d48","benchmark_version":"rolling-v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":123,"at":"2026-07-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"277f0c7209140553e497ec74810fd8734d884598d12ea6206e87ff3a4c868e76","measurement_key":"9ec8a1487d3c7ad140e2c34c1a70e9dee3ef72b0161bfcb6cd3164e9ec759898","metric":"resolved_rate","protocol_fingerprint":"a399d27e825618cb353e8e50bf75dcd706952ca7575dce1096ed9443bf37b7e7","run_fingerprint":"bcc8e41dde7f4b66d8ec829c320dd9761819a8a5c98ef9d10a7318c33383acf4","score":24.684684684684683,"score_display":"24.68","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f377cfdc5fe45182122cd035","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"bcc8e41dde7f4b66d8ec829c320dd9761819a8a5c98ef9d10a7318c33383acf4","score":24.684684684684683,"score_display":"24.68","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-05-15/2026-07-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f377cfdc5fe45182122cd035","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"tau3-banking":{"benchmark_release_id":"release_c6e5abafbb7bffc0975932de","benchmark_version":"TAU3-Bench · Qwen vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":199,"at":"2026-04-16","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"e574e87e5070501a934849b975a8bcea9b21372b779ddc0338d4274b5ad49904","measurement_key":"ce699b0877596cdb8f83dae19c0fc574a0b4c9e5ddcfa26e2aeafb8a714c2438","metric":"pass_rate","protocol_fingerprint":"ac033ae84d9e8c3792065e58a44a15f3d80b846134d957b52b2b43ded2458ebb","run_fingerprint":"0eb52403dc1e2c99a89458965f90edefc52618f10f346ce6633a4e5bbf742904","score":67.2,"score_display":"67.2","source":{"id":"qwen3-6-35b-a3b-card","name":"Qwen3.6-35B-A3B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},"source_authority_tier":"B","split_or_window":"qwen-official-user-model-bm25","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_771e537906e49bf2223bf52f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9ba30ba3e9d8a0cba7896284c6b52afa4f8e0b77714096b816931af4eecc5a6b","measurement_key":"64e37e1769be5e8e18388c2d16b04e77c38ab28f5cf6b73041c3923b9dd0090c","metric":"pass_at_1","protocol_fingerprint":"fe6ecc7d35a7d6b511e8c0e144cbe3f1174e02bfef493c3afd91004448589cdc","run_fingerprint":"0d5b68e31981ac4fedd61c3e8491a5c3c9a47200b159582942a6cfc9ec3ba275","score":9.278351,"score_display":"9.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_fa62330ab4b31843f371c58b","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_c53c830678318dc1763793c8","benchmark_version":"Terminal-Bench 2.1 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a7c1f69834b429ed2617399373cecabff5182d6bf2a5e50cb15b7c1fb44ec01a","measurement_key":"93710c59a4317612223a866f381c9747c9343c8e0f6cf44a97d6149cb51dec8c","metric":"pass_at_1","protocol_fingerprint":"a36d5f73d6e5a36197320d6f5a15cecaf242e49008583c6dc40589b9d1e92211","run_fingerprint":"809e4b563e243904bafd67a0e2403e35e7adcf5f2ff60a91de5fc994f9f52f1f","score":44.94382,"score_display":"44.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"terminus-2-89-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_fa62330ab4b31843f371c58b","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_b7d9ab744ffac0cb856e114d","benchmark_version":"Terminal-Bench 4.0 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:17Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0dde2bcdeb6bd4e6db7304498ec0905a98de2b97431078c3e4d134e1e8d15bfc","measurement_key":"0cd0e0e5fbac584f5fa0476111de72e07ec3b1f3d8d4f381a76863aaa76dc48e","metric":"pass_at_1","protocol_fingerprint":"14947b626dca43242a89569994807d9d005f2ff17b42177d4963c9ed18fd3609","run_fingerprint":"c006572d4493d234c814b6404dcbb94ae99299a2de00c6b52af30946e625cf7f","score":0.0,"score_display":"0.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"mini-swe-agent-66-tasks-500-steps","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_fa62330ab4b31843f371c58b","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_65fc140e7ffbb7bf62021f84","benchmark_version":"Text Arena Coding current pool","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:15Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8f5fd428cec0612b9e31b687887691cf101d7491b75de81e5fd057da9cea81f2","measurement_key":"7aa63b4beb380689382089125e7117967fcfbc8c017e9c69a9d7b4ede9677576","metric":"bradley_terry_rating","protocol_fingerprint":"c9662d1a8fa00d0b928c4439fae85fbe4d0b0b5bf5f3915e743eece8b290e8f5","run_fingerprint":"0a6740bfe0003766d05a2be59d494b06fa9d5ed3ce16fecfec6c6da4f6fc00a5","score":1250.15,"score_display":"1250.15","source":{"id":"epoch-webdev-arena","name":"Epoch AI mirror · Text Arena (Coding)","url":"https://epoch.ai/benchmarks/webdev-arena"},"source_authority_tier":"B","split_or_window":"text-arena-coding-bradley-terry","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7831c3668b6ad545a4b181f8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6d19c9fc3377d2468854ecbfb8aba4529637ccb9f113c1a1875f08dc406d6a70","measurement_key":"42ad0c3ab9ae040c92838e83b1cba329ba73e18a3b758eed3413ad0a6e1e317c","metric":"accuracy","protocol_fingerprint":"c6c795b7e9a1dbcd297aa30fcc438a0b5d01f63aeb58081a4b8c2776603b447f","run_fingerprint":"d3ba5a61e6a9e3978f73df75ca41761992a18a09b6557ffaf88d9fa8c07ac2c4","score":34.49,"score_display":"34.5","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_766e368be42d8b18446b5ede","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":true,"model_id":"alibaba/qwen3-6-35b-a3b","model_name":"Qwen 3.6 35B-A3B","parameter_count_active":3000000000,"parameter_count_total":35000000000,"provider":"Alibaba","selection_rank":83,"weights_status":"open"},{"cells":{"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"442afa4ba4c3760951bcaac67f0947e491ad2ea762e3bf29fac3da7ea9e8c811","measurement_key":"0abc502b49cdccca92eee63b9d0416e7aae07adbd9dd61bf31e5cb07c318cf96","metric":"ips_score","protocol_fingerprint":"1ba5ed3ee1b56f6117b4921d36f1d7ec9f63734e33fcc1eff4067e87fb591576","run_fingerprint":"2f1a43e4ebfcbef878f6d530f831a8b290759db10ca2647b3a47dbd96911a3f6","score":-0.04022661938759629,"score_display":"-0.0402","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_905688dc095b693c8f3fab53","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c1c7a90be90ec6878521ad2562c12ac18a3e6193da387e3288008fe971fa530b","measurement_key":"657636a24eedf07981a57fd213d95dd7a90770b521a4fd0c3694e99673783782","metric":"accuracy","protocol_fingerprint":"95e3251a48840fe43ec7d3a35c85d33000956d934cf5658c049514852a511dc7","run_fingerprint":"4e4dce762d957c28dfd118dd80d68c64f5236000eb9b053b219f419e15e2dbeb","score":11.142857,"score_display":"11.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a9a476e7573bba3097d22172","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"deepswe":{"benchmark_release_id":"release_12e8a62d68d933c29dcdf020","benchmark_version":"DeepSWE 1.1 vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":66,"at":"2026-08-27","last_confirmed_at":"2026-11-01T03:42:36Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e90a3198f6d981321746ff06de256d780783c636f766d15c1c8338fa409b1cdb","measurement_key":"662402c82ea4861d7b699aeb30365e99fe90fbef3371c36b75fc50e533a0a1c2","metric":"resolved_rate","protocol_fingerprint":"8952100b315bc05cb6845e1f3c7939f39264ad2d12eab342c072a06b1c4f1351","run_fingerprint":"949a28e6130f4052403eb43c6cdcdf4c1b49a73e88bd5103937d5640882024fc","score":58.7,"score_display":"58.7","source":{"id":"qwen3-8-flash-card","name":"Qwen3.8-Flash-Next official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next"},"source_authority_tier":"B","split_or_window":"vendor-model-card-run","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0ee939ebaa5890202c8663ac","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fbdb49cc508f7b40ca48b89f96eb7c310966cb0dea77b9fa1c530ad0c563ec53","measurement_key":"ae32f1121d8234b44abd633f51649d6148ef27637b346d9a95322cc570fea2eb","metric":"elo","protocol_fingerprint":"fb4990f26a0e638d811ef69156d86fa985f98d759defc5e8df18fad20f1d90d1","run_fingerprint":"a03bf184cc44b71054168f8885bcce77784aa43ef879a2e170aa5b4529afab18","score":1635.78,"score_display":"1636","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a9a476e7573bba3097d22172","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_f83cfc2a9e19b8d654d7b58e","benchmark_version":"GPQA Diamond (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"be4db36753516bfad62409acb8c07fbf32cfed02c9fd032f03667befd9d6414c","measurement_key":"1d4cc5229fa99849e1869abb512e6e7e4fdf41fa90f25cf55f2c13cfd57e5234","metric":"accuracy","protocol_fingerprint":"96a8d2d312a7017af06c07868a02badf24feae0b6af2f80ef79cfd4a09f2bcbe","run_fingerprint":"13c5d95f1c9407120e26f3dc87410ea852f95a2f522e51ca8454802300812007","score":92.323232,"score_display":"92.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"diamond-198-zero-shot-5-repeats","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a9a476e7573bba3097d22172","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_287aa4bcb31b5b1ba26e562a","benchmark_version":"HLE · Qwen vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":66,"at":"2026-08-27","last_confirmed_at":"2026-11-01T03:42:36Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"49d0aee1d3d042d3f65fe4f1ee5742ec7a78f5123e770f6928e9284a4cc7696e","measurement_key":"a0899c0b432e214c7748dc2f008a46108dd588bb05d5856211659fed4fde8460","metric":"accuracy","protocol_fingerprint":"70e596e918ba6dfcb89e204cfc4f567f7cfee53e41c3d48d086272421582cf13","run_fingerprint":"6d626bd77f15e5242b6d18759f61c6bfbf2db0fbd66caf747183fcf5f773065f","score":35.9,"score_display":"35.9","source":{"id":"qwen3-8-flash-card","name":"Qwen3.8-Flash-Next official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next"},"source_authority_tier":"B","split_or_window":"vendor-card-protocol-undisclosed","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0ee939ebaa5890202c8663ac","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e66906c8a3ec83ecf82f6cf8b3a0179d857965a793066f094eb5e2075a4869a6","measurement_key":"6ef2c2ff4b1dbfdb194f10697533ca603ce5433f8a8060bd60be21bd8eaf359e","metric":"accuracy","protocol_fingerprint":"fa3a16087856d6b370a7cc0bddb3305dd311110562c9d2678fa42f46fec06978","run_fingerprint":"f3abad538a865df0d32eda6ecf280877592f3478b41513a3c3a989870fa6f130","score":38.044486,"score_display":"38.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a9a476e7573bba3097d22172","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:36Z","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"23c8f637313e13ee86c5a006d08a712687ca350daea18b06e95caae320ef1ac4","measurement_key":"ce7c87ecd33e8faf522a02b63482eee2756d28477ee1a7cb9e7d50863a086f0e","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"fc84ad62421809cc0539b9568c74d402790d4cebc56de197eeaee90db83719a9","score":76.19415476190476,"score_display":"76.19","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d95c76a014239d533b5e8b3f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8831df20f5f870224c6c67ade64ea474cafb4a55ce8cbb74fac2ac1e601f674e","measurement_key":"54ff40c12e1a7f4bacc5e8af7029ef231b259c1bd5460c5fbc05f61b4bc29ee3","metric":"accuracy","protocol_fingerprint":"343457ef16609f777d8a29321f25ebd88d24f7451aa6ce6625c800d64e623b43","run_fingerprint":"043117908cf30ce05b0bf2d02b0ecb53964675b543471b0e39000be5f30fd087","score":79.768786,"score_display":"79.8","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a9a476e7573bba3097d22172","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_de40c66bd40a7b5483b40f9a","benchmark_version":"SciCode v1.0.1 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":56,"at":"2026-09-05T17:21:27Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"06ac9d6efd71ee7dc92d0a31174fb41bdaa7d310d16096e1422b300d7507efd0","measurement_key":"64084f16867b94ad64d61f44611a3123b32f98f30d0a3038550fe66467c943bf","metric":"subproblem_accuracy","protocol_fingerprint":"e8b485c58fee3e97f4fe7a224620a310102d3c6952e5799ecc39671660311646","run_fingerprint":"bd88a3761ecdf0891f381973cd8a40d75525a66f663eb7f802057852718dc180","score":50.578704,"score_display":"50.6","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a9a476e7573bba3097d22172","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f1d9597544051938bf47a0a4c142e5e9f3d777548c71c01d56fc5e5e1d6b1173","measurement_key":"6007f84cc4e4b1d21c0387d6065967bd3802b3bfddc4e127caaf464a64ba1bcb","metric":"pass_at_1","protocol_fingerprint":"fdc0aeb253baf28cd463d39c9ebab3b9206e0bdaa677e65a59a9743cd272bc31","run_fingerprint":"38e33aa0e5eb214e27961806fbbd0bebdb5e6c7dba603dbdbff29e7cbe432581","score":45.360825,"score_display":"45.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a9a476e7573bba3097d22172","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_c53c830678318dc1763793c8","benchmark_version":"Terminal-Bench 2.1 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"27aee8d88572b62f0a90e0f81d286ba3499ffd2d0f1189dd2863f178a77443cd","measurement_key":"a72a09acdc09fdf6587b4bc1898b62e66978efb2d9e5de8f85f8c840fe5f8ea7","metric":"pass_at_1","protocol_fingerprint":"5f6fb3bea08984c87ec14fba7756a8d20232a7ac9b38f3bcc2ec256472771f93","run_fingerprint":"e7be9ef0ed2a31067b66233bb66caa3b509e4aab835e956922b3479d32b4cf8b","score":86.142322,"score_display":"86.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"terminus-2-89-tasks","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a9a476e7573bba3097d22172","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_b7d9ab744ffac0cb856e114d","benchmark_version":"Terminal-Bench 4.0 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:17Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"09dabf754c08ced5d1edfd1da8b8beed059c2ea2c064f6cbb924df7058fa3818","measurement_key":"5d9f1797a851815ace4467e4e1f0029baa4471fa840d50662b9c96fde310edd3","metric":"pass_at_1","protocol_fingerprint":"074587c74ddeba8d16bc4aa58ec9ec9ee03b64ba6db2db5bfab96c64f3fd53ef","run_fingerprint":"f30f1bb94f7c4b6bf8ca555c176334248fbc9132c01e56d3f43c8ea0d9bdcca5","score":25.252525,"score_display":"25.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"mini-swe-agent-66-tasks-500-steps","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a9a476e7573bba3097d22172","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f65221593ad2b841b953212b5455dde404372e9545456c5d91857a89878ae0a9","measurement_key":"e2157c1d591f90a5ffcd4e55080ade573ce67c2adfaef9f0c371611b27ff1e21","metric":"arena_score","protocol_fingerprint":"b8edd355d20d33258f3eca81e0d0b87541d0515330d92d6324b937db2ddf48a2","run_fingerprint":"f6c917cae705f3c8294efea0635e591eef12801d3d3ceabd2f695001186a5080","score":1628.3220907822047,"score_display":"1628","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c9c41d02d7ef3f31e9d42eeb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":true,"model_id":"alibaba/qwen3-8-flash-next","model_name":"Qwen 3.8 Flash Next","parameter_count_active":6000000000,"parameter_count_total":125000000000,"provider":"Alibaba","selection_rank":84,"weights_status":"open"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"39dd03db89da3440a278ad54919e1d79954ae4219040669ee001e4c036a21996","measurement_key":"e191435c077d39c8673c90e918d78bfcdd57a2e97d635e3190fbca2ccf7ae8bb","metric":"performance_rating","protocol_fingerprint":"7ad5ec9cfe49e1d8ab07f2b42696a1b26507dbdcb90832dad73af780b7a383e0","run_fingerprint":"c756e2d8be60aba061b67a1a95cfa26df11fcd01919b89378affb878ea1959db","score":925.5,"score_display":"925.50","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9bb470d85c107daac9f268e7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:41Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b9dda1a7a1bcfa245a0b27dc5b5d5a94adfb053338ef6ad5e0448149b8de200b","measurement_key":"6be01ca84b2ca50db5c6ccab646c4c5131bb71f0194bd306a56ad1d1ad1e60cb","metric":"accuracy","protocol_fingerprint":"0cfe56e5bc37e596794d50564f26128c19f9853fed0f910971fbed831d41d643","run_fingerprint":"5abb5f89b01ff96359cd1a5b1017da7bcb7971173ab2e0595031693a7205d5b7","score":1.42857142857143,"score_display":"1.4","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7d82a165512b034548c396d2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4ad24a168e6d9825842c67c75b59cda8cebb24357935d3d22bc1278d11ddadc8","measurement_key":"8ec266c93642634a6673e5917ee5b0ba75dffb59b441fb73ed2780984bec2e98","metric":"eci","protocol_fingerprint":"3f8096875b85336944d40d3b06a9b502e3c6d15ea3eef0543a5fb399c882b1d5","run_fingerprint":"cc81244a93076e0168727fe63a1619c880b161f8df9af5da59962236a45a7f9f","score":143.08,"score_display":"143.08","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_5df12bd86522bd0fba242adc","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-06T23:59:38.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d376f4e49689556b76201a01d25993ffb542a4d059898a61546c91a38589a4a1","measurement_key":"f80f585d3513a4fbc16b568e40c0d1620dbd7698f401c0c14a544638646f86a3","metric":"accuracy","protocol_fingerprint":"32b3f877f64442a1212d93dcbfb81f5c80369c109f440911702295426a25237a","run_fingerprint":"6e02d42e2d21ac45fc5435e3ce78467997da817c01fb0836e6604e00ae06fcc5","score":75.75757575757575,"score_display":"75.8","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"minimal","profile_id":"profile_af2ff99bab99820d4a9eb678","raw_label":"minimal","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_9b8cd6ba0a835eb2da22bb93","benchmark_version":"HLE","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":104,"at":"2026-07-20","last_confirmed_at":"2026-11-01T03:42:37Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"33b6281ff3e4ea642abf9498634127dc6495925dfb92c55ccb9411fd7123b2a7","measurement_key":"39484073340c51346a70c27feb0dbfe920beeb8ef41b4fc2777d4850e99a479c","metric":"accuracy","protocol_fingerprint":"9bf33a886a0f23c36ca21f71357edb46598a0aa53c037d5b817890035204e13e","run_fingerprint":"f29f4178978b7af215f39660737eae7e7c3029f1ce53d84b4ac3f50fbb003879","score":19.5,"score_display":"19.5","source":{"id":"gemma4-31b-card","name":"Gemma 4 31B IT official model card","url":"https://huggingface.co/google/gemma-4-31B-it"},"source_authority_tier":"B","split_or_window":"google-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e32b67ae6bf59f0434d4b67f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"ifbench":{"benchmark_release_id":"release_4adf348ac2f76539ed7ccb10","benchmark_version":"swallow-evaluation-instruct","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-09-30T18:53:19Z","last_confirmed_at":"2026-11-01T03:42:24Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fd2bcf07c727dcc8176a3dcd5cf4a9114db31356efb3bec74b4daed4945ffc16","measurement_key":"c0bad531d08cd51f1a76fcc10d43b25d7352de56ff99512b210cde12db5faee8","metric":"inst_level_strict_acc","protocol_fingerprint":"6cfb052f9166158b3e6c3af96acd982cbea69c72aac5685f77a8a96d272bc4cb","run_fingerprint":"6bc1a87a33305bba5e345913c69faa169b17aca9640083ab6484f16524d31678","score":76.5,"score_display":"76.5","source":{"id":"swallow-llm-leaderboard","name":"Swallow LLM Leaderboard","url":"https://raw.githubusercontent.com/swallow-llm/leaderboard/c58a13a852eba061d639af7caf4ddbdff33b36e3/swallow_leaderboard_post_en.js"},"source_authority_tier":"B","split_or_window":"ifbench-test-300-prompts-344-instructions","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_82d7b860b7defe3c83636cc3","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_1d1cf16bb310d2fb0576bb02","benchmark_version":"v6","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":104,"at":"2026-07-20","last_confirmed_at":"2026-11-01T03:42:37Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2f34f468b18cbd0c11832768d6dd2e9ea628350f6de035ca9b3dfe45f767d6da","measurement_key":"0c36157f76908a6436324a4a537da0f8f7dfe509ae52ae7e2d6b8c87bf6fb514","metric":"pass@1","protocol_fingerprint":"6d83bbcf136942f9b5279b1d5eef6f61d1c43f1bfd5d2d2a9b7aee53f4a643f4","run_fingerprint":"eaf6d59bbcdd16bcaac3a5ac06f41977df3acc8aeadd3ee2df9e26b99c1817a6","score":80.0,"score_display":"80.0","source":{"id":"gemma4-31b-card","name":"Gemma 4 31B IT official model card","url":"https://huggingface.co/google/gemma-4-31B-it"},"source_authority_tier":"B","split_or_window":"google-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e32b67ae6bf59f0434d4b67f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"mmlu-pro":{"benchmark_release_id":"release_cbef64e634e73d9217bfe565","benchmark_version":"MMLU-Pro","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":104,"at":"2026-07-20","last_confirmed_at":"2026-11-01T03:42:37Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4f9949cda683889721cbde50c847a62adada4351046b79163a263f6f7c97fe14","measurement_key":"4422d96e7bf967a78e059d47dc01f3b063210f971efeb40ff216693851d66a20","metric":"accuracy","protocol_fingerprint":"78530b6152fd4eaecf30afb5b591e4d005694e92002f866fb1149eea1731e217","run_fingerprint":"47a3f272644a74934efee821a31ac6b49d38ab79f6db5c4b81a7d28d95df49e4","score":85.2,"score_display":"85.2","source":{"id":"gemma4-31b-card","name":"Gemma 4 31B IT official model card","url":"https://huggingface.co/google/gemma-4-31B-it"},"source_authority_tier":"B","split_or_window":"google-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e32b67ae6bf59f0434d4b67f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"mmmu-pro":{"benchmark_release_id":"release_6f3fd0029277bfcad78a10b3","benchmark_version":"MMMU-Pro","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":104,"at":"2026-07-20","last_confirmed_at":"2026-11-01T03:42:37Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b79e7440839dbcf84a17ad59d2677f7937dc77a425fcc4325cca5892dd93c776","measurement_key":"e7e852b5c5cd6142874a422ab75c4e4d355968047d966f78f6479ddf644d3382","metric":"accuracy","protocol_fingerprint":"b4ea8f2c161f678a1cd9587ed3df25a8dd6a87cbc1e1c751bec680b93db62fb0","run_fingerprint":"6f348d5593d6801efe9aeea7e579c7a2ddb03d14b3b9a7f12e2f1b68535d0b4d","score":76.9,"score_display":"76.9","source":{"id":"gemma4-31b-card","name":"Gemma 4 31B IT official model card","url":"https://huggingface.co/google/gemma-4-31B-it"},"source_authority_tier":"B","split_or_window":"google-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e32b67ae6bf59f0434d4b67f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-06T23:59:45.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0605537700019c3c627460b1cf538754616d4b111b405107e658e76cd26c2308","measurement_key":"1b4aa7b674e54052573782e6a348a71dd66e872c5c764bb6994a1d397336c6e5","metric":"mean_score","protocol_fingerprint":"07e5cbaa45798df58d2463abaff06d5b328765e707e6e30a522c548f450919c7","run_fingerprint":"06fe7f3aa09c562ad2c99d740b3c4fb874387ae04c2da7d0e67b9a2810e49a24","score":73.33333333333333,"score_display":"73.3","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"minimal","profile_id":"profile_af2ff99bab99820d4a9eb678","raw_label":"minimal","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"29e576a435b30fd9c90afaebf4e3efb898912a3c6efc730c34909186f0ad2b5f","measurement_key":"f72875dbd6a1f5ebbba5b6ea7013f53d03211a50460abb8092d674e718c3477f","metric":"subproblem_accuracy","protocol_fingerprint":"78047ad15e5eb077962e61f38f7459e1eec7493ed9d02e1063369fc7aa5a19be","run_fingerprint":"7d20e6093f81c0b03b0b41d6f6b7bf2de73b47c7bcc6473baf84595b2387dee3","score":45.4861111111111,"score_display":"45.5","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e139c296e22aa94481af21b8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:30:07.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"46b98fe9db692e65b4555920d3b384862d63ec16a682254b9ad8bd2cd085fa31","measurement_key":"92e3f700fb1c1d6a5ae469d882e92559c4514fc164b88d3eced27b9d881fe6f3","metric":"accuracy","protocol_fingerprint":"3ac8135ce62560dc2e1a768e0d30d97275fa17858342f1639436428e2c14b10c","run_fingerprint":"3b8e30cc051012cca3f62f02e0a30dddd7c20ac090da11df88f85f53049de715","score":10.4,"score_display":"10.4","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3bc4445984e2cfe1b5212307","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_65fc140e7ffbb7bf62021f84","benchmark_version":"Text Arena Coding current pool","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:15Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b611de399190d651846614a7f08c3e9fba3184a2fe2a71bb514d1b2e9abc929b","measurement_key":"d8de26a8ae68bd6665c108ec0d72193dca873d77fade9a27b115c33f8a5b309e","metric":"bradley_terry_rating","protocol_fingerprint":"a1493a09d9576bf0250a9a2dc1b687cc35f4f06bd586fe3e0007f0ff135aad04","run_fingerprint":"196e1911cce5af03af1085f765d196a61c96c3a4036df0dba4f332aacec7cc2f","score":1364.13,"score_display":"1364.13","source":{"id":"epoch-webdev-arena","name":"Epoch AI mirror · Text Arena (Coding)","url":"https://epoch.ai/benchmarks/webdev-arena"},"source_authority_tier":"B","split_or_window":"text-arena-coding-bradley-terry","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d9228fbf3d63a4e480591aec","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"70a3a8f413de5dac2933b048e958c39dbb1e9ae1f2278a9e40f40e96e8db1de4","measurement_key":"1dad47ea9012a8df597d97d76307ab49ee09876c986a63e284144cecccf9b8cd","metric":"accuracy","protocol_fingerprint":"18ea39e9a2f389d9640f329d7b2fc41406f5d7e4329aa71c69b1482d9dbd6ece","run_fingerprint":"a1a64ae228d171aba40f706420edf01a6d9e2455f8953c138323916d1b6c504b","score":52.26,"score_display":"52.3","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e9bf89560c783f7a74d891aa","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"google/gemma-4-31b-it","model_name":"Gemma 4 31B IT","parameter_count_active":null,"parameter_count_total":30700000000,"provider":"Google","selection_rank":85,"weights_status":"open"},{"cells":{"bfcl-v4":{"benchmark_release_id":"release_367e04d56fad3a6f9849489d","benchmark_version":"BFCL-V4","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":244,"at":"2026-03-02","last_confirmed_at":"2026-11-01T03:42:36Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"486d953a6edb19e2e0e1eac69de127d049a38ad4aa99be8d8dc5659d2a9f9dad","measurement_key":"27fef9521aa4c85cee307650b3cab7cd7cfa047175714b4341da2583106491d6","metric":"overall_accuracy","protocol_fingerprint":"9d10e802f12470bbac18314ad12a3fbec3074eedd5d2186e2a365133438c65d4","run_fingerprint":"83a334dce84488221936c7a13fadd794bdb17317f106acc1dd477eae4afbd8b5","score":66.1,"score_display":"66.1","source":{"id":"qwen3-5-9b-card","name":"Qwen3.5-9B official model card","url":"https://huggingface.co/Qwen/Qwen3.5-9B"},"source_authority_tier":"B","split_or_window":"qwen-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b87cc44f5a3902b1b71e87ed","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:03Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cea0225f303bedf6b2830c4bc9cb6c017aed351e783044cac3f076f0d2a91b99","measurement_key":"f4e5c6b26d7f1301aefd9ab073e05eea4f59297197062476230afa6d77746642","metric":"accuracy","protocol_fingerprint":"3963f6d4480ad557ed35cc4768ce48d66f48efb32f20ceb414f149f8b9ab5426","run_fingerprint":"e461ca18d9ebecf8f2718238ce01ad4853e92942f8991720a1fdc2594584f590","score":0.571428571428571,"score_display":"0.6","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_4779204b36659935aea6f3dc","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6455fbcd9300b203535be9ccf3c07ca1519308a4b7c3728a83ce23253bfb81d6","measurement_key":"e6bcc8d63de35e3403fd6e15be3a19a12b48f154e254790b3069f1e9e8c3e1ec","metric":"eci","protocol_fingerprint":"a7bbe8483e8615ef42616e54afc59e20ef74d773969cb6f3b6143ecabe42cbf0","run_fingerprint":"ce9999891a651259eb2b82400442b60a4eb9a68466e6569265e8a2f894957045","score":139.37,"score_display":"139.37","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_92d32148ceeb2d09e13b1a18","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cc1b5f17198a94cc14bcd50f89c9574235d58121794c425baeb5990a1fe1f62d","measurement_key":"5e1c5ea0f0acdba4302be9da1d2baae01aa73412fdffd27a1fb0b9a03f9f9ffc","metric":"elo","protocol_fingerprint":"dfc0ccfade597262db190d2a32dc545f2a3978536f008dbe6d9dd0a82d033431","run_fingerprint":"3b9bb4f9da67e2f57c7bc7a75a2c46d7168e31121f6d800134e05512410bebf3","score":426.58,"score_display":"427","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_128d9317b7e94f2fdf3d00ed","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_f83cfc2a9e19b8d654d7b58e","benchmark_version":"GPQA Diamond (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0187438286baa92acaa9bf9bfa0eb73ad8d08e7958d3bdbe99f153dab485911f","measurement_key":"007d85c13c7020d97326925ef816ede291844ed9d7608556d1b788f1d4a32c8c","metric":"accuracy","protocol_fingerprint":"4232061a938da4e3519e29afe67de368f790079a5b3f48f6520b7daac397041d","run_fingerprint":"5f0c55b62d650d789b21fb0fa27e3562d90a195966664b769afd07a0e50a09a4","score":80.606061,"score_display":"80.6","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"diamond-198-zero-shot-5-repeats","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_128d9317b7e94f2fdf3d00ed","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b7868f0886e8d8083adca18701114284576569c024b57263585dc4cd826d0746","measurement_key":"6c743dc44f3549903edfe7c5fcf56347aa8942d96692dc8e45629b883a2e2fb4","metric":"accuracy","protocol_fingerprint":"17211bf56287f72c07f53c3763c7956d1c2da66d284e1722f2a454e56e656c4e","run_fingerprint":"4d5d33513341af3eed2237e567a0e7fefc4e2bc053508272f1525ea6a37d5314","score":14.921223,"score_display":"14.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_128d9317b7e94f2fdf3d00ed","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ifbench":{"benchmark_release_id":"release_4adf348ac2f76539ed7ccb10","benchmark_version":"swallow-evaluation-instruct","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-09-30T18:53:19Z","last_confirmed_at":"2026-11-01T03:42:24Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e22c80f41d0986c1a1b38bc1bbd57a06b2db83c2408e5c8d7e6f55dc74ae1b75","measurement_key":"8a013deb814bd674977d0bf06a07532a59685084535224204e98249b73476c71","metric":"inst_level_strict_acc","protocol_fingerprint":"73ea367f7a86235a5d384e9dce2985cfcbe634f786e9dcc20c22225705467b05","run_fingerprint":"d257907fc25eed9b044ee68378705daae998f98425c18d8b0f7f61d2fd2c23b6","score":48.3,"score_display":"48.3","source":{"id":"swallow-llm-leaderboard","name":"Swallow LLM Leaderboard","url":"https://raw.githubusercontent.com/swallow-llm/leaderboard/c58a13a852eba061d639af7caf4ddbdff33b36e3/swallow_leaderboard_post_en.js"},"source_authority_tier":"B","split_or_window":"ifbench-test-300-prompts-344-instructions","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_128d9317b7e94f2fdf3d00ed","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"ifeval":{"benchmark_release_id":"release_eaa2f0262bb0264860cb2c8e","benchmark_version":"IFEval","comparison_lane":"source-specific","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":244,"at":"2026-03-02","last_confirmed_at":"2026-11-01T03:42:36Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"b843259777bba2aa4b266d44719f3606efdd96a235abb7aecd488390753637c6","measurement_key":"012018bbd080b9a41eb4b5ff0e91211edccb120899b3d56a55e7e470dee24f7d","metric":"accuracy","protocol_fingerprint":"c2532bd711b5e3c0b76299a052a42563ef11942e70f026510be845076dcb1554","run_fingerprint":"0d4d2a96a79a786100ab483068ec76c74fad3067e340e91b85af0a37a8facba3","score":91.5,"score_display":"91.5","source":{"id":"qwen3-5-9b-card","name":"Qwen3.5-9B official model card","url":"https://huggingface.co/Qwen/Qwen3.5-9B"},"source_authority_tier":"B","split_or_window":"qwen-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b87cc44f5a3902b1b71e87ed","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"livecodebench":{"benchmark_release_id":"release_b530ca4da413885c54f52baa","benchmark_version":"v6","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":244,"at":"2026-03-02","last_confirmed_at":"2026-11-01T03:42:36Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"ee0ed12422f2fea70a6d103fe70e39d4e43ab28813161dda0c31e04dcbf7a6dc","measurement_key":"6f4801518b11aa27249bb704804ccc69baaadb2489c20d458fb707ed929be26e","metric":"pass@1","protocol_fingerprint":"c1d1df0ddb34c3aad1342929c2b8d8d955114aae5c9a0d882037f2e4f2898440","run_fingerprint":"a1d652cbfb6a18325c2ff5520422d392a72743d8246741fc8cdc51dfb05127fb","score":65.6,"score_display":"65.6","source":{"id":"qwen3-5-9b-card","name":"Qwen3.5-9B official model card","url":"https://huggingface.co/Qwen/Qwen3.5-9B"},"source_authority_tier":"B","split_or_window":"qwen-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b87cc44f5a3902b1b71e87ed","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"mmlu-pro":{"benchmark_release_id":"release_cd90aeaaf8e38ae0a7eb7edd","benchmark_version":"MMLU-Pro","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":244,"at":"2026-03-02","last_confirmed_at":"2026-11-01T03:42:36Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"9e3c9648fd59b167e1c8c0819cebc876bd729996c0c8cd50f46b075e45062476","measurement_key":"48fd23be13a5f7099dd8daee460dd9709a3d2db3398af4c2a0ca678d24de2757","metric":"accuracy","protocol_fingerprint":"67b82b3d54800e8378e5357b208e7d192247e30225c7df8f7d7fbaa13b033818","run_fingerprint":"8eb7cf6080d4d5949b44a517ebc2102339590daeed7cf8a362deae972c072c4b","score":82.5,"score_display":"82.5","source":{"id":"qwen3-5-9b-card","name":"Qwen3.5-9B official model card","url":"https://huggingface.co/Qwen/Qwen3.5-9B"},"source_authority_tier":"B","split_or_window":"qwen-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b87cc44f5a3902b1b71e87ed","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"446c47973eb0727194a12afe4f071d86c294c8412e248852d408a5cd64b748ff","measurement_key":"861f8a5fc40fb301847aed02301b630369e836ee65532698b95c8f7938364861","metric":"accuracy","protocol_fingerprint":"34dd4fab6dce26b8d061080a94c98fe213c3d3ab32dd98def5e7ff099cbd78bd","run_fingerprint":"2f45ab3cdfed1b31d8a3b6691304a87de5ab071492535627a758c1bba67407bf","score":69.248555,"score_display":"69.2","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_128d9317b7e94f2fdf3d00ed","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T14:31:08.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ca8befb728e3c92ea525932d20b9a10711cf3fa0e8958bfd6bc54859cf7a416f","measurement_key":"b4ed74466f8d7ba9f46e4ecae9a2c29e5e19ca76aa774e6591597d476f4ed7e5","metric":"mean_score","protocol_fingerprint":"05e2ba21e785d3047e3d2cac876f614eca4581d545cf95a07baa82d5f5802307","run_fingerprint":"7dc6abd765e7f88864fe6b49795d01ca3246f228c7e82768d1851cf1b65d2f0c","score":61.66666666666667,"score_display":"61.7","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_4779204b36659935aea6f3dc","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"07f28a554f937caf024252099c601e53e6e968d690391469e6a49522c9f24bb4","measurement_key":"27a9102bc3042081ca9a7fbfa4cc80be0eef5d2013e67c8dc865f74920b173fa","metric":"subproblem_accuracy","protocol_fingerprint":"ce03d7b06d623fd647ca7fa0f501a311374ee36b58b6abddccbfb58c5e2868bb","run_fingerprint":"f6afd2c6ed210a4258728cb0a47198c2782da22209d675585cbb7ab30a351bbf","score":29.5138888888889,"score_display":"29.5","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b8beb3f11c16f95fe7bd0c8e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a1f33b3ee1231cdc9df821c82e545b6a0f95d77676f380de099fdc4218fa8f8b","measurement_key":"6ebdf7b6a73863470d4582a1d7c45232e898939ad2181c18af3ab32623c1ce5e","metric":"pass_at_1","protocol_fingerprint":"40e62be72828723b1479c7f8217fb6bb92767f840aa690e6f01aeef5c118c823","run_fingerprint":"47579c450dc6e32c121a8786b0d2c3f378780975b87843e3704e5de1d7923f4b","score":7.010309,"score_display":"7.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_128d9317b7e94f2fdf3d00ed","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_c53c830678318dc1763793c8","benchmark_version":"Terminal-Bench 2.1 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d9456099806ed96af5cef3c547a5a0d5717280bafc52f293e4254adcffd3bc59","measurement_key":"bed386bbd3110e4f86b3e7f382cf42246353db635bf72d56f0ca38ba0ea07563","metric":"pass_at_1","protocol_fingerprint":"7b8ecb4fba82b9e2c7d2e39b08d1f2ffbc09fa7cb79786b323a00bf93933c07e","run_fingerprint":"395eda4cce822acbdc033aacbe9641d682aa65f4d2a757d6a294f4501dacf1c2","score":29.213483,"score_display":"29.2","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"terminus-2-89-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_128d9317b7e94f2fdf3d00ed","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_b7d9ab744ffac0cb856e114d","benchmark_version":"Terminal-Bench 4.0 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:17Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1bf98ca38122403a56a213a1f77e1d6820f4d532ee8fff704fbd2b09e8e5f5ec","measurement_key":"40dcbf1bf08912cd353ac562b80f9b16ab715ae0c38a24ae0d93289bac255096","metric":"pass_at_1","protocol_fingerprint":"a092f43887d1c2633ca620892aef0f93724cc2ed9ef9f780a5b7cbb58a70b572","run_fingerprint":"2c892a023c585ae0e99f90aa99b99d7d8b9ef0a1192e49ca77b6117bfda92904","score":0.505051,"score_display":"0.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"mini-swe-agent-66-tasks-500-steps","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_128d9317b7e94f2fdf3d00ed","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}},"local_open_weight_essential":false,"model_id":"alibaba/qwen3-5-9b","model_name":"Qwen 3.5 9B","parameter_count_active":null,"parameter_count_total":9000000000,"provider":"Alibaba","selection_rank":86,"weights_status":"open"},{"cells":{"appworld":{"benchmark_release_id":"release_3fa145932216c0afcdd9dae6","benchmark_version":"official-c1f56015cf7c","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":259,"at":"2026-02-15","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"add59be5c620d5f99ea80296255008411c5ed53e69b7eeb132c55657881ad2b5","measurement_key":"053286b53e4428b5948dbfb7ffadd7789e67838f389ec185e8ce874327023690","metric":"task_goal_completion","protocol_fingerprint":"3fd2d05d1806fc66922d5d31d1ed44fa2ec28c31ae87e104d2ae6d50e87e1673","run_fingerprint":"6a282aa75481b9e6924ce9566869eae06b580de362e97655cf399e9f83b2edb7","score":67.6,"score_display":"67.6","source":{"id":"appworld","name":"AppWorld official leaderboard","url":"https://raw.githubusercontent.com/StonyBrookNLP/appworld-leaderboard/c1f56015cf7c3441ff1933f5bfbec879798d7bbe/experiments/outputs/_leaderboard.json"},"source_authority_tier":"A+","split_or_window":"test-challenge-all","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_65e947029c095ac93b048fea","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"bfcl-v4":{"benchmark_release_id":"release_7d2560723dba9d549cd10b25","benchmark_version":"v4-ede5081a24bc","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":64,"at":"2026-08-28T22:03:18Z","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a4be7722c0edcbeca9ee305400a8f3df1d6a0b321ffa1f9ef51f7ad5c2eac59b","measurement_key":"9a884085239b65b75bafac568bc1aba90581932794bbe5a5a1208c557e32e4bb","metric":"overall_accuracy","protocol_fingerprint":"6a9c99bccbca11748bdf70a2bdd6eb864726c94bf4a029f84ab95898fe96d192","run_fingerprint":"3b39bae4fee1ecfc98e5010cad97c89a5c8d0375f97c6b10e4bf0e29760015dd","score":41.03,"score_display":"41.03","source":{"id":"bfcl-v4","name":"BFCL V4","url":"https://gorilla.cs.berkeley.edu/leaderboard.html"},"source_authority_tier":"A","split_or_window":"overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_b2ae49bd61766d7bcecc4aec","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T21:27:01Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"50be307c898b725bfa259f8738d0e8eaeb717a93fb7b8ed73b4001c2193c1c03","measurement_key":"621e016a734dd10e3fc7a9427ebbf0d3d49a7bab3a5239bc9c33e72e06556c69","metric":"accuracy","protocol_fingerprint":"9e57af0a6ede2d58f965f4e049058a4a2c8ad42b3a15fd865d21d3d2db170f48","run_fingerprint":"bbe681072662e313775063854049721b450309f846b1791c245f6966179fe320","score":0.0,"score_display":"0.0","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_117d28b5512fedd5597760f4","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6aacd95904ab05d9ed051d7448ef54f3c119ca17aa30ab4512181bf2d40783e4","measurement_key":"8d9b2403fa0f4015ef3e8a7229c3f3db3660cfd34954ed85315390b7034d9587","metric":"eci","protocol_fingerprint":"4cadc4bfe54fc11c813b9c46c5584cf989bb2fcebfe4bcec7cd80ff70e752f1b","run_fingerprint":"920da185d60b0bf1c82c60be27ea0f87912d7220f7950cc2a36d400421463c8d","score":138.2,"score_display":"138.20","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_de4bc2746c30edb0d1633245","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8497a24538b3acf91108a6c1cc132fe22891ad95d6bcc1cf4ec85beeb3d29fb4","measurement_key":"e989364c41cf2fbf2fad358f131dbceef5e257ff6d835a0f3afd0d74508b4db6","metric":"elo","protocol_fingerprint":"99fa32f2d158823ab7e3c18a005a794c66bfa4b940eb6307004a6d2210995c71","run_fingerprint":"202091fd9c66be1cb0cb293b3f3c275a104f7c43ade67cef73cad3d3c8d40a6a","score":-17.25,"score_display":"-17","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_c046a0e96997ecfa1f9b15d9","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":64,"at":"2026-08-28T16:54:57.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9306dc03b93ef652ec0af01630bb56c0b9cdd6825cd0b1c5f58f22bddea7f9eb","measurement_key":"af17c2b19296afe1bbfe110ca78ab0ae7585c1b2edf82c900571cb7dfe530225","metric":"accuracy","protocol_fingerprint":"5b280138ae3a1b4b075a4a4d1589cbfc5ce70e41aaa4f0fa1b5d23f94de2d258","run_fingerprint":"b8901bfcea26f29206029bb1f5287101609e1b44b2899038fa850e6dd0b3ab22","score":53.40909090909091,"score_display":"53.4","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_67bb468286cf106525571e45","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ifbench":{"benchmark_release_id":"release_4adf348ac2f76539ed7ccb10","benchmark_version":"swallow-evaluation-instruct","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-09-30T18:53:19Z","last_confirmed_at":"2026-11-01T03:42:24Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1c7cdf0ea5925ae7ddcbb9cb7dbbececbbcf8d408fa4522200c1eeb4f2aea355","measurement_key":"be330733e279c7207bced0abe1aa6ffd0beade60227abc5cd648ee21a7690a5d","metric":"inst_level_strict_acc","protocol_fingerprint":"6492833b49c17c6db29dd2299cdcda765ec1357b6c689b61d0600cba0e168682","run_fingerprint":"b34adedafb1fde9d3f452badf0b307a7770fc4c905dcecfaa026dcd714a115b0","score":32.300000000000004,"score_display":"32.3","source":{"id":"swallow-llm-leaderboard","name":"Swallow LLM Leaderboard","url":"https://raw.githubusercontent.com/swallow-llm/leaderboard/c58a13a852eba061d639af7caf4ddbdff33b36e3/swallow_leaderboard_post_en.js"},"source_authority_tier":"B","split_or_window":"ifbench-test-300-prompts-344-instructions","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_c046a0e96997ecfa1f9b15d9","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T22:42:57.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1afdfead017cf75066f1cf69e29c5b53215fec31a39b216a0553eaed681d0f4c","measurement_key":"060e8afde39b4b3a3c68135b090849b130924d45efa758a7b9636d1637cb987a","metric":"mean_score","protocol_fingerprint":"82dd0f787fed28a4d341c9c175a630d392f770778c928a6945501cee25d76b47","run_fingerprint":"f800b18d1a8b03cf98ff24407319e3e90d7d34838dc18722c0156b660e51532e","score":25.833333333333336,"score_display":"25.8","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_67bb468286cf106525571e45","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T21:26:51Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bf8084b04648bd59fc95510c6db770dc9a5df917095415464e86e648709fc2af","measurement_key":"c4a077c584acdcc0a8d7e75bdb2ccf9c7e319b656e20a9f6114e8ae35affad8c","metric":"subproblem_accuracy","protocol_fingerprint":"14600173be83f44c993298618540e9f6ba4f2dbd4d19dbdd47f484352f9151ef","run_fingerprint":"b1fc55f0eb78e35c2afd995737d2799e488745bf30b99af8e07a64a8697c5861","score":31.5972222222222,"score_display":"31.6","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f72a9c1ff904f7e8fb9475ac","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"alibaba/qwen3-14b","model_name":"Qwen 3 14B","parameter_count_active":null,"parameter_count_total":14768307200,"provider":"Alibaba","selection_rank":87,"weights_status":"open"},{"cells":{"gpqa-diamond":{"benchmark_release_id":"release_fa97cbc1bde3163225d15751","benchmark_version":"GPQA Diamond","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":104,"at":"2026-07-20","last_confirmed_at":"2026-11-01T03:42:37Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"67c3d42930ed74602bce0f3e6aeb82a997165c83a9f680222b27e4071b4da4c8","measurement_key":"1f13880c531b2feab69f6d641048dad6fdb04ddb13e7ef8514c266f366775665","metric":"accuracy","protocol_fingerprint":"8bb642c88acb255828e2b9b1f8de45d7378e2b4db0e5af2b1f5cc9c54331afa8","run_fingerprint":"8263e40bd6175aec016ada4a40dd3693cdc0838024773b66d3360b42b260f37b","score":78.8,"score_display":"78.8","source":{"id":"gemma4-12b-card","name":"Gemma 4 12B IT official model card","url":"https://huggingface.co/google/gemma-4-12B-it"},"source_authority_tier":"B","split_or_window":"google-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3b514549614b819522b86adb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"hle":{"benchmark_release_id":"release_9b8cd6ba0a835eb2da22bb93","benchmark_version":"HLE","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":104,"at":"2026-07-20","last_confirmed_at":"2026-11-01T03:42:37Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d18c8a8cd0cca8206b37c89c6780e6765d3e737fdeb12375abd7ee6aa3847428","measurement_key":"101ec3034cd1c5260339dfd9d6ecc79414aa76222423c1eda28bd815729eef65","metric":"accuracy","protocol_fingerprint":"c7b0e4330c983c8b61ff308934dd9e46ac24e7b939d101095153586aa5e21a2e","run_fingerprint":"65a5492c7a96153ccf605341e32e1777d82d4e3af9fe4ab26af91fb02872f5af","score":5.2,"score_display":"5.2","source":{"id":"gemma4-12b-card","name":"Gemma 4 12B IT official model card","url":"https://huggingface.co/google/gemma-4-12B-it"},"source_authority_tier":"B","split_or_window":"google-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3b514549614b819522b86adb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"livecodebench":{"benchmark_release_id":"release_1d1cf16bb310d2fb0576bb02","benchmark_version":"v6","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":104,"at":"2026-07-20","last_confirmed_at":"2026-11-01T03:42:37Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cc47b23796a94a95e343fefcfcb69a0d5b2aa87ffdc24c765e18a6fc3456447d","measurement_key":"14319394957ba87dccd92ce4ab34b795d850027a2e3c0c252d0b941f69980f39","metric":"pass@1","protocol_fingerprint":"0b730d9b32134e49951ef8ed8d71eb2e3dae7bc469983e225238f4cef7d267d9","run_fingerprint":"56e72150ed4cc6072c9711350da5acb66bfe7da1b075cd89d887fa7da483cb33","score":72.0,"score_display":"72.0","source":{"id":"gemma4-12b-card","name":"Gemma 4 12B IT official model card","url":"https://huggingface.co/google/gemma-4-12B-it"},"source_authority_tier":"B","split_or_window":"google-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3b514549614b819522b86adb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"mmlu-pro":{"benchmark_release_id":"release_cbef64e634e73d9217bfe565","benchmark_version":"MMLU-Pro","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":104,"at":"2026-07-20","last_confirmed_at":"2026-11-01T03:42:37Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"77500c915baa81e8fac0378c8847e20f2312c0a92e6be77494f87723f84d56b3","measurement_key":"9d45d2ab092c9d74db2fd458d266bcd7c43c95d465961e56a95970f59ef78595","metric":"accuracy","protocol_fingerprint":"701b19bfac3ec0298ae4580dfb7a13feef9ff9e77cd0cb2cdc7e0a0e8c25976c","run_fingerprint":"15d413232dacf9e401f359fb25b4666e595a7d36996e8ef531621ecb52c1cd3e","score":77.2,"score_display":"77.2","source":{"id":"gemma4-12b-card","name":"Gemma 4 12B IT official model card","url":"https://huggingface.co/google/gemma-4-12B-it"},"source_authority_tier":"B","split_or_window":"google-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3b514549614b819522b86adb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"mmmu-pro":{"benchmark_release_id":"release_6f3fd0029277bfcad78a10b3","benchmark_version":"MMMU-Pro","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":104,"at":"2026-07-20","last_confirmed_at":"2026-11-01T03:42:37Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8c846ddbb6c8348543ac851b4b044db6ddbe2f58983bc494b688f2d62e321aad","measurement_key":"4a6b607a11f7efdf4051f6477993440d60303670bbf1917ae312c2a68db76470","metric":"accuracy","protocol_fingerprint":"bb9f70a6a5495741815c8a649fc71037491b19c339ce5782e0a65c139014c769","run_fingerprint":"8c4561873e44e627448e353e0e22d3e9652c4cdbd34908950291d7878e414f90","score":69.1,"score_display":"69.1","source":{"id":"gemma4-12b-card","name":"Gemma 4 12B IT official model card","url":"https://huggingface.co/google/gemma-4-12B-it"},"source_authority_tier":"B","split_or_window":"google-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3b514549614b819522b86adb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"}},"local_open_weight_essential":false,"model_id":"google/gemma-4-12b-it","model_name":"Gemma 4 12B IT","parameter_count_active":null,"parameter_count_total":11950000000,"provider":"Google","selection_rank":88,"weights_status":"open"},{"cells":{"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-06T23:59:25.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"691306ae3fab23ff0110df4ca9c62a279770ef07c7aa05e2084285075d6f5661","measurement_key":"c9d3b15bbc59483181ca7fa36a9358cc3d6a73838266ec9f2ed97265cecb122e","metric":"accuracy","protocol_fingerprint":"a1c40e0218605478104c85e1c23125c3f8ab74131ce10b070928d9226d484a23","run_fingerprint":"612e2c5282a027b331e7612ed465e8c70f185d0a0c66c8567af1365d005f670c","score":73.23232323232324,"score_display":"73.2","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"minimal","profile_id":"profile_bc8fb7aacaacf9a5181ca317","raw_label":"minimal","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_9b8cd6ba0a835eb2da22bb93","benchmark_version":"HLE","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":104,"at":"2026-07-20","last_confirmed_at":"2026-11-01T03:42:37Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4cfc9930b1d7c404ed6d5762b3f3af2f5228e546e778ace5a674dcbd593bff87","measurement_key":"16ad0ebfc09be24d915b146d76a20538d3bc449a99191a3d047269537a7b1997","metric":"accuracy","protocol_fingerprint":"06ac0b5ca9aa6c39ffe98cb437a39fcfcce2acb7262c96bbdc1e654d9cc4bbc0","run_fingerprint":"02d5ef20549391d85a4ec163bbee89739ec5c80cf2bc5017739c3f0e1bee36a9","score":8.7,"score_display":"8.7","source":{"id":"gemma4-26b-a4b-card","name":"Gemma 4 26B A4B IT official model card","url":"https://huggingface.co/google/gemma-4-26B-A4B-it"},"source_authority_tier":"B","split_or_window":"google-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6f7c719dfe08806351b5e839","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"ifbench":{"benchmark_release_id":"release_4adf348ac2f76539ed7ccb10","benchmark_version":"swallow-evaluation-instruct","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":31,"at":"2026-09-30T18:53:19Z","last_confirmed_at":"2026-11-01T03:42:24Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bdcef8a4037ad26843447cdb8142c10cfd48493a506b85d5647dd89769baf493","measurement_key":"6ff4469b2f97f1fb5c6be6d62655585944206815f4fc1593d695659759f24704","metric":"inst_level_strict_acc","protocol_fingerprint":"f55d1bb34adc6d2f246c79d0307e2ab6ee1679c31c3304e9628c0cdc7e169f71","run_fingerprint":"5ebf3111b8bd70382c9189a6fc80a52c24cad87741579f76b3f7437c100b588c","score":72.7,"score_display":"72.7","source":{"id":"swallow-llm-leaderboard","name":"Swallow LLM Leaderboard","url":"https://raw.githubusercontent.com/swallow-llm/leaderboard/c58a13a852eba061d639af7caf4ddbdff33b36e3/swallow_leaderboard_post_en.js"},"source_authority_tier":"B","split_or_window":"ifbench-test-300-prompts-344-instructions","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_15d0ef6dad8ff8c425a50e57","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_1d1cf16bb310d2fb0576bb02","benchmark_version":"v6","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":104,"at":"2026-07-20","last_confirmed_at":"2026-11-01T03:42:37Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a45a3ce9fb128956b56f5cf7a857ed169bd7c6bb501a49150c87e22eb924dbbc","measurement_key":"1dcbcf5c15fa54ec3445bf10d40a40eab32d99cc59c1711b55fa66ea9f0c3862","metric":"pass@1","protocol_fingerprint":"5d31469ed4451daa67379e297cddd9f64424f87add212e1bf0b12450d9b3b79f","run_fingerprint":"13120c5ba16380749a067f7ac080a75d046a91306a339c88986d5c0d14a61c51","score":77.1,"score_display":"77.1","source":{"id":"gemma4-26b-a4b-card","name":"Gemma 4 26B A4B IT official model card","url":"https://huggingface.co/google/gemma-4-26B-A4B-it"},"source_authority_tier":"B","split_or_window":"google-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6f7c719dfe08806351b5e839","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"mmlu-pro":{"benchmark_release_id":"release_cbef64e634e73d9217bfe565","benchmark_version":"MMLU-Pro","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":104,"at":"2026-07-20","last_confirmed_at":"2026-11-01T03:42:37Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7957c91bbd25f5eef424f8f3afce09cc57a5062ba5d640e1681cb4f3579a8360","measurement_key":"dc816e609b4cad4aaa64cd14ab03cccc5d9ce264447bf13adc73e0bb0e62189f","metric":"accuracy","protocol_fingerprint":"a2a0026bdf12f6d0b107ae36753b679cab04abadefa418ed0920e49d04843f0f","run_fingerprint":"84b4cfcca39babd5b69aa7a9cb6ac3b160709d817affe063345ec7428ffe3a58","score":82.6,"score_display":"82.6","source":{"id":"gemma4-26b-a4b-card","name":"Gemma 4 26B A4B IT official model card","url":"https://huggingface.co/google/gemma-4-26B-A4B-it"},"source_authority_tier":"B","split_or_window":"google-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6f7c719dfe08806351b5e839","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"mmmu-pro":{"benchmark_release_id":"release_6f3fd0029277bfcad78a10b3","benchmark_version":"MMMU-Pro","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":104,"at":"2026-07-20","last_confirmed_at":"2026-11-01T03:42:37Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"689a8540de8f3c7a5f0674146ba0f31668a064c5903ecaca16d601bc0d6cf1ed","measurement_key":"0ace1769017fcbfe00e57c112fef4f4fa5c9de6ccb6c1e1792a747489cdca99c","metric":"accuracy","protocol_fingerprint":"6d01ec25a9572f1b2135d4ad993b46c30e87e32cbb3c89a35cf3c019bba2bd3d","run_fingerprint":"149ac26e99ff80e5f298c6f184758c11b986fc881eb925310bf9df892ee98226","score":73.8,"score_display":"73.8","source":{"id":"gemma4-26b-a4b-card","name":"Gemma 4 26B A4B IT official model card","url":"https://huggingface.co/google/gemma-4-26B-A4B-it"},"source_authority_tier":"B","split_or_window":"google-vendor-reported","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6f7c719dfe08806351b5e839","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":64,"at":"2026-08-28T12:55:56.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"956a7d7866d03959fb18dc1538b8607543796abb71c6148ed57da4838435e908","measurement_key":"a18b6f40a4f9f926e67cc0ee39b14237729af16402ffd43df22821202abb9c03","metric":"mean_score","protocol_fingerprint":"e34b79d4bd0fd4a67e6ab3ac50f1df288ff091726118fba383eb00ed5ec197be","run_fingerprint":"984822f592f1958ecb67ab85147675534db13c363a83b8802077f37e3690999b","score":82.22222222222221,"score_display":"82.2","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"minimal","profile_id":"profile_bc8fb7aacaacf9a5181ca317","raw_label":"minimal","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}},"local_open_weight_essential":false,"model_id":"google/gemma-4-26b-a4b-it","model_name":"Gemma 4 26B-A4B IT","parameter_count_active":3800000000,"parameter_count_total":25200000000,"provider":"Google","selection_rank":89,"weights_status":"open"},{"cells":{"aa-intelligence-index":{"benchmark_release_id":"release_c1cd22cc93bbb595b7e3c6f3","benchmark_version":"Artificial Analysis Intelligence Index v5.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T10:53:25Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c3de7b8ca1a567b7398e148f6574c0a09edc508a66f48fa8bfe954c7dc320e9a","measurement_key":"c819b884254149e7a6ee638f743f0a6f5e664f47d355b55c7268fb8bdb7acc44","metric":"index_score","protocol_fingerprint":"2ed15744d2f984a906bfd4d45bafa9ea8325573bcdb72a803752953a712d5de1","run_fingerprint":"bd2c26a05279b976466bd63beb59de5cd400dafb3e6c0e44dad20bd7a88778f0","score":12.910162,"score_display":"12.9","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"intelligence-index-v5-0","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_20eb51e9f88cfd04e5ce2e9d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"55a43d347baba0e8b66db0de0bdd8589df35592f4b8b6a08ef734cf2b57ac89f","measurement_key":"a4c61865d46a04a470e63f7ab9de3038b8d17c221c0a12908d0774a566990619","metric":"pass_at_2_accuracy","protocol_fingerprint":"b23c7b89a7b59a9f38b93fdb7965b185db7bf5d22ddf0951429c283f83756fae","run_fingerprint":"f991f89d449f430276429e1c89defe5c7fb989c747084d33a287642ca7de73da","score":84.0,"score_display":"84.0","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_11897b7e05ae3b489552bf1b","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fd2ffa704695bec3ee000edc6a070e245993d98147542773ca8b77127aecf039","measurement_key":"674039bcdc1a451fe1b4f43e77bbb6f7995cdd2b152cc47093850e8c170485ec","metric":"accuracy","protocol_fingerprint":"f1c08ad01e5310c4d0aa22562f56e8ff60f51fd82895da2534adea920bcc71c5","run_fingerprint":"6a3fdbb035c6f4bdfc703192088ebf4543574902a5083f0c6b9de6ddba89b303","score":40.138888888888886,"score_display":"40","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_11897b7e05ae3b489552bf1b","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-agent":{"benchmark_release_id":"release_7d8f719478c55b93fbf0585e","benchmark_version":"2026-10-28","comparison_lane":"source-specific","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7fe834bae68a47013070f025b893518e5be28b22f49878e27e4060a64bdf404b","measurement_key":"18a4e1093a9120469541ddb93fc2406cd84642d4188d02a2b8bb662c13a825f5","metric":"ips_score","protocol_fingerprint":"b2a02e9a9bd2c163c3cd1fea8cf66291a9f8b24cc004173e5ab19155e294c0be","run_fingerprint":"1f5c234b174492be761d1998ea7ec317606b7d1d6ff656ee0b4ecce8a673a130","score":-0.17010177604397714,"score_display":"-0.1701","source":{"id":"arena-agent","name":"LMArena Agent Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/agent/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-ips-aggregate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9487927c8b4ab32b43e1f141","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"ips","verification_status":"official-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"46537e998deb3080e7bf79bfe42035e02a328311c3a73cdf600c1eb84f5a429d","measurement_key":"75653e910f59f5a7794f85e8c8e8844b28109c747fcc37ba71da995c31cf9d04","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"5f4430875bade41b3cd464e25813a44ac8ad20889db4985f572fe36052e6b67b","score":1405.5220424213123,"score_display":"1406","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9afb89ae1ce26b5639d73387","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"24a8fdb723dde086ac7598dc35681f44cd920039422bcd93c9a63c77a241d569","measurement_key":"4a08d0c7b00d69fcd5864bde1decc7b8cef53e735051feafb9215b42b1f9aa3b","metric":"accuracy","protocol_fingerprint":"057f0d50f46701d2e33e77c0d7fb81654a0fc92fe0ab67133a18d8fa4479c4af","run_fingerprint":"944d910124e7e3966227d67d0b7928e262c858d292c86a91427ae12b4e250e75","score":8.285714,"score_display":"8.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_20eb51e9f88cfd04e5ce2e9d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"184209afa681e9bb5651a92f15daf437c4d8a8a5d95c06678217f7d11350cdc0","measurement_key":"3efc689883b5ad45c53fef08d1e0dbf59c035f1febb904611bf07b1fd4718a70","metric":"eci","protocol_fingerprint":"f21e6df7bf1044455256ced8c3ed6d506e3759d6ae79a744c9e5420acb8698ab","run_fingerprint":"0f566a7fffe682c87272012061d3a7391a91efacd3bc7113ef84b9e2aec06160","score":150.46,"score_display":"150.46","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_16db478ee7ae220f4d066083","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":78,"at":"2026-08-14T19:59:09.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3c55539942bd956465ab01ea93ef2733e89b60d6d52b4a5f6463b95a06128279","measurement_key":"2027f52cf0be86ad750783f289b2827009cd38beec80984399af55437ef7671e","metric":"mean_score","protocol_fingerprint":"1175a744640d4a5c8c5837b22e5668b81b7454a29aca4cbd40a878a02f6aff48","run_fingerprint":"acdf7419e13b15645bb5757240ae8785217a1870730cfc1ae4473338dc4caf1e","score":46.31578947368421,"score_display":"46.3","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_11897b7e05ae3b489552bf1b","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":78,"at":"2026-08-14T19:59:09.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9360b80d988e91b0bd6e9b89ea36598c26cdec3828bf4602e1f9d31b9a87c845","measurement_key":"f767416e5ca54353f8a4a041e769e0dfe87673a3b74fe00d46882d49dd799084","metric":"mean_score","protocol_fingerprint":"8a4e42c5a1b8e6bf5f6c5dbb9c7133e83186afc175e7a112a74935b3030c4f51","run_fingerprint":"7f1b1e9202b27f97d0386b43279e377df953efb8f15c9d1db91897d24ae0ab4d","score":17.073170731707318,"score_display":"17.1","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_11897b7e05ae3b489552bf1b","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2884f07c2d98d5fe0baca1d650b351137dfdb4c7daac4cd6bb2d3fff30de51fc","measurement_key":"7a4a6c73963452182cd7ae84d9af39d215448a0f2f0f56ce6e76e07282d42e4a","metric":"elo","protocol_fingerprint":"160924b0df04a32838bf5f5b4bb87eaa317a9eeeacfae44f8336c34ec4be552c","run_fingerprint":"8e7b220e390d5e52cdd7a4c00e0e5598a80403f93b394626a99a924355610c68","score":1132.56,"score_display":"1133","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_20eb51e9f88cfd04e5ce2e9d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"710291b8cf7860f9d4610e1658c5359abb8dc7f7f24211f21ab83c220e4ec962","measurement_key":"7d9170e9120fa9728b6235da635522517331e2ebcf8a4a11b1cb42a339c36e42","metric":"accuracy","protocol_fingerprint":"b4e40cd174a8badf46e20b26e1810dd03fb5514adfbe5d2c780c768418782efa","run_fingerprint":"0835a475ee249273c8e4a92554f5995d1fad29fbedb197e29264945b021bff5d","score":83.586,"score_display":"83.59","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e7221fcbe0df2d3f97b361b4","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_fa9e908ac04b067eb00182d4","benchmark_version":"HLE official leaderboard","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":8,"at":"2026-10-23T21:21:02Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"09c331e89f7d2cbc19db734f2117734ee334cad0c22742500cdb3d9816de6769","measurement_key":"a825395fda5b7f133f99f2bd7419e30cd786049d10293bb5b80093e270a0d84e","metric":"accuracy","protocol_fingerprint":"ace1ba8ee6ddec70890eafd20d98cb24e8cc615fe1b0f5899e8549c87453e562","run_fingerprint":"1994683afa46673c48d1181a83f144d13047321b137011a89f26e26010b7ce2e","score":31.6,"score_display":"31.6","source":{"id":"hle","name":"Humanity's Last Exam","url":"https://huggingface.co/api/datasets/cais/hle/leaderboard?limit=200"},"source_authority_tier":"A","split_or_window":"published-leaderboard","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d2b3708222c5ac4dd0dbf632","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"C","evidence_rank":5,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"self-reported","verified_status":"self-reported"},"unit":"percent","verification_status":"self-reported"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cfa1def513b2409506a4d7346fab88b5e5bc36db651ddae62ff506993cba9376","measurement_key":"a358e4af28414a12664786f770768028d9267bc3462340dd006d92051f895b85","metric":"accuracy","protocol_fingerprint":"1b28dab1a1a430aa0e5ed2ea185cde86e3d2be3b91d72a14f3efd94953e40fca","run_fingerprint":"8e71f13fd1a0d250249e9b3074c5d25d38f637d9a71e4ec7a7039b70965c0729","score":33.317887,"score_display":"33.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_20eb51e9f88cfd04e5ce2e9d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"ioi":{"benchmark_release_id":"release_e9a397f5dc7f7ff80be0a322","benchmark_version":"Vals IOI v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fed8b5a8afe3c669d323e9c4560745cc0498fb05c0502fff490c8863a7e3e9fe","measurement_key":"e5f58fd2236e7763a65664943bdfc9beaaadfe3db432ed8e695166415c3409bd","metric":"score","protocol_fingerprint":"c7fc7ea5ca742d26b71ac37e76c415e45b367b43a4fd4a342a4cf757b70c7d73","run_fingerprint":"70d3c0bbc193bd96c09a62150878283b6f1a5f36c7121918d05e95b50e2f4647","score":9.333,"score_display":"9.3","source":{"id":"vals-ioi","name":"Vals AI · IOI","url":"https://www.vals.ai/benchmarks/ioi"},"source_authority_tier":"B","split_or_window":"vals-ioi-2024-2026-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_dd301f51b56b79061d8b85c8","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"29bbb351dda5ce6409f95629668a151af52e580186616a8b075a659c24b0df9d","measurement_key":"e6123084ad9a85520f2d9df90204cba20de25cb4120dedfca4fc57a4dea15789","metric":"pass_at_1","protocol_fingerprint":"5908a331e7fff5448ab4dfd47c9906598a798b61151b8726e4d43e0ee056b7a2","run_fingerprint":"af8d5cc203876c3e8e99591aea80c5986d9c4e477425c6630324e95030a8f54a","score":85.931,"score_display":"85.9","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e7bf88fa29d99292354422f8","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":93,"at":"2026-07-30T19:17:22Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"835f74ff996d53cbb22a27a16d39705d2e3743a970c12dca747d350bc4e81935","measurement_key":"400549375e08b6487723fedcfda77c4865c0e7afceab0a3a39fc4f45130145b0","metric":"pass_rate","protocol_fingerprint":"26ab4b1c4e8cadd2cea7040524808a410c6fcd380c3ed939d31e923b42466cb0","run_fingerprint":"9a5cd7108b71669923f562ea1615aa80242254d4b1d533b36af17ffc687a465a","score":79.2,"score_display":"79.2","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_318b9d51698a9143a85074a8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dbfdf6fa117988b7305e64080f13896b0d47ad8b1c0262ff7e649d1d3d64e2c1","measurement_key":"840b9eb753d4b1dae876ef30822e87c1976105a928e00ea3c25a9b75c1efb580","metric":"accuracy","protocol_fingerprint":"79eb70b78262259dbf59d93e79b296bd094bd31d0f8cb5dae3362b0f394979f4","run_fingerprint":"09a4ddd5c6cb9b6f9e8210c233c2b836000e54d060cf3d2af70efd5319f2194d","score":85.566,"score_display":"85.6","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4afb8d94c07f2a4577e683fa","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d8aef58a30e3f8647d08b4a09eefcd5e5816aacc2f2c8623d130accd3a44ad79","measurement_key":"30d48f62a6227aa5eff1a218628b40225acd85a1a9a32ce55b8304e2a7a63fc9","metric":"accuracy","protocol_fingerprint":"fe7a06af4072ada5e73d091112397576edd5b505c7eb7f17e938be8883165d4b","run_fingerprint":"c3c12678fe5c75076eeaa61f51888210044a511312decbb19f0f22aba63369de","score":74.046243,"score_display":"74.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_20eb51e9f88cfd04e5ce2e9d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":78,"at":"2026-08-14T14:19:47.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"862f340b771080696b2bb00611bdd0885dff9b3706e26104beff2c3c79715d96","measurement_key":"ff0fbd3c716dc34918c806d675bc201ea429d5a2e9ce516b8cb2063ff87dc9de","metric":"mean_score","protocol_fingerprint":"5ba7da82e26519352aaaa2731865202ebb0ad36f685e72035b623886ce822905","run_fingerprint":"d0ca8f22660cd4586e2ecf98a914d737760bc1f9b9fd5325459f8a8dd5a24dfd","score":90.0,"score_display":"90.0","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_11897b7e05ae3b489552bf1b","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"262fb50bf303095582c9651b5027714a318cec1fe40e0e2a426c207619b2236b","measurement_key":"931b8450486faf33756a051a489c13df45cb061e3cca59c793341de9f9b938a1","metric":"fully_resolved_rate","protocol_fingerprint":"dbe63254234b16431309b2a726973637f4b012dc4e9cf08b25d861965d3deb2e","run_fingerprint":"2072f473a5597048b3ceb70726364323057c9b9649d23bbeac4c9df3106d0470","score":0.5,"score_display":"0.5","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a4f343eeab832539cf337101","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bf9dab9475f01d92f0b20b6a1dad3c3892ec68420f80fd1937e760e2de836f57","measurement_key":"f8ffd7918c495f0f4121fa4565ce048ab9da3e62c7fc853e57584fce46ca6ecd","metric":"subproblem_accuracy","protocol_fingerprint":"f0903fc29e56ecd3275b78d6d34d7b354f54d7774c9a741193679cf523544919","run_fingerprint":"94649923025f12a9518edfe452268738fce0ec650aa62ff330720f6ee683e473","score":49.6527777777778,"score_display":"49.7","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_5ef7626ca399657d16aa77c6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:36:17.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f251d79a001dfa252f7d162fe4d54450457740baf4fb28ee338cd6321be10d9d","measurement_key":"8246e7c57e6354ab4731f5c8838496f09350906c67dcc10003c146cef7483602","metric":"accuracy","protocol_fingerprint":"233a1f4e148821f06ce49380fe8bc1814d008506ed8870d14305ed38a37e8dc6","run_fingerprint":"e4b4b55b1c4a8787dd0ed9c78c2cf1a52cae3b719aba48e1ff7438ca1b10c6f0","score":19.1,"score_display":"19.1","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_11897b7e05ae3b489552bf1b","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3b77ce662616620e9c6a032a0724d50774d7095f5f810955a6db9182ebec2808","measurement_key":"cfb931151d0e72f22bd314ac7db9345d2abe714ed839481a3cd87e6e87a52670","metric":"resolved_rate","protocol_fingerprint":"fab4fc70e27554b8de56bb649d0feb76a74eeb75cda84a66163688c988a397eb","run_fingerprint":"b26533c2ec49f018c04fba36a7e6ced76b5293a09f63c6dd4603d9f10cf88850","score":82.2,"score_display":"82.2","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_703781bfe8a825dd1e4f60a3","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3b77ce662616620e9c6a032a0724d50774d7095f5f810955a6db9182ebec2808","measurement_key":"cfb931151d0e72f22bd314ac7db9345d2abe714ed839481a3cd87e6e87a52670","metric":"resolved_rate","protocol_fingerprint":"fab4fc70e27554b8de56bb649d0feb76a74eeb75cda84a66163688c988a397eb","reporting_origin":"organizer","run_fingerprint":"b26533c2ec49f018c04fba36a7e6ced76b5293a09f63c6dd4603d9f10cf88850","score":82.2,"score_display":"82.2","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_703781bfe8a825dd1e4f60a3","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bfa4d297b930b6b6f00d2421b98a91be6bc0fd91564543c2e357e7bea94ed9f1","measurement_key":"872cd44bac603a8144fec5d2f006e28ebdca8c1953ce4b73c0cbc5a8672e6d55","metric":"pass_at_1","protocol_fingerprint":"6bca21909196ef9b1bc2254f2a5b35d7288ac76ea0b8682752a2e683e92a3520","run_fingerprint":"de3d5c152a0f163f7b25700294fa1628c7af66ea8de67d4edd37eb988c0e9f5f","score":18.762887,"score_display":"18.8","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_20eb51e9f88cfd04e5ce2e9d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9904a4950829dd35162b59c6e7dbf77d498879279e3a2839e1575777af89eb30","measurement_key":"384d6e4c73804e3ec7c95ab0225b877e5e43e9a7cb77ead86090c58a987ab231","metric":"accuracy","protocol_fingerprint":"50d5b67ce1f30bb532f62334f5c2967061a39634a3df5e532823bd42bd7801af","run_fingerprint":"0dba9f1ce633c6619848b20894567a8d831e6022a6bfe1ccf44e2a7a98de7229","score":55.056,"score_display":"55.1","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_629f3e62b174a633d2359fb4","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_d944507cc6b610fbbf6eb832","benchmark_version":"Vals Terminal-Bench 4.0 v4.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:14Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9a42581b5d16ecb7556855d8a550104ba89dd1794ebcd49de191e57f7aac2cd2","measurement_key":"2b6fd6ab89b881473656cbf2f9ba8f8f33a46393a318b774e5c4dd6e4e2bd261","metric":"accuracy","protocol_fingerprint":"5807ef6f33eab5251c77fc6b4c30f3bb7faf37df4949a812ec4889ac489272d7","run_fingerprint":"f72cc14e10264ad2d804d4a6cfa44d5259906a43266a9b7454998ee16b7e3f55","score":0.0,"score_display":"0.0","source":{"id":"vals-terminal-bench-4","name":"Vals AI · Terminal-Bench 4.0","url":"https://www.vals.ai/benchmarks/terminal-bench-4"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-4-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_71890960f4f5938a7741e052","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"683d4ec649b5c8dd59da94c237715465485f86464acf1ea76b19d7f3d37bb0b9","measurement_key":"a60a62fbb7a4771a4ab776c9caa0484a5b5608438b59ff81f7ca06efe0255297","metric":"score","protocol_fingerprint":"25d75f6996e99bf80763cf17a190c08520df25c0829c3695e4662c128b073620","run_fingerprint":"d023213ecf3ac148545daa0c9ee76728e822d61747daa7c5d07e2ca429ed13dc","score":19.052,"score_display":"19.1","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1a5020ecdcfbe5f23617785d","raw_label":"0.99","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"706acc7a1074d29510952fbb2a57d999238f767ac2a5cd0a4b05ecaee36cd9ab","measurement_key":"58f8934b37db364989bd0a605374e058e7ed91fb1cf0cf33ad89b91178e57acd","metric":"arena_score","protocol_fingerprint":"7bc13f86b676cd657a6a1bbe561c8fd3d20a00d987266c3c3fe6c424a8d93172","run_fingerprint":"6be81d75ca36c070685854ab414620cfc24b1cf82e83075f994e33cf24be9e46","score":1409.1376517895078,"score_display":"1409","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_13830015e96667e4be7dbbf9","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"thinking-machines/inkling-small","model_name":"Inkling Small","parameter_count_active":12000000000,"parameter_count_total":276000000000,"provider":"Thinking Machines Lab","selection_rank":90,"weights_status":"open"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5e669305c42d4e329531a630504c3bb2a9e777b6754ea185e9cbc2a934aad873","measurement_key":"94f65dc2e0e01fc22ce785e57281041175194b64def80ce74d46d82341b61e0b","metric":"performance_rating","protocol_fingerprint":"860d50f7d2ce508d6a774bf679003e9580848eac4e86b958ad49d04a68a96675","run_fingerprint":"531f54234feb8424c7d322ea443e1c81b2a1a1f3b65152ab6e2de9c3c173159f","score":821.65,"score_display":"821.65","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4a115fb2a00cd4c6610fdf9c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bce36270835b9e565ec1f01f90a613cc3a44e0b4e2651667f6870e83ee7f388a","measurement_key":"aa925458bd4e0585fd42696a1e946c0cf568e927e7c0452c945c92d8cc90756d","metric":"pass_at_2_accuracy","protocol_fingerprint":"cc43816fd6d881f3b38fb823a89342968180109a116a45d9f4de815ec4d9cf15","run_fingerprint":"dd7b161deb464e517c56fe5b5e048573b9a1b3fe075fc1fdce358ef8a905ebd2","score":65.33,"score_display":"65.3","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a605b31119223a617f1c6466","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"de92e702186834573601a58dd39024401df3f2e3b2784efaf13ae9bed02e6f3d","measurement_key":"47db917e5a4f9e2e720549b022bc62589e4c68975a635f3c648aced20dec0efa","metric":"accuracy","protocol_fingerprint":"d2f5a5a3807c2d47e07c18d7540fe3125ac78f0374c963dd93a0a538bb54bb38","run_fingerprint":"ebcd5666ae1d0c53b61aba5581361536f38f768b402706ae48edc21a3faba355","score":11.81,"score_display":"12","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_5231d77a85df897c20d6ce6e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6502ba4562588d3ab2ff7e3de5d356471ed46f0c7dfe61ae977a46971198e9e0","measurement_key":"9f1acc85843aae2ed67292df5e9303888f1e6ad753d941b72a74f102bc162ef3","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"95e65031829995a84133ca0f058f6375a7839b3317f6dba276f7ff1a1845dbea","score":1449.746776109821,"score_display":"1450","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_6ae6ce92018cc9651626b3ec","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:41Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"424f5358b9cd934b7441a5a75f8b0f66f1c2e2c94c41331a6341899ca1d9f0ee","measurement_key":"4c24ee055fbffb1741f1e9c9a1666a4a6df7505934491f4e597f4e44c183c987","metric":"accuracy","protocol_fingerprint":"d54638f4ca45fb6c067f5ce4c9ba2dd1e3cfac45b51ddfe7af5014674c9ecbb5","run_fingerprint":"9b71e82ddfc4af314a95e159eb08a0d73fc8eb6abb6d1f2ae211e4ba697c88b0","score":3.14285714285714,"score_display":"3.1","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3274c202f27b162a812bd5b0","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9f278d67466b29dcbf537ed55fb73251abd68f423f3873b6317668de26996693","measurement_key":"f80c4a5590d5e7cafee50c7169d8e8725f31ca84a67ed5cbd580cac7fcf2c833","metric":"eci","protocol_fingerprint":"e57dd7cbb950e5797f9f0fe81ab5be952e8ecdb43f3bb637edc01d37a63a3959","run_fingerprint":"d9e723dc1b629fdcc8234c5d530970aa5afbc5e5432cf0630ed9b415fabd289f","score":148.11,"score_display":"148.11","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_319ef04e6ebcddf6677b39cd","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"df62ac856b75803896ee538cec1ecf384b59e37271a0cb66cc0d93b521e313c2","measurement_key":"b91135ad16a907e57f85581896525eb37b12317daedf5b0d39c4973dd74f4e6a","metric":"elo","protocol_fingerprint":"a67ad4ed32c6284b0f077084f97c8e710bb6286bc434a416e8bde92edfac81cf","run_fingerprint":"e293713c57826e5cd3a1e21a04422b14dcca8e5a7960b865f3a334f8c650c74d","score":846.64,"score_display":"847","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_6ae6ce92018cc9651626b3ec","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fc648ecf67ee1be770a0f96cb74df0105bb74cad8cfd30ae3c9d7068ed7f31dc","measurement_key":"1c7cfde023bd8aaec8dd36c152cfed6224868cebf224e7f0a62dbb17dcac4291","metric":"accuracy","protocol_fingerprint":"423d01a485c271876c1915edbf0abe3ca359455ecc1eddebed52ea6de97eb299","run_fingerprint":"9fa688da9f8f5ed3b6b6c02894d00e6b664e7290b51fc2a5ff6ac09828b43ad9","score":84.091,"score_display":"84.09","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_6ae6ce92018cc9651626b3ec","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_8817af9d9a0235bce0826e22","benchmark_version":"HLE finalized 2,500 · Scale protocol 2025-04-03","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":260,"at":"2026-02-13T14:32:29Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"86bf32b440da394bdf5389da39db825adc3331991f341fe5293d5014ace05a0d","measurement_key":"83c8926e9614129ddbb42f064bbca6542e05797aa4fc11c7e98124c692dc92b5","metric":"accuracy","protocol_fingerprint":"6db70fd2943965952ae5b0bd64daaf0d7150dd757c24d6f2f8202ade570a1dc3","run_fingerprint":"2e850e7ed70441be8b812d73b0301841a31cc7acf05b31456a4b15d845912595","score":24.37,"score_display":"24.37","source":{"id":"scale-hle","name":"Scale AI Labs · Humanity's Last Exam Full","url":"https://labs.scale.com/leaderboard/humanitys_last_exam"},"source_authority_tier":"A+","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a22fc3d76219aa5ad672fcbb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"992b37e67975297b06468c6e9ce6f766ccf10eaf5742fdb8c0e1269b6b082b90","measurement_key":"dbe2e50c149aee047df4e804e75d06a35e09a54fd178a4499c97bdbe707f8fc3","metric":"pass_at_1","protocol_fingerprint":"2af08ef4db534aedceaad55ef487e6530a8d7db766b9491fc248b5d9cbd288a7","run_fingerprint":"b6fb3f0f2d85630c92051c15505df2e7f468c7e5a275fa248d90758ada0e6806","score":83.868,"score_display":"83.9","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_6ae6ce92018cc9651626b3ec","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"688702f41eda54165b2e871f54106b358a0c601953e7338623dcebd5bd940f15","measurement_key":"35481d169ac2bdd510bc604188101bf34fc66cf1b9a6e409a5cd4098ca41e1be","metric":"accuracy","protocol_fingerprint":"97e9a5836bd57f0f1eba1091596dd1c3a3974f9f73de6bf4cbd43fd15c1ca3c3","run_fingerprint":"1a3b39cf7c97fc9328d3297f47f2cfe9a2dd3916845523b1aad659d9e55d6dd5","score":85.914,"score_display":"85.9","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_6ae6ce92018cc9651626b3ec","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:41Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4ed87390b66f6b9d630ef32cc517ae9c792d9456c661c0e4751243ac235b8da0","measurement_key":"98d54126dd9bc7fd59b9eeeba99fdf0619f1ab00a7d4c2cd9fbdaf96f7f0fe26","metric":"accuracy","protocol_fingerprint":"9143580b75a90983f666093f3cbc153429479f600899d32e509199afd95eb35a","run_fingerprint":"131e449c81fe0ac9f4246d63c2b3ed434b11a20f6c0c5c3b9f01cd1274c9cf89","score":84.335,"score_display":"84.3","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_6ae6ce92018cc9651626b3ec","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":271,"at":"2026-02-02T10:53:14.986Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"919b3cea001418242d59467bddb96b27f516debd934379ac16f1351816ee3b6a","measurement_key":"4096676b0bd51afa7792fe3fb30b093f2336a80fe33f01500d31e5edadf5b44d","metric":"mean_score","protocol_fingerprint":"53b5afd59ed2fcc1bea62c05d6126c9965d6161c4095ab8a5398b2b254a04a9f","run_fingerprint":"ed9a5daceebca5335ac9cf309bc8921076e7be01636f9efe832a13ce6a42395c","score":92.2,"score_display":"92.2","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_04028ed53a8f5ae82875593a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:47:54Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a40a91379dca063e09e6afa1d513f8aebc0c0d4c520cce77fa8b22ed69319f36","measurement_key":"27a1018793753ae555f49d8d18a85eabd51746922632e32d45905eedd7b18463","metric":"subproblem_accuracy","protocol_fingerprint":"9a751ce3717bf2e8fcd5e6795198ab13ebf865224c830224359510696dd32fa7","run_fingerprint":"579c7d0908c30a1369ec3f2e20e833bcf0f4feef7f56d7372e3541d00d936d56","score":48.9583333333333,"score_display":"49.0","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1307685283e08685791dd3b9","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ba76bb771a11466d19a080d2d32495484f5a3190ff1e79306136a6d96f00c537","measurement_key":"4dd162bda8de5e663829ee81333bde6e31accae0cd8b71d2800ce7c9db6e39e9","metric":"accuracy_avg_at_5","protocol_fingerprint":"56f2ca3e622b4d4d099aec16d36c9c43e7e45524034c416dc2bb838c50d8990e","run_fingerprint":"652867cc1c8aa4baf1b9ba1cd58cda5005b8195d16e081b0c6df3ea7361241a1","score":46.8,"score_display":"46.8","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_cdd77eeb27e64fe682104bb2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:35:45.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c50f4133e34cf346498948b130308fc8022b86ed1e86af1548e9952a9fbf851b","measurement_key":"f60a3870dc599c9a11817de888757ac13fd1b04f9b34aa974a37910f697b7b3b","metric":"accuracy","protocol_fingerprint":"9b27a207e2a514be653bf3478a54786b2e28f6a37c4d6332e9e947a6618acd03","run_fingerprint":"f8a3858077fab309f8086e27150189245ffbaf7067eac5c3e766a7ce7bd9d473","score":34.300000000000004,"score_display":"34.3","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7aaddd2f0cc6c1a8ff26df64","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"72522dd24c6d25ec39a4dfe4309f6ad90ed7ce6949081a535584e925af757126","measurement_key":"905bbdba17d6aece0ead57013b3387c70421d66e766c7f783ea43186a579e0f7","metric":"resolved_rate","protocol_fingerprint":"3aeeedd7aaf29a157ada175202d53fa3db6e75153173f3a290265a0bc18cb6eb","run_fingerprint":"c1231cae401dd9744d098e470bdeba618e54c73e83d1275fb12a804cfc0d25ef","score":70.0,"score_display":"70.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_6ae6ce92018cc9651626b3ec","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"72522dd24c6d25ec39a4dfe4309f6ad90ed7ce6949081a535584e925af757126","measurement_key":"905bbdba17d6aece0ead57013b3387c70421d66e766c7f783ea43186a579e0f7","metric":"resolved_rate","protocol_fingerprint":"3aeeedd7aaf29a157ada175202d53fa3db6e75153173f3a290265a0bc18cb6eb","reporting_origin":"organizer","run_fingerprint":"c1231cae401dd9744d098e470bdeba618e54c73e83d1275fb12a804cfc0d25ef","score":70.0,"score_display":"70.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_6ae6ce92018cc9651626b3ec","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_2125f5e1cd1e1b1aa6168fb5","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":245,"at":"2026-03-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"4d9ea716c84dbaaa7a43d5a830adfccf8586f5538ea064bcd73c7464cb7e5630","measurement_key":"ef16d2bfbbeec45376d033d47691707166de631579fb89d70a6f188cbe01d70e","metric":"resolved_rate","protocol_fingerprint":"141d7a694df4e1ca70e967074cda149ad778755d6ce8798e08f8a094860fec90","run_fingerprint":"5ebda0432145016aaefc28405cad973ad75bfa27af6115b9d4d89ca511b2c057","score":58.452380952380956,"score_display":"58.45","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-02-01/2026-03-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_025533521cd219b3ae285dd7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e9e1b1875a980a50790aef4b7bd3a16816d7485ebddbb99314e79934d41d738b","measurement_key":"2f9a5522be3a505371e46f13e37316dbdcef959f213b6c32809d6d501139c279","metric":"accuracy","protocol_fingerprint":"05d83f9558f680b0715f571eafc49a45ac79be2670a2c6021b6d03ba4920b20f","run_fingerprint":"07974584d555a6f1248a9c191677f54a12662acc57cec0657f81819e8ae78a8f","score":41.948,"score_display":"41.9","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_6ae6ce92018cc9651626b3ec","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bebed54504a4ec3a55ef290bbbed321961f946604ffecf82de8bead4a97c7b70","measurement_key":"7a09ae85974eb1901824ed06dacddd5dbd929ce2b6c6f8f334e6c49a1aaf329f","metric":"mean_final_balance_usd","protocol_fingerprint":"ceb47379ebb944853a74277a42f187b11105aff2cab403497864f58f2829b934","run_fingerprint":"008d81ed10abf19df9bf1d6c087c6d8709c217540b467f46cea6cb31cf143201","score":1198.4579999999999,"score_display":"1198.46","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c40dc6af044b94a7c275bc96","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f589efc0e39e68b102cf22e0070190bca353284320635917d4aa5a1e44834db9","measurement_key":"4eed55b77a0e291c2481a38e28cebc59696d4a3dbc793c312551da23fbbc5405","metric":"score","protocol_fingerprint":"25b79921a5da4317f38186d40d9c1876794606d48cab970584ec97391d864284","run_fingerprint":"1b475729c12a6f6acd36647318b8c478dfa67352e47e075875a8cc5e04cb32dd","score":17.536,"score_display":"17.5","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_6ae6ce92018cc9651626b3ec","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"efbd786303f6ebd8d02c01f8faf3973c49fbae4a773d311fad2b27b321df4c10","measurement_key":"60b2964c7c726b9b83bb624ddf8a7821772a27d6bfa7a82385ad7c131b8a4629","metric":"arena_score","protocol_fingerprint":"919b8d94f2472f2879c56026df59729b35ab43c62f1c3e55773886879416c02d","run_fingerprint":"b2f49ba2077ca3f96f045d25772fee110bcefc191b71d78d9ce8431745351d1b","score":1436.2450288272603,"score_display":"1436","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_6ae6ce92018cc9651626b3ec","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c9e50fffd268058791314f53e802a757246f18714f364d5a730016e4f978fc47","measurement_key":"ab9aae84dc91962c2712137b537c20836ea343f5d45bdbce47cf4e7f4f53927e","metric":"accuracy","protocol_fingerprint":"944c42581b9cf19afddbc0b18f843bea0572518f388d8eba131a1bd77f675dfb","run_fingerprint":"2599b340f53510b657e070b78c5518f17199a0fa6c3955657ed9afef5f17ff0e","score":45.6,"score_display":"45.6","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4ba684af8be038b2c7303841","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"moonshot/kimi-k2-5","model_name":"Kimi K2.5","parameter_count_active":32000000000,"parameter_count_total":1000000000000,"provider":"Moonshot AI","selection_rank":91,"weights_status":"open"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"14642ae646028eede1ab351078b4cc6f987ddc3cedb24ada6d3c583abb71753e","measurement_key":"88de9f99ce6d0a34d5c63c4a11788c5bb14c40711253bcfef77e0325dc3f3359","metric":"performance_rating","protocol_fingerprint":"e08b8bef922d2365af23dc1a66a5964759321622b95ad38de5d62684f7c89410","run_fingerprint":"8a250df5e71b7871cef738921f76558072fe71b1d7fd74135d101823745ac660","score":886.23,"score_display":"886.23","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_623f2c3e7cb74eeabc3b0ea1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9f6769abba3f7bbaabe5c61215d2ae11c719ca8d1a15c693de3e1c7c0e312563","measurement_key":"0db715c8586d601ca97e3aed23963bf87e9ad2dedd49e5686fd4745c3d219469","metric":"pass_at_1","protocol_fingerprint":"c9debe73032802fb9ce488d44f09b424ff97a76151b7b4146ddb59958b243b4a","run_fingerprint":"97a6785fd637d46b40f6d69f4e3deb6fc82d635bf7fe000eccbfca90c8d12d75","score":37.6,"score_display":"37.6","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_099c0ba8b21819b771db4fc6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T17:13:43.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4e020953e924182ba85a7f06e1a89f5537070480cd016026c5ad56abf67f57b6","measurement_key":"5739837d879b72e18397a18e70a82af68b803d8b12a8c6a133f68bad333b6638","metric":"mean_score","protocol_fingerprint":"cfe739535319190b76841d0eb8b10e35fb5ebdff216eb6496017cfdbed8cabb1","run_fingerprint":"264432ba8c0d7a57581d823aa86cf6453d1e74ef916abf5155b2bb52c2bce66a","score":14.000000000000002,"score_display":"14.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a5fda2880c2096a50b322ade","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c73062a96f3409f114aaae3d8c7842c662176932334102ad1491f383a798a877","measurement_key":"2f06e89768faa227c69f3cda671e28dbc990c1bb5012689f9defcbce37de9018","metric":"accuracy","protocol_fingerprint":"2528582e78dc47e9aae05644e86a22532b5609720f64082a54e09642fc3a5633","run_fingerprint":"868140a783dcea3332e634fc766749a40baa73b9bb67297c8587901ea17bbd89","score":10.0,"score_display":"10.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c418354814777762766b7183","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"deepswe":{"benchmark_release_id":"release_4731f79a89e61b8ad678b622","benchmark_version":"DeepSWE v1.1 live leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":63,"at":"2026-08-29T23:52:22Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"848afee5ef88db978248d9efbcc83b4123d280b45f5665d0648c0c8e0fee7524","measurement_key":"3c12dc737fe6a5c5d21e47d238aa38e59ebf6517a3b295be5de65b071e46cbf6","metric":"pass_at_1","protocol_fingerprint":"779874d29535932d55ae2983cd4c98afc7144b8b4301e0a615e94f526da87de2","run_fingerprint":"c1e8cbed9a32399d6f611ef470ec52cffae1aadc3aeeff2ffd6eceee9ed501d3","score":30.53097345132743,"score_display":"30.5","source":{"id":"deepswe","name":"DeepSWE official live leaderboard","url":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json"},"source_authority_tier":"A+","split_or_window":"113-original-long-horizon-tasks","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1d6cf902dce1551711bea365","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"deacdc5e90df2de94feef9387ff08df26de1c04b21c183e63c23d5c2e2d0e21b","measurement_key":"eae0f3c7615e712d928cb11729fbd4f0f9e5fcd3205181e53df33abde537e3b5","metric":"eci","protocol_fingerprint":"0522a423c124834e0a23595e46e5eb07c3d85add8e954dc06c03db7ffe976938","run_fingerprint":"edaa87f5398456f3a94ac2503b7a2226de4e7c1aeb8d9d01a7250a250b6abe4e","score":150.23,"score_display":"150.23","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_985db51e44c0b3d3bb9fbbfb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiercode":{"benchmark_release_id":"release_28313b815e5f20ff3646855e","benchmark_version":"FrontierCode 1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:38:18Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"aa4ab57ad65ec5b5f894537d5dc45afe5100160109d0ab5ca71b329c92934927","measurement_key":"527b1b8a56dde17b18b5292c7269a9f334a0ea4e41a69dd97b427bbfa4b23fe7","metric":"mergeability_rubric_mean_at_5","protocol_fingerprint":"227f91e8c423af202566cf13b45663433088c2b5a0344b93eabc4c5fd2951896","run_fingerprint":"64469ff3d0088423c40720e54568c4ff3eafe37965d82461eb4a0970efb222bc","score":30.06,"score_display":"30.1","source":{"id":"epoch-frontiercode","name":"Epoch AI mirror · FrontierCode 1.1","url":"https://epoch.ai/benchmarks/frontiercode"},"source_authority_tier":"B","split_or_window":"main-100-hardest-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_dd4b35536a13bf97a852f231","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":141,"at":"2026-06-13T01:39:44.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0d332f6735a6b86f3d2f7ed09f6daa7e0bbdf2f7363fa6e9571c616bfaccc550","measurement_key":"635f3880d3f4bd8c599b5bdd1297eb2543f845a4c863758716ae55ff4f70046b","metric":"mean_score","protocol_fingerprint":"c934cab44e6163fc127623626f7cab37035e2979a6b4784688228eb71f9b820c","run_fingerprint":"943833210192902bdf3bb3e20b09f2c02a31b7a938b519a489aa395b9aa68023","score":54.03508771929825,"score_display":"54.0","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9137a8c8a7db7d39dbe479e9","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":141,"at":"2026-06-13T01:39:44.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"05ade21a00f2daffe49608971919cbb8cb1f5e96d85343958b29ddd4fe897b69","measurement_key":"171a6e8d59ac0fd997c61a7cfdbcf41c0c6f8d4d2e99ca87826f729cf612ad6f","metric":"mean_score","protocol_fingerprint":"cb655832235294bac51fdb680d75442eac73bd158681fbf20e452ca29f822269","run_fingerprint":"101c2feb34110401f816b734c334dc9aaea3ae25d92baede7d61ec311011e00c","score":12.195121951219512,"score_display":"12.2","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_37090ab2b47281e7d26ce1a7","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2a0670a4b7647129092df5e97574030145ae375a8ff58450d7fb545337eeb701","measurement_key":"7380adb9ad7056b70eb3ceb3a9b94f867fc1bc52ca8ad8f5508b66e1c8bc82a9","metric":"elo","protocol_fingerprint":"2ffce7450eb8681bc24ef818920ce220a7bc6b670e86ea76c61e0feced6cf104","run_fingerprint":"438b158a4d68d87565dde9b17a3db3ff375316972f994aa0618349399cabac64","score":1046.01,"score_display":"1046","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c418354814777762766b7183","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_f83cfc2a9e19b8d654d7b58e","benchmark_version":"GPQA Diamond (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"81ce2acaad30b48c8e7e6773e970285575b59cf1cfb050f146e42662ea4990c1","measurement_key":"edf5b2c9c869ed47ff8731a64349a422714900f966e52d18e0974d965389a672","metric":"accuracy","protocol_fingerprint":"31c9e1853f57d6597a92c38c93fe9f8b762953a9f551ebb99438326d6adaf99c","run_fingerprint":"1beaec7bbdb4beace853476b82f8f395ea17f0f1000b15b57ebd042133165cc1","score":89.59596,"score_display":"89.6","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"diamond-198-zero-shot-5-repeats","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c418354814777762766b7183","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"49f602ea5c85b8b9c26e8168c2df3984f78044eb902f4d5db437d2b2fb6ff421","measurement_key":"6fa73371015c1baf4511794c562af649407cd8990403fac6cb0ae22ccddab9e6","metric":"accuracy","protocol_fingerprint":"cbf12bdea6cf080e4b48675595fb2285a324557cf6454f20733ca656213d4980","run_fingerprint":"23e9fc12a95af09be475898d6e0747a08ad723cfccb473658ef550f642691065","score":35.032437,"score_display":"35.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c418354814777762766b7183","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livebench":{"benchmark_release_id":"release_c94a1cfb9d281df4254ff243","benchmark_version":"2026-06-25","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":129,"at":"2026-06-25","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"eb8833b05acd587662c89ac13779200cd8a0c61e1fa742b6a9f1dcd5ae6aca82","measurement_key":"2da38af83a69abc86d9c121f387a50f9d9b4bdbe5ab6701897936102e884f1ad","metric":"category_balanced_average","protocol_fingerprint":"a84af31207ac7d6490dcb1124920c18a5cc4c38ca783ab2559a81357f257ddaa","run_fingerprint":"0a86bf6a0b6b2c7a592bd30688ec9cb5b78e0941279851c764600df7d40ac5b0","score":68.41172619047619,"score_display":"68.41","source":{"id":"livebench","name":"LiveBench","url":"https://livebench.ai/v1/table_2026_06_25.csv"},"source_authority_tier":"A","split_or_window":"overall-seven-category","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_47aaeb01147213e8437e7340","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"83db7b37e3c4d90be9438d697b3556f37698465e3022dcac047fbdae0c0e78ff","measurement_key":"ac4cd3ab7c29805b719ad5ab4eb1a356cb54f4d6c8c5fba250cf925fc6b30775","metric":"pass_at_1","protocol_fingerprint":"d08af2a5b5ddf37a13d08b258ae499a5bbe2fd41acf262dde3feca8c731c36fe","run_fingerprint":"e7af5dd4614dd5c97c5b495ca91a2e261e4f745868a020143c3b7fb27833b2ab","score":82.05,"score_display":"82.0","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d975f32ded4665b2f1e01b66","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-07T00:20:43.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ffe88e2ae9dea362b4b9af43b4b14fa9ea12c0e61d03b3103f48afbdb2d54f3e","measurement_key":"e2722eee3e5998f7d02706a35a095caea5be2797573ef780839ef2291e415786","metric":"mean_score","protocol_fingerprint":"ba1560a0e78954e95a1fbeff6bb7dc8f519b825a9793b92f0c72e4c4343ebbcb","run_fingerprint":"fdee7e95be1875bc6af041247fae7aa09d68f462caa02d76103285318d7f1d0e","score":95.55555555555556,"score_display":"95.6","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a87929f64e446284534a7d50","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"programbench":{"benchmark_release_id":"release_88931830e68b802f00d3f781","benchmark_version":"Vals ProgramBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:15Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1ab3ad9013572e281fece9e46a69dd7a9c121086fafbeaa0cfd3a86d3be0948c","measurement_key":"8ba8895f8295a7a6c0c7633ea4f9c1f0cd88acfdab89ce0b91e8bb16b35346b9","metric":"fully_resolved_rate","protocol_fingerprint":"e3e3464450eff5c115e48dd7d8023c66a76a14e7d37083aecd1cb72d127657a2","run_fingerprint":"6f043dc4ea237435ec49159fd5b0aaa239818d2e5c543eb556cdf340737a5f13","score":0.0,"score_display":"0.0","source":{"id":"vals-programbench","name":"Vals AI · ProgramBench","url":"https://www.vals.ai/benchmarks/programbench"},"source_authority_tier":"B","split_or_window":"vals-programbench-200-public-tasks","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3d974e559f7d9d71f38a39cf","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a786ccbd59e0f0ca58f81ef55becfcd1a3f56fb7e0f27c5e866fc5b8bd9a169c","measurement_key":"e59701058078d22fe4d95b4e66378e34b37780e7d4cc39b945a56fe731d05c7c","metric":"subproblem_accuracy","protocol_fingerprint":"e8e79e98bd24134c864da2b0e0dfbd0d74a2bdbc0d01c47a64397f02de275a25","run_fingerprint":"329646bed6c21f04d5d74613e39921ca7db618f7960d7e87add14355a8a74cb5","score":47.8009259259259,"score_display":"47.8","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1c34c4174282cba541b7d9bc","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1cc721ff6d34a396a3a8a8d82a51a7907a0c096d1624e65096d1c9077ce44a2a","measurement_key":"98f5468c052e36fd33a49d94440ab6d988b32edffdf76ccacd282f59c54e2f28","metric":"accuracy_avg_at_5","protocol_fingerprint":"bf92dc42aced9cbce2c8fb44c7e2bb56f53e75fb33c035f97e38139ed580cfd4","run_fingerprint":"484954f7fc29c6141f17b4402127e51b27fd85a3f98a4dbbf848c8f5d3ff085a","score":57.9,"score_display":"57.9","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8861fafa0de5f1d143a949c9","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:36:03.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"38381dc8d16af483aa95c85aea32f80cc6fd1b4a57b6c506db85840f210160d8","measurement_key":"23f195939053a546ca4118a94bd620b2a62293f8459921b5980c4c5d8be2f1a0","metric":"accuracy","protocol_fingerprint":"aa2afddb6862878a83c16956406d08720ef942d16c7bcb30f7d35c9d8326149a","run_fingerprint":"5520a38af43a5b177f3b4b1606398c8892cc57722cf57cf3bc9bda2ef93c59a5","score":36.5,"score_display":"36.5","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_63aaba2756ec14ee77fae61c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"50e6f9a2f250af4b4b76594bea5f77133e379c00eef9c08b2f3aa72799ccda0e","measurement_key":"fc47c5d21546f78cc8b27bf0f874fe25cce248b5417c092a0bd620090ef42f4e","metric":"resolved_rate","protocol_fingerprint":"cf2233bfa2373c71c8ed2087846a2f4d1737f015763e77f6af90d1af8b710e6a","run_fingerprint":"460ba4c48ec551141bdf47f1877d0454db4d058d0ad05933370a997994556970","score":78.2,"score_display":"78.2","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4563edc5bc06fca8cdd968dd","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"50e6f9a2f250af4b4b76594bea5f77133e379c00eef9c08b2f3aa72799ccda0e","measurement_key":"fc47c5d21546f78cc8b27bf0f874fe25cce248b5417c092a0bd620090ef42f4e","metric":"resolved_rate","protocol_fingerprint":"cf2233bfa2373c71c8ed2087846a2f4d1737f015763e77f6af90d1af8b710e6a","reporting_origin":"organizer","run_fingerprint":"460ba4c48ec551141bdf47f1877d0454db4d058d0ad05933370a997994556970","score":78.2,"score_display":"78.2","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4563edc5bc06fca8cdd968dd","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3ceb234a7f0c3bf3751f735f30a9a733a5f4e2293369b672b6706389bb3f65a9","measurement_key":"be972df0a8f75700cc36bc0e16f90a42914ead8b67369b39249d154608ae13f4","metric":"pass_at_1","protocol_fingerprint":"d80d07f36bfd41d5a1f8c6f5422c88eb4ca7f6b198e76104962918e59f7c558f","run_fingerprint":"a1a697f2c274336eb89c5eeebe4bb16db800d63a5e11f23ef783cfe5dd9f67f1","score":20.206186,"score_display":"20.2","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c418354814777762766b7183","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_3a1f88ce28d6c9608c34ad04","benchmark_version":"Vals Terminal-Bench 2.1 v2.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:43Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"325bd85ef5e9788ed6641dc07201e68defef06638d04dfb49b4a4c7fa72b01e2","measurement_key":"4b9b19f5eb25809bd06d3bb11dd2f7e2c1ced12f765186749f33fbb88e74feb5","metric":"accuracy","protocol_fingerprint":"627971640dbf722ed7d004d14af9b96bb57d0780f5336de49662bdc58f7bf696","run_fingerprint":"ac3fef2d020fe6e804e072902bc1b2d1e18437257d8a3d66a9deac06c8933718","score":67.041,"score_display":"67.0","source":{"id":"vals-terminal-bench-2-1","name":"Vals AI · Terminal-Bench 2.1","url":"https://www.vals.ai/benchmarks/terminal-bench-2-1"},"source_authority_tier":"B","split_or_window":"vals-terminal-bench-2-1-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f7cb373722491bb55787c0f1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_b7d9ab744ffac0cb856e114d","benchmark_version":"Terminal-Bench 4.0 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:17Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2015ecc01bdec07e20db77bb8392b711f56f068a7186763f5ba0ad076baf10ab","measurement_key":"32bc03fc7fac9fc22bffb7e5baf26130b8efaa0631cf401f574cc67a3d9cb350","metric":"pass_at_1","protocol_fingerprint":"90c7acd2ed3d0523b4adfd570ea5eacdb5c711cf72f5d905d945974f58aa54a7","run_fingerprint":"fd87050f863c05de173eb58a5a71ea23e9f76bde02f43a28021bd2bdad29a833","score":1.010101,"score_display":"1.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"mini-swe-agent-66-tasks-500-steps","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c418354814777762766b7183","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"007f0c3c496243838690df069bba27b3f0d86bce3476da3cf371a3f8b420038b","measurement_key":"529b0bdfaad6967cb07dccab276df7485c00517fda6a4bcf54a0fe7042458e64","metric":"mean_final_balance_usd","protocol_fingerprint":"38be7dd9ac77751164079289b317909d6a2c57075ba33d292d0899260c6fefb5","run_fingerprint":"ad5d2a7d52a458582795f391a51c306be68f7fc7031ef18f1a16edbbad2d60db","score":5082.936,"score_display":"5082.94","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2b04515110e6907c541185f5","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5fc1e40f75312af0080e341f5d19ba95fa69fbee7519157cbec0504e23cc96fa","measurement_key":"860b8ad77f270a87f9e2b9c22e506622d218f1f1efb9aff7ba83afe5970809ea","metric":"score","protocol_fingerprint":"3d1932a9d9af66f3d40d79a7c2832fc36a316362897d293c86a16f16042cf41b","run_fingerprint":"fcaddd0f33c844b034a1e53b6796516d4b18241b9fef15d31618ec82e736a603","score":47.211,"score_display":"47.2","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e042f5db1ee3a91dd7a3bc95","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ead56752fd5ee9b987204f4799ced7c765fd2da8b1321813adfd67ef69ac5b92","measurement_key":"c94b54e7b7dc3ed45f16b1350b8deb97ce1ce8f701d73976cbacacb6566a97ca","metric":"arena_score","protocol_fingerprint":"04bc93151a5e84d1a5cbbf6a85efeec55df22ef665fafe007d005255b851ce89","run_fingerprint":"bfff7ec0ddb824928eaa1eff3f04580efe1cea9863c1ba5ccf8084e12aa22df7","score":1473.5355204604502,"score_display":"1474","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d8d2349529d194d11d6a5ea0","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4e759bf4605d0ff61586da645cfdfaf18a48c55f9a71012bf2d871a1f578b63b","measurement_key":"c2a5bd14d55cbbb357ad7b58f7badb8f6a30295effef2e41146da744f926e81a","metric":"accuracy","protocol_fingerprint":"e3029412c8500dac68ebb1de4e59896852700e290bd965b86f9f8cc7d11f9fb9","run_fingerprint":"7272f4f9ff1f3b6aa3e412336686d918e8b8bbc3498b6943396b9bb3c12fdf00","score":54.120000000000005,"score_display":"54.1","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_85f25685b1561fc4451541c5","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"moonshot/kimi-k2-7-code","model_name":"Kimi K2.7 Code","parameter_count_active":32000000000,"parameter_count_total":1000000000000,"provider":"Moonshot AI","selection_rank":92,"weights_status":"open"},{"cells":{"apex-agents":{"benchmark_release_id":"release_e102ff7c1fdcabae1b00cd4a","benchmark_version":"APEX-Agents · Epoch evaluation since 2026-09-30","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":31,"at":"2026-09-30T18:53:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"efc3d2e4a1db10432044885d5c0d15d1e562fa5ca77b1e5ba1e5fc32c1a4cc78","measurement_key":"9ad229de03c966400a062934ba30bb6a6d006748fdd834ddc9a23ddb6db684e1","metric":"pass_at_1","protocol_fingerprint":"8e4b2b2b9208e63ae9b3331b08fb7e1e68674f25cd35a332f6dddf35c0e78f17","run_fingerprint":"1224deaeb2e1bc3bc83b53213416dc1dd94ccb205910df1d8496491222b0f2ba","score":24.9,"score_display":"24.9","source":{"id":"epoch-apex-agents","name":"Epoch AI mirror · APEX-Agents","url":"https://epoch.ai/benchmarks/apex-agents"},"source_authority_tier":"B","split_or_window":"480-professional-tasks-33-worlds","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f2df9bdc5ed37041104d582e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"35cf8aaad2b9fa2c59c8c8ec777ad9f0eff4c6aaf9764fa0763d41d4593426b1","measurement_key":"d51148002a0a816562fe46e58eb351d205433d921204df4f2b751a14ff0e0ef5","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"1fd4b540020ed46a12db1de04ae6a6db310679cbd6db38e44fb711def8f409a5","score":1441.403236489422,"score_display":"1441","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_062b1dd6a5a62c713b280490","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"bfcl-v4":{"benchmark_release_id":"release_6b9456463dae72f95fadf6b3","benchmark_version":"BFCL V4 · Qwen vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":258,"at":"2026-02-16","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"83dd3b78c54352e64b8bff8bd90b81c57ef3bfc1d9658f94cec1b90bebdd251f","measurement_key":"6e45664d3fe375b2df801fe35944286e116c4f5d09255533295207d6f779cc86","metric":"overall_accuracy","protocol_fingerprint":"2be3c8fde04bf33c6b6db13a6ae1981f288300b9baf0dde2bfae161e55ae4181","run_fingerprint":"d7cb6a43287918f300482b7aabb4124578f3dff767b00503545c975d2b0a610d","score":72.9,"score_display":"72.9","source":{"id":"qwen3-5-397b-a17b-card","name":"Qwen3.5-397B-A17B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B"},"source_authority_tier":"B","split_or_window":"vendor-card-protocol-undisclosed","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_28d4327ed17739786e2e7ac4","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":3,"at":"2026-10-28T21:25:03Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"19f28c0d04bd7952bf8cfe0c748ed486580c40f5499cd83e55bacc8340a63499","measurement_key":"ce7b7f3f19e3e5ee31d3c3310dd9e80a01b56b70a7150799152810d535be42b1","metric":"accuracy","protocol_fingerprint":"9eea1925b989dc40c0ec9008c754919603aa0721eaffe8b990fe19d8966dbaa8","run_fingerprint":"b36880442937c4bb62dc47b7e369d64a043559f886c841522dfb9a652513e292","score":0.857142857142857,"score_display":"0.9","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_f05cee9da83990f5cc4a1d0c","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d42a0166b48640c10f22725b26f44e0a42928358ac4a2f31e3e1d0463791b1c4","measurement_key":"28767cafab8dfa17a625d4ae2b942c3b59d41f6af59c033da3a7802da7f7bc7d","metric":"eci","protocol_fingerprint":"ac3a582014ccb9e1add6048f494bee24f454ad2985c7137efcf44a6956c7374e","run_fingerprint":"5c777e68f81024986ce2f36c3a051fae157ea27e317d49361502be52dd31f718","score":146.85,"score_display":"146.85","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_90e56fd70dd0364120d5d708","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T22:34:18.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4a4589d6b746837d91f663ab89ad5e31230d46634f8cf0e4c27274f9e4a35267","measurement_key":"04e90786e047bf43121aba131394f4f9bd27da87a9df447e355046298c9a85be","metric":"mean_score","protocol_fingerprint":"d8ecfaeb0fafa1b6bb87324c051d31193978f4f8bbf35f3aa4df329071cebd42","run_fingerprint":"e2ff315674937383987073fd3aa42e03f1b6d889045cb33bbbb0070b4b96af36","score":31.2280701754386,"score_display":"31.2","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"off","profile_id":"profile_f05cee9da83990f5cc4a1d0c","raw_label":"off","reasoning_enabled":false,"strategy":"none","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"23036c6d817b1044e889941e5a65ffff15331896921783abe3fa869da492f690","measurement_key":"405dbab5e0c702d84632e3c440918d1506c9d61be5aa3cdb7922a5c409a7bd27","metric":"elo","protocol_fingerprint":"ea714612113691365b594e9602c7fed643989edbab7ab049f89a82d36993198f","run_fingerprint":"b3fd68385df92d6cb937b3010e8236767bd58a70f0d2670d2ae01c3d4add41ce","score":800.64,"score_display":"801","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_d177f1d7065fe8f8ce6ad0c2","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_f83cfc2a9e19b8d654d7b58e","benchmark_version":"GPQA Diamond (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b77ec050f53aa28119260c972f657bfcc9921703abe51bea5508bebebe46e814","measurement_key":"cf14a6bb1e07de61939f4d06cf519453102df9a275364e4c9bafda9800abd783","metric":"accuracy","protocol_fingerprint":"bd9de00bd5433c347bd7f68e4aa17f4dfa14742cda8f4713d0d2ebc0be75c1fa","run_fingerprint":"70ed449f60ac1edce0d07c38bef94c79a6c0c7d19a29491204d5dd7ed04887df","score":89.292929,"score_display":"89.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"diamond-198-zero-shot-5-repeats","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_d177f1d7065fe8f8ce6ad0c2","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_2f3c6e21d0f3616fdb78f627","benchmark_version":"HLE · Qwen vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":258,"at":"2026-02-16","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"3e8d2522565e34e4fb8783d591b72fcb487cbf8d0a9623b5efb70d6cb9c7bd21","measurement_key":"fc273ef2bc54332c21b7e8ef2319797370dfe4d7db60e76189e583c208d738aa","metric":"accuracy","protocol_fingerprint":"868bb776b8522904ff0c5ee9dd97bd51db6e2af1f9b16da3811eb93464730240","run_fingerprint":"bcd5d7cdee647bb9f08d1813095c2bab2574d416311f8e80d993c7869682c8ea","score":28.7,"score_display":"28.7","source":{"id":"qwen3-5-397b-a17b-card","name":"Qwen3.5-397B-A17B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B"},"source_authority_tier":"B","split_or_window":"full-multimodal-cot-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_28d4327ed17739786e2e7ac4","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ae372169a0bef9c68f25ba26053302a2e6de87eff8a980936985dc8d84e2e9aa","measurement_key":"07d547fcdc55c1910bc7d9ae4865f730f77378e4fc79525194b520d4ad152bc9","metric":"accuracy","protocol_fingerprint":"f316e6da39745a3aeef81c5887a1dbc43344c449a6fe5c2ae3ab631f773424ae","run_fingerprint":"794b9d3a14e9e32cfb945c0e62dbaabdf5120ecff4f9c1148c358b422e7b0182","score":28.962002,"score_display":"29.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_d177f1d7065fe8f8ce6ad0c2","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_95dc04609d027072fa229d3b","benchmark_version":"MMLU-Pro · Qwen vendor run","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":193,"at":"2026-04-22","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"ce207ba88dc13c7a99aa5a3d58b8d984d8e570abeabe617e299acfb27c5b711c","measurement_key":"cb0d5abf8808e4bbbb2e660e520183e966381584521fe6bee37160c9045737d3","metric":"accuracy","protocol_fingerprint":"44f56864a490bb7582461036c068400061930b80aee3b634127a43235a3bd532","run_fingerprint":"e3570f95190160986b5ad0e26740a4eac24c380aefbdd2a5ed46b3f4657f928f","score":87.8,"score_display":"87.8","source":{"id":"qwen3-6-27b-card","name":"Qwen3.6-27B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-27B"},"source_authority_tier":"B","split_or_window":"vendor-card-protocol-undisclosed","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_54abff30262a823e8f5a7fc3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c32eb82db435f498be90eb9b34703e479609b080a33624d7fdf63bc823cf893f","measurement_key":"2fca996907f73dd115fef1232d5605e199b7d65d7cadae93f8b6a6063688b56e","metric":"accuracy","protocol_fingerprint":"f6a42b3c673b70f19114b664286aa3515baee4fb0558d019697ada3e4ef1f1f0","run_fingerprint":"d1f784aa5e6d21cc56b3dcd56661c807653e54eac23a93bf5f4e450ebb8765d9","score":77.283237,"score_display":"77.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_d177f1d7065fe8f8ce6ad0c2","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-07T00:12:18.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9a7bb916d010611e847a7a8815fc725df23da7d3e0224ad158430431d04337ff","measurement_key":"96f74b495f0f64ac2272a56cecf9dd06066f7e4976e257ea03acadf0c699a84c","metric":"mean_score","protocol_fingerprint":"f767e31ef1f628d16486a10f8c816a461a1bf1fc45e3fd6d62bc0494285aef5a","run_fingerprint":"d45c1c519352dcbf0ba91d67ea73b35fbd636ddd63788d84615072db43d26a4d","score":88.88888888888889,"score_display":"88.9","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_7cce63965b2039e8ed31c47c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_de40c66bd40a7b5483b40f9a","benchmark_version":"SciCode v1.0.1 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":54,"at":"2026-09-08T00:34:38Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1504e6e001f80ef3d8b9fbae91fc307b7b1e50e1b937fa6012d8531f0d6ef7d8","measurement_key":"54ea2c116020c6088b400caa4508b934075b6a53f9aec33594b820b985969cd3","metric":"subproblem_accuracy","protocol_fingerprint":"8f1633398f8a29186d3ec6e1e9998e315767bb63261e54a062fc855688c57796","run_fingerprint":"581f164c27bb71270e14b75312a9c05bcf71a704da99afa82e77803f1950b4f9","score":44.791667,"score_display":"44.8","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_d177f1d7065fe8f8ce6ad0c2","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"skillsbench":{"benchmark_release_id":"release_5af9fe5a9d5e275323798c8b","benchmark_version":"SkillsBench · Qwen 78-task self-contained subset","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":193,"at":"2026-04-22","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"bdfed38e704e0c0b9349070d11f6a7a744e5b63f20f7e377d82e0cd62ae74244","measurement_key":"e599d0a837bb1c6ceec14d4da5e813ebf80318dd60a3297dc59d260e7df51537","metric":"pass_rate","protocol_fingerprint":"0075a32b62b602932d1572b58a2560fe97ac92d58166e3cd33e67ab077a6bac5","run_fingerprint":"f4fe44d781b8822dc371f22076a32f5ac304b518eea29f0ca81e0e11c7677aca","score":30.0,"score_display":"30.0","source":{"id":"qwen3-6-27b-card","name":"Qwen3.6-27B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-27B"},"source_authority_tier":"B","split_or_window":"self-contained-78-no-api-subset","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_54abff30262a823e8f5a7fc3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"swe-bench-verified":{"benchmark_release_id":"release_9162beb27813d52a46a20a9f","benchmark_version":"SWE-bench Verified · Qwen vendor protocol","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":193,"at":"2026-04-22","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"96c3d27aadd523c2bbdb530cd5da43a329116dd83a0c30a0a97d2861c1c2c925","measurement_key":"f092c4f8936eccb2be6a12bd7921528ca519749fa98331ca03bf1dd4a3c29f55","metric":"resolved_rate","protocol_fingerprint":"76ed278b99ffd1e5f9230954bc4ee5268b74c5c42a740c706366f11a530ecbf6","run_fingerprint":"c2f707b99a2815e07c1030e5d1d1d5b3c12a1582bccd8136cfdf4c6caed5432f","score":76.2,"score_display":"76.2","source":{"id":"qwen3-6-27b-card","name":"Qwen3.6-27B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-27B"},"source_authority_tier":"B","split_or_window":"qwen-internal-agent-run","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_54abff30262a823e8f5a7fc3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report","views":{"reported_system":{"benchmark_release_id":"release_9162beb27813d52a46a20a9f","benchmark_version":"SWE-bench Verified · Qwen vendor protocol","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"B","freshness":{"age_days":193,"at":"2026-04-22","last_confirmed_at":"2026-11-01T03:42:35Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"96c3d27aadd523c2bbdb530cd5da43a329116dd83a0c30a0a97d2861c1c2c925","measurement_key":"f092c4f8936eccb2be6a12bd7921528ca519749fa98331ca03bf1dd4a3c29f55","metric":"resolved_rate","protocol_fingerprint":"76ed278b99ffd1e5f9230954bc4ee5268b74c5c42a740c706366f11a530ecbf6","reporting_origin":"provider","run_fingerprint":"c2f707b99a2815e07c1030e5d1d1d5b3c12a1582bccd8136cfdf4c6caed5432f","score":76.2,"score_display":"76.2","source":{"id":"qwen3-6-27b-card","name":"Qwen3.6-27B official revision-pinned model card","url":"https://huggingface.co/Qwen/Qwen3.6-27B"},"source_authority_tier":"B","split_or_window":"qwen-internal-agent-run","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_54abff30262a823e8f5a7fc3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"B","evidence_rank":2,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-model-vendor-report","verified_status":"official-model-vendor-report"},"unit":"percent","verification_status":"official-model-vendor-report"},"strict":null}},"swe-rebench-v2":{"benchmark_release_id":"release_7449132b5f078c71f23c26b5","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":245,"at":"2026-03-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"b359c40930a830e9d1647d42947ed8fd8e385004370531197e9b0b3458cf1a15","measurement_key":"3694da6c73d3de8386520027c522936a46baf774a8574e2717058cdad14cc602","metric":"resolved_rate","protocol_fingerprint":"01da0eb2fd9c383f12ef300cd69d69d04eda6900ff1aa1003fe2c725832a2382","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-02-15/2026-03-01":{"benchmark_release_id":"release_7449132b5f078c71f23c26b5","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":245,"at":"2026-03-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"b359c40930a830e9d1647d42947ed8fd8e385004370531197e9b0b3458cf1a15","measurement_key":"3694da6c73d3de8386520027c522936a46baf774a8574e2717058cdad14cc602","metric":"resolved_rate","protocol_fingerprint":"01da0eb2fd9c383f12ef300cd69d69d04eda6900ff1aa1003fe2c725832a2382","run_fingerprint":"d5f0bf44ff1ea49a9ecdca3047d6021cb335d747e2dd7a384178604ea738d8f3","score":56.837606837606835,"score_display":"56.84","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-02-15/2026-03-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ddb434ba4c54ecfb0e035efd","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"d5f0bf44ff1ea49a9ecdca3047d6021cb335d747e2dd7a384178604ea738d8f3","score":56.837606837606835,"score_display":"56.84","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-02-15/2026-03-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ddb434ba4c54ecfb0e035efd","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":247,"at":"2026-02-27","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"8b355f074dccabde9ceeb5a4bb26bfccc17a78678a244f55ac7e55afa5186e11","measurement_key":"aff3963d4886eb43b3aadb9ff72bc51b09468d4fee76c015e5008927b1fd9fe5","metric":"pass_1","protocol_fingerprint":"f060008efbd1330fcb16847cd355ebaffc070cbb0b9dd1b31485f1394c535163","run_fingerprint":"aa004272b65d364615cf5f98fd0b53f9dc824b734a3fa36169c50ced77388944","score":9.79,"score_display":"9.8","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fec2e8c4ae6e264376e8e9fd","raw_label":"enabled","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cfaa016efce5b4749862a903bcd48a3392870f87a952d62078ffb3c0e7e3c079","measurement_key":"eddb29060fb0b904f9166c754673892baa6caebb7168fd21f6e1a61f94626749","metric":"pass_at_1","protocol_fingerprint":"d6903f51b87e19042dac19fbb1d86f91bbc9d8ad83806b456ecb0ebe95e16dc1","run_fingerprint":"f43354c00908a8771d9b98a7f9e7240659ebd888cc8b6c83546bd5dde1199b7a","score":13.402062,"score_display":"13.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_d177f1d7065fe8f8ce6ad0c2","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_c53c830678318dc1763793c8","benchmark_version":"Terminal-Bench 2.1 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9fa46f1672726652ceb4f95bad745706cf3097ead8174ebba497049165649513","measurement_key":"45867ddd6d2dd5c977262927c4269d1243f0a4c607060c0c89687cf181fff046","metric":"pass_at_1","protocol_fingerprint":"00b43fd9ca289c42d0beb098afccdf3cf238f10120d2858968ec3d98c6b09f11","run_fingerprint":"1f87088a4d9990a8d2d18d331038a634a295ebcc4dcd2ca35d8f92c55071592e","score":51.310861,"score_display":"51.3","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"terminus-2-89-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_d177f1d7065fe8f8ce6ad0c2","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_b7d9ab744ffac0cb856e114d","benchmark_version":"Terminal-Bench 4.0 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:17Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"799e892b8f2bd742ec90e9f0d2d308a89b9189e793606a42b4e2b745eacc7785","measurement_key":"6a7cb43090a9d898783f4c60313c10b35dc2509eb19dc0645ecb1c95f96dd099","metric":"pass_at_1","protocol_fingerprint":"8f78486beeddbb49c8623a4314b10df5c24398a38651efea42424aa8802acc57","run_fingerprint":"3deb4d62d9413a7fb937cb2c33e270d4d8688c817cc9e22bf9c356d7426ca7bb","score":0.0,"score_display":"0.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"mini-swe-agent-66-tasks-500-steps","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_d177f1d7065fe8f8ce6ad0c2","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"aeded49bc462d814813d99e8f6b2ebaa634ca594c84fdc254fca6eb8c3c1dc78","measurement_key":"85f6cf1f57d29d65256b43f96f3feb73e381c3ff6f398b9cf084859bfda9126e","metric":"arena_score","protocol_fingerprint":"5ba244c43b5f7537b5fd92430355ef77d604108fb710c111057a9a770fdb33fe","run_fingerprint":"166f023084fb6e7f28591d17bb9193ac6f7cfdbc57d428191321a47ce0cd0188","score":1400.2208309279806,"score_display":"1400","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4837b3098d8faed90802985c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"alibaba/qwen3-5-397b-a17b","model_name":"Qwen 3.5 397B-A17B","parameter_count_active":17000000000,"parameter_count_total":397000000000,"provider":"Alibaba","selection_rank":93,"weights_status":"open"},{"cells":{"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"16a4cabcd11c005ca4ef485820a322d57216dd0779b7328bd8a604a7c61820c9","measurement_key":"acc73527c8e54adf1b9e60d4e651f4538a462dc5d35553249a8f6f07966a8f3a","metric":"accuracy","protocol_fingerprint":"32c64e7085a4b74a03105464f87aeab6550cfc6c70d84c111a6042eaa5aadce7","run_fingerprint":"330cad8965b17dc572a6d2256f66452d5f7d5237be0f260e5d2af44611ff03a7","score":20.0,"score_display":"20.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_dd2002eab3ec3258a39b1020","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-30T09:17:57Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"802229938acdc632d6ffed545bec486a7af4e01d79133c11b83ffc56f97343a4","measurement_key":"6fae9675e28a62f319be7b40a3a40689f8459323314c2c9f2d8fdec950f1bdd1","metric":"elo","protocol_fingerprint":"e7a3be2fad89121cb026b4893bb3c0d272e694a63588ef23570a75e241c538b6","run_fingerprint":"1a9fe59010535609f0e640c1ca28be6a47fd7454822a46b9be34090728f73979","score":1615.72,"score_display":"1616","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_dd2002eab3ec3258a39b1020","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_f83cfc2a9e19b8d654d7b58e","benchmark_version":"GPQA Diamond (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"895065af9442feffed6fdb928bd0f11d8823f949fa5bcf1ce9dcb4725286f228","measurement_key":"07495a934d88b1d27ce960a4af04a100fbcf4ab24549a134fcdc0d08caba4d68","metric":"accuracy","protocol_fingerprint":"c951e008fd1e95da37f9853a35a9d63c98520d3c85b7c74a6bbef9ec347a8142","run_fingerprint":"61511f694177c3ac5442163433e507233122b620c2bd4d0b5e866ea00cfebf79","score":93.535354,"score_display":"93.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"diamond-198-zero-shot-5-repeats","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_dd2002eab3ec3258a39b1020","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_fa9e908ac04b067eb00182d4","benchmark_version":"HLE official leaderboard","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":63,"at":"2026-08-29T23:52:43Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"42b915cdbbbbb3884ad5a8601c0df9828227b19da0f0f200ed1cad13dba273d4","measurement_key":"1a6ddc9c7fef106eaa68a6c987efc64a6d16bccad9281f14ca55103d507552a5","metric":"accuracy","protocol_fingerprint":"e1f956386a97e6ba42a3c396757902d19f19cdabb10fcc91e345af5c771a2890","run_fingerprint":"8ca7498bf7d5f957fad20dfaefdfedbd5bdf33488010adc22da9fca788313845","score":43.6,"score_display":"43.6","source":{"id":"hle","name":"Humanity's Last Exam","url":"https://huggingface.co/api/datasets/cais/hle/leaderboard?limit=200"},"source_authority_tier":"A","split_or_window":"published-leaderboard","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_9a07d223bdd9e8b87c6a58c3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"C","evidence_rank":5,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"self-reported","verified_status":"self-reported"},"unit":"percent","verification_status":"self-reported"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1ec8c8eed8f554bfdabb60ea538b86629f8000b50dc146313f55dc9d70810ec0","measurement_key":"942fd68d01867fba909dcc2d0712f8cb590fd09e62f22a9cb9e06d4e728d3eb8","metric":"accuracy","protocol_fingerprint":"2702d49cca72c3306f1d671402ff6b60bc98b2efd30c9305500933280881dfef","run_fingerprint":"f7412f0a089a724590586d6a0328bed82fa58dbd510541ba6af8b27a5fec9bc2","score":42.44671,"score_display":"42.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_dd2002eab3ec3258a39b1020","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":44,"at":"2026-09-17T14:59:32Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"586fb01249fa94b0d92516926a13fcdd5d9113e5226bca39dc87fe0bfabd0608","measurement_key":"cea7a59313f2d12d7440f47736b78feb6cf93ea1983816089609d1b1fe710ea6","metric":"pass_rate","protocol_fingerprint":"3abe620455155e020933a485ba9b63047c422c73c5781f34ccd647cd59c1c078","run_fingerprint":"4979b6d1f8fd9514f8531dc34fd00b7e91afb0952be780edafd0c3801a9ee17a","score":84.5,"score_display":"84.5","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"xhigh","profile_id":"profile_99463af9d053c64e40c26c38","raw_label":"xhigh","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"scicode":{"benchmark_release_id":"release_de40c66bd40a7b5483b40f9a","benchmark_version":"SciCode v1.0.1 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":56,"at":"2026-09-05T17:21:27Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fcd0b9bfa39b5093ebf9065f2dc8ce9241989e4cbad3988c76deefa80e4a9e2b","measurement_key":"45c0765a9d1e21b70261a44c85c79a10fb8a6046154ee24badb1b5f3e2aea5bc","metric":"subproblem_accuracy","protocol_fingerprint":"a845e32771dc4669b5899b30646a47a4ffd982b194519955ab3c2f609eaa32dc","run_fingerprint":"57379139d5c1e5be64f81bf7c27532f0c6c7a9b2762d5a867561f2cf2f9275ab","score":54.050926,"score_display":"54.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_dd2002eab3ec3258a39b1020","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ff31f5e5f2f5dc63a328563b9e0743f81c46c269de987467397175b83756057d","measurement_key":"da9646ee997a33f70378834438a42bb7f84d860f4c6ec0fc3c023a487553ef02","metric":"pass_at_1","protocol_fingerprint":"8990bbfc9edee19a0378f5574b8299d090877c08324a7f8eba51f2d76af190c8","run_fingerprint":"5d2995595c233b13635135b080e23b009eac4d20ad9b54ef50f869eb064a4cb4","score":49.072165,"score_display":"49.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_dd2002eab3ec3258a39b1020","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_c53c830678318dc1763793c8","benchmark_version":"Terminal-Bench 2.1 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c3dc7dfcd629efb8bd0ea8274bddb504c527e7cff145fa81db1b4869bf7a6259","measurement_key":"fadd5c9b8af5b97e176d3b20e8e7067aa0d35b4b327ed24ca45bfb03974f43ba","metric":"pass_at_1","protocol_fingerprint":"7bfbe2612c758d5760a631cc6ec05da1c9a0e2d8fb6afe9ec1f541bb80c98c4d","run_fingerprint":"bf975bfef830870c8130cc37b217f517fef8833005b94ad809b4347582d8cf55","score":82.022472,"score_display":"82.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"terminus-2-89-tasks","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_dd2002eab3ec3258a39b1020","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_b7d9ab744ffac0cb856e114d","benchmark_version":"Terminal-Bench 4.0 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:17Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c2602a60ecef8851a5f10fb933893989c9245bc0f82bbf0b76041914b808cc83","measurement_key":"c1109c470b14f94f556b6a5b8e724db5489c5f0c8a8e6a1ca038a4618b1676f4","metric":"pass_at_1","protocol_fingerprint":"78742f435bcf919ac96006668fc210d2024c724feb5db534903d520fdf88d8c3","run_fingerprint":"7dc4b699c46ccf03baa0d7670002f41c739c7bcffd38c890e759dfe794cd20df","score":11.111111,"score_display":"11.1","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"mini-swe-agent-66-tasks-500-steps","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_dd2002eab3ec3258a39b1020","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}},"local_open_weight_essential":false,"model_id":"alibaba/qwen3-8-2-4t-a95b","model_name":"Qwen 3.8 2.4T-A95B","parameter_count_active":95000000000,"parameter_count_total":2400000000000,"provider":"Alibaba","selection_rank":94,"weights_status":"open"},{"cells":{"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c9c19a5b175e96a82e791801e99d5ee9ab3d05451421a8c30b1ca86769b418b6","measurement_key":"131432a65c40b4d2b2ddc168f84a10787a5296264b80d094989b7bd8407c19b7","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"1ec20d56906b3e84ad975527995e86aed4e91542191b433281a66ce26a4721ff","score":1460.2131590348529,"score_display":"1460","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e0cdc415c5b29e9a4e97c44b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0c8eee1d628510bd549013078ab637d0510fbe35403be236330f61f67020417a","measurement_key":"5c11d79c8e7a0616f4414fdede85de9edd5ef1fa572c0742eb46db04af2e4d60","metric":"eci","protocol_fingerprint":"873b1028434ebba2742a925a924197c3ee9a3603d93041f13ab4bbf823508efd","run_fingerprint":"1c9e9dd859a7aba299b86e1f8b0bc1ede6437efe01891406873016c8b9844a5b","score":149.38,"score_display":"149.38","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d3b3c1e009228ac3e1f855f2","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"gpqa-diamond":{"benchmark_release_id":"release_130743b4d612a7ac7c996be4","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-07T00:46:39.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"23cbbfd21dee5765870c0f9ea0b54c653f6e947c62b56bdf911e2a17320bd11d","measurement_key":"6d52cbbeb7f9ea815ea030121e72e462dec9441cc612b7e9431b63931a10831e","metric":"accuracy","protocol_fingerprint":"0b0b7941b04d488dd65911e62a5ef48434dbfce3fef6c7a28590d294277391d3","run_fingerprint":"fd2c603d90fc2608fbb39cb254591004168833a494af0f23d78fe4b306e4c9bd","score":87.37373737373737,"score_display":"87.4","source":{"id":"epoch-gpqa-diamond","name":"Epoch AI GPQA Diamond","url":"https://epoch.ai/benchmarks/gpqa-diamond"},"source_authority_tier":"A","split_or_window":"diamond-epoch-inspect","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c656be424b91b5bbd75f2aec","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":86,"at":"2026-08-07T00:42:24.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"03ba39e15b251678319319ec9ed0026b43a353573e6cc9734eff30cb0c0a2984","measurement_key":"8e7501b943a1e256f13e83151237c099a42036037fe52cc4a17c0089af1cdbe1","metric":"mean_score","protocol_fingerprint":"53721f0f1d9a2b4915003b28b41904796c4720cefb18cc3ec8c3c5237db1499a","run_fingerprint":"e7026cb4d98e9157aa78c42276885e8e7bce89d3ee9b556b33e2866ffb8a8094","score":91.11111111111111,"score_display":"91.1","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4b807b8f467caef3423aa98d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"49cc42c853febbbe9ba9cc88db6dfd5b8c517b58cf2e2e61d67e6a753812e7e8","measurement_key":"3c6e2c7b792adae199f20bbfba45a4755edc484b153778d111ca30e5b08c909e","metric":"accuracy_avg_at_5","protocol_fingerprint":"6dbccd280fb64a450c00c0ff2232ac25f842fdf586a8d550543ba0310005b1a2","run_fingerprint":"fbd2d6f82325fae5f980ded8de6d3c531dcf1e4609aab1711c36ef05b0d279c2","score":63.0,"score_display":"63.0","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f0189e6e512a7f8f6c14d55a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:33:58.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"158c92862098523075c051dcdbf5a23afa5bc5932bed8f6318a58e6989f8e77d","measurement_key":"40ca09fbe04ede87b65c5e736f290839e3bbd6fad90f4d8c91619784e16fac5e","metric":"accuracy","protocol_fingerprint":"d333fa9c9c40094adf12bb365e2ca5af71c35f022bcf022cf3ed1e8461311ff1","run_fingerprint":"e1633df1ffbe058fc72ef08e56c918e41c722b52d2427ed1e27e107bb49ebc17","score":52.00400801603207,"score_display":"52.0","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3fc6875ee3cff2a0aacf3f9d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4f7a2e18825248e23d2e9b9af78f71171c73247ff2c1681b0cae593c824c762e","measurement_key":"ce15ce4413e4d8bc06e09210d9057b0d25b52c29dc7727215976448bca4a1c4d","metric":"resolved_rate","protocol_fingerprint":"3fb6eb7fdcc7d7ef8a2ab537b37bdb23ab31a934113d4446ccc777d5c46c3238","run_fingerprint":"6ffb16487a50a714ff3c7c929d863922eb54ab6ba9d38ed9c54ea6fd415f4af0","score":72.8,"score_display":"72.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1d20a31e24960743cd851fca","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"4f7a2e18825248e23d2e9b9af78f71171c73247ff2c1681b0cae593c824c762e","measurement_key":"ce15ce4413e4d8bc06e09210d9057b0d25b52c29dc7727215976448bca4a1c4d","metric":"resolved_rate","protocol_fingerprint":"3fb6eb7fdcc7d7ef8a2ab537b37bdb23ab31a934113d4446ccc777d5c46c3238","reporting_origin":"organizer","run_fingerprint":"6ffb16487a50a714ff3c7c929d863922eb54ab6ba9d38ed9c54ea6fd415f4af0","score":72.8,"score_display":"72.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1d20a31e24960743cd851fca","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7d3df7776d36216d79b3f345979373292d0e57745233d02398b87c76200bb095","measurement_key":"7acb183ecab0f6137fd9e7e83b57bfbed050e6b7269f1512d0f05834ef6d95de","metric":"mean_final_balance_usd","protocol_fingerprint":"ed54e35bb086ed6ae1376be374c47344eb3021e2ebf1fbbe3d1e4469cf6bafed","run_fingerprint":"ff0c90291dbc88e03b37028e194fcef5f386d6b6d951645c55a87c1d6f3b0671","score":4254.1866666666665,"score_display":"4254.19","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"max","profile_id":"profile_a08522d91e6bb53b70645ffa","raw_label":"max","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"dcc700ba0a09e3af1f3453082859a39277d7a7b8e11436a0133715593a3807a0","measurement_key":"84a07e119f05a8a900eb9ed07d2760b9d4cbe4285253c0b75b3d55bd7aeb7380","metric":"arena_score","protocol_fingerprint":"89a29151fdb7e16187487835798dd5eb7f6abfa6ee84a0b58e7a608a4a20be31","run_fingerprint":"442b790298f1313876668934ca8c02287ecdb34e07c5e3bb95d54849baa0a521","score":1481.8179582284795,"score_display":"1482","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a0689db8baf849f97eac474b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"alibaba/qwen3-6-max-preview","model_name":"Qwen 3.6 Max Preview","parameter_count_active":null,"parameter_count_total":null,"provider":"Alibaba","selection_rank":95,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"71a63c3fa42f889333295fad7243a3fc7cd0131ea674c5edc5e50ab108f67e67","measurement_key":"19c03c33218943405d11fbec06ad1e6be2acb3bd3f3656d6be95f7b258cda300","metric":"performance_rating","protocol_fingerprint":"1e275173e9df9ea2c30f14c0e4badff4ff8640ece726084771e1affe20ef4804","run_fingerprint":"161cff83cf84783e5cf4644b5207e1e1e35376b7f65192fede1c11f8b9dca8ef","score":765.62,"score_display":"765.62","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a6a581cf3925bd5dfbd5710f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7d5534bae527b9c0bf40d2287f5bc8299c7fbc84ab5732f9b2c9a75305ae7978","measurement_key":"6a45165733b1c07ceee02bfb9820ef8d4325865dda30c37ca10ef42ab446226b","metric":"pass_at_2_accuracy","protocol_fingerprint":"54207793d4d27d8f38a115533712e157798c696fa5d5368797e5c8a606bbf29a","run_fingerprint":"c9c135b7c7708a93e4f6bd69bfc26b08e528026be7d67597f13e74ff3dc2f5fa","score":44.67,"score_display":"44.7","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_c6d6445cb7c06336b725fc29","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a5f00c260d83bfe46d6cb5b19f4c03a91cacedcdef26392ab55e44a0aaf6c4c0","measurement_key":"98a55bf44491a05d9b1d815f734467b7d07b03cf81ef52e707d0df8c634a080d","metric":"accuracy","protocol_fingerprint":"a5ac13d6ba1560e9e9fe4f99107a0952e138420cd6e6f9258afc35b2f41425cf","run_fingerprint":"d8a8d1f6ffa3a5f40bb48b65d58d9c22f84bfcb4bb6c58bac2ecd10baac0008c","score":4.859999999999999,"score_display":"5","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_476fbefcb74061bff19d00f4","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e6d79220af87f38316ce4993937d2c433236b6706f4e8a46b3f55c39a76974c6","measurement_key":"06cccb60297cc5e23dc7bf5407f65dada0b6d08719ad99c102b27c28a2de1767","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"86e93a76da0884a3309b1584eada007310fb0cb97bc017af17a94e9761f09b77","score":1457.2370395963933,"score_display":"1457","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0f408aa2a737e269f251bd52","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f019e923a0527f50215790c4e403ea68a192fae34ed665d996b5d1968c9276c5","measurement_key":"55208da0cf1e55d078bf7e87740ec5082c29a3e5a7e549085ac9ccae06024c2d","metric":"eci","protocol_fingerprint":"9760fb7bae977280edb83ad403592430cc08dde477d094c98a90c7e2bd228b3f","run_fingerprint":"ad702841814fe3dced480b594b625d0a00328060e12634736b7cffac13e0978c","score":145.79,"score_display":"145.79","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_85a8ec980f1ad054744d25c6","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"72a9cb01082e0fd66f3c54e8110738bb296de676f5c898feb6876b06d6112b3b","measurement_key":"8cfb4aa00d206a25400380d31806853cae5a3b960a96ae1ce391a3bfbf270e53","metric":"accuracy","protocol_fingerprint":"84bc7170d2cd2a10bf4063f3368c91dd9726ae1a51b414f3c065e088a9005833","run_fingerprint":"a80e977f69d13a35fa79988dc11a6577901e145a8a2b037bb83e864aca6b785d","score":83.333,"score_display":"83.33","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_c3d225c30664ec01fcf514bd","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle":{"benchmark_release_id":"release_fa9e908ac04b067eb00182d4","benchmark_version":"HLE official leaderboard","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":261,"at":"2026-02-13","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"31d766a61c06222f617f27f45763c8c99d237161d5bf21e26bf3118a45a69eaf","measurement_key":"ba7556eb3fd11376dd1c3b64cf594c0a6ce532f21e762e8085f486590a4b4ff2","metric":"accuracy","protocol_fingerprint":"e1f956386a97e6ba42a3c396757902d19f19cdabb10fcc91e345af5c771a2890","run_fingerprint":"8757c3359b588d8e3fa27fdc5b2a6a5e79ad0df932ae24be959ea4d9d548b96a","score":30.5,"score_display":"30.5","source":{"id":"hle","name":"Humanity's Last Exam","url":"https://huggingface.co/api/datasets/cais/hle/leaderboard?limit=200"},"source_authority_tier":"A","split_or_window":"published-leaderboard","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8bc699530339dcbdd472b963","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"C","evidence_rank":5,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"self-reported","verified_status":"self-reported"},"unit":"percent","verification_status":"self-reported"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2ca00aa602b75605dfa9d2f3f574962e397c56da4828973c5a12c826f4b39252","measurement_key":"233a280161d1418d5baf970cf230cc3fe3d3507d3c2cc2d4bde4fcc06d19651f","metric":"pass_at_1","protocol_fingerprint":"d9665a74984bdd9123ef1ef4b855a575fb8ce7e6e334a426b44b6f9ecd38e722","run_fingerprint":"6cad06ef23fbe63ecfd74c932f34baf0335335656fee697acf36ae3773a4a587","score":81.868,"score_display":"81.9","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_c3d225c30664ec01fcf514bd","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"01c280936861d78a3e8b9a5f26e744fe12a7892aa54ccf16935765ef850ce778","measurement_key":"d923315320e2e03eb93e88db06658d0422e5248067680c47e49a84b9bc3bf4ee","metric":"accuracy","protocol_fingerprint":"7255300ff750a1be144dd15aaf255edcd95b8de423a1eb180d93c718fe5ba721","run_fingerprint":"95ff32f07bf828895cd409262ad99985ce047610f3d7ddebd3f55ca708a87a9e","score":86.03,"score_display":"86.0","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_c3d225c30664ec01fcf514bd","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":261,"at":"2026-02-12T16:08:22.578Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"4d44ef488103f8e5036a165845d63c21677fbec90fe93aafcb3620d48a370c25","measurement_key":"080b9ed53f64de68826ce9acbe4ab1a670089d0728f547ca79c88d65f63aa409","metric":"mean_score","protocol_fingerprint":"24834bb9e849cfb43ac09a1b9c8e00f0dfb2ce51bb07c739eb6f0dcde7817da6","run_fingerprint":"af2d5632db64c19b400f78e46c1792f8cbd8f9ea4981c8b20bb760ec17174d6e","score":80.0,"score_display":"80.0","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_47f623c312e058af8554fde4","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"82ab2344b8802e3f31520111661afbf9bd10a5bd9e457d0c268ab8295f1c1663","measurement_key":"3e8041b8fcd70b3e651db67ed9cfd3392955f05fbc0f20624f1d74a495d2f0ce","metric":"accuracy_avg_at_5","protocol_fingerprint":"ba21d91c69b2bfb5562da24595fe712c6aa16a43bea96d18b26d0459c948a095","run_fingerprint":"3e9157f5e61fa7bf97e00c3c0bd45331c88d9ef47a5d34aad9efe800825b9a7b","score":53.2,"score_display":"53.2","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_927bf51b0edb096333435e1c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"efca3a916af92abec1f062e28449402df61683016645969bbb4851aa1572d17c","measurement_key":"2a3c0aa8b4977aefcb17805882241cc0d4ff14c68282d6f08677c1fd765cbc74","metric":"resolved_rate","protocol_fingerprint":"e5e1f04a928af175f9bb63792493818a8f4d5e94c6ffcdd00a598e6865f561d8","run_fingerprint":"cfd4e693216e3d7df05bff959e88caae82588e85c6710899b132b639c91bb564","score":71.4,"score_display":"71.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_c3d225c30664ec01fcf514bd","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"efca3a916af92abec1f062e28449402df61683016645969bbb4851aa1572d17c","measurement_key":"2a3c0aa8b4977aefcb17805882241cc0d4ff14c68282d6f08677c1fd765cbc74","metric":"resolved_rate","protocol_fingerprint":"e5e1f04a928af175f9bb63792493818a8f4d5e94c6ffcdd00a598e6865f561d8","reporting_origin":"organizer","run_fingerprint":"cfd4e693216e3d7df05bff959e88caae82588e85c6710899b132b639c91bb564","score":71.4,"score_display":"71.4","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_c3d225c30664ec01fcf514bd","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_7449132b5f078c71f23c26b5","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":245,"at":"2026-03-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"39af4b113159dd99644b030d734259a14ba4ec78dbafef15442807f608da7a95","measurement_key":"aabf91b47c7439749e6605f9c6bfa75bc2689de72e84b383de6361f9df6fe7eb","metric":"resolved_rate","protocol_fingerprint":"3a19811f492e0107b51dc9de4ab7d657eafc63c27b4c368713b29690d8fd2d14","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-02-15/2026-03-01":{"benchmark_release_id":"release_7449132b5f078c71f23c26b5","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":245,"at":"2026-03-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"39af4b113159dd99644b030d734259a14ba4ec78dbafef15442807f608da7a95","measurement_key":"aabf91b47c7439749e6605f9c6bfa75bc2689de72e84b383de6361f9df6fe7eb","metric":"resolved_rate","protocol_fingerprint":"3a19811f492e0107b51dc9de4ab7d657eafc63c27b4c368713b29690d8fd2d14","run_fingerprint":"7d6cdf91cf00098d20807b8d5fd993c19ce5780a669f1f5e519dc4c0adea7078","score":62.96296296296296,"score_display":"62.96","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-02-15/2026-03-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d4385bff71d0ba7da64cdc30","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"7d6cdf91cf00098d20807b8d5fd993c19ce5780a669f1f5e519dc4c0adea7078","score":62.96296296296296,"score_display":"62.96","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-02-15/2026-03-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d4385bff71d0ba7da64cdc30","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":247,"at":"2026-02-27","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"3ef7c6432ef6064baa419a68bd91a7ad41941afbc61ff08ce06213e51ef02a12","measurement_key":"2ccaddb25446be7f2d01d07ac72f0d8a354f5c5cc36ac5693927cb4125d5eadd","metric":"pass_1","protocol_fingerprint":"d56ddeb73571ba07e4be83089b0896e0f20a4d20ab1108fa0607d3706ea2a01c","run_fingerprint":"fb288f278955b3b9d506e1b53929591fbd647e671864b45a9bc55d17a1b2aef6","score":9.79,"score_display":"9.8","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ce13d8bd3f6566efc90ebe09","raw_label":"enabled","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"95c5f50e4f834d538747477f06bc4ef2202cc452738e82363bb8fd82621cb83e","measurement_key":"2a5417660c65e63a6eb5cc18d66a39a13b6156f2c03591b80f819e2fef3ce416","metric":"mean_final_balance_usd","protocol_fingerprint":"554f9877bfc4e217d97cca49b51d650a61d333d955822e66a234c870093a445d","run_fingerprint":"e6262b1eb3d735be11cc784679eb3728eec49e12f3b0bc10ee599c00af353148","score":4432.122000000001,"score_display":"4432.12","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_cf429bf4453c02a3a83fad37","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"888f2fbe69b06eedcd4ee90235b87212f2af83739c25120c77c4bf635bd81bad","measurement_key":"5dba41c10974918e0a72a27e34caae9cc7a774a6794b5d7af2b6c091c3dfbe72","metric":"score","protocol_fingerprint":"fbaf9d05cbc62c85cf56b0a4090fbe24f3ed44f21be79a7bddb66ef8597f7ade","run_fingerprint":"8747de58678dfd5f9193c700196d1fcf5f9d6da1e40f76c3c509a1fae798294b","score":23.359,"score_display":"23.4","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_c3d225c30664ec01fcf514bd","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e203b80d4475687a7f64cd50772b0e2e57151b069c2e8575d904811efee72595","measurement_key":"f4fc7056bbd7fd5fdf3d4e15eeac2760be034e48d1a3b9edf689ab346a1e947f","metric":"arena_score","protocol_fingerprint":"bba3a0a1773262918b49cea5234f83ecb793964f60b767df6d0e9a19c6bba4de","run_fingerprint":"d5042ff681871bd502ea77ee9159d1ec0dfb8a71589e55a79af6e4b95585d316","score":1435.569438296295,"score_display":"1436","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_fcf17c516dbc641b9250907f","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0274294a6c12935e0e768ca0d3c6ca7a4dc41ef7899119c31e7eae8216fc7c54","measurement_key":"fb21b098827d2229a988944e983c611635cd2632226d9bc63688231400274c8a","metric":"accuracy","protocol_fingerprint":"4c2a0f437452a47939588543ed5de59f8baa840b89d7cdfba721482c4cfae020","run_fingerprint":"689bd3af35d1ef34de07a75f5794fbb623177429e5f075da17219a465fa2d3c2","score":48.17,"score_display":"48.2","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_818aa5ca47a72c9303b2a24e","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"zai/glm-5","model_name":"GLM 5","parameter_count_active":null,"parameter_count_total":null,"provider":"Z.ai","selection_rank":96,"weights_status":"open"},{"cells":{"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8da819e49d5586377af1d75b39c3ab1402192d9812946d88c0372360dedbbefd","measurement_key":"7c7311fcf2c0214652a5961ce6329c66f6db66aecb9124296a39feabc370a885","metric":"pass_at_2_accuracy","protocol_fingerprint":"927a7a84c5b9eaaebb3c9c04a4e8184369edc2fa0aa7bae89f816e11c3f637c4","run_fingerprint":"60293b5967d2c3ece1adca411920a3ca1c26d511fe3b80023a1fb0846691612f","score":25.5,"score_display":"25.5","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0de451a2a2c91a817f1dd3ec","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ee22e98cebc6a8f3bae398f447e25fc8473985153bd9ada379d8d59498c8ecc3","measurement_key":"e82bf99fc4ae7fecb9aca64d1800cbabcd4fb545beb53e060bf1048f1520387d","metric":"accuracy","protocol_fingerprint":"6b9c2fd7654c4f0f9bfb026fcfc72a0b96661576340141c91daef92c4047280f","run_fingerprint":"7cdf20953c18e5700e7f6418d51533caa1ee0ff811f555789aa820b757537c44","score":13.61,"score_display":"14","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_beda1f27c08006aeb0f60b10","raw_label":"Thinking 32K","reasoning_enabled":null,"strategy":"token_budget","token_budget":32000},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0a92ab3fde14edf41463536976e2737b16db3768cb3c4969f2f439066140d108","measurement_key":"054954002a214d9570b51a0c6c660cd69611bbd23f66cce40567740e18702564","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"327a17f91a10e363cddbbfb564fb9000062e34d414791b4b57184c4674f7f0b5","score":1456.3246398176152,"score_display":"1456","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_cf2150debee34b4d5f1bf4b9","raw_label":"high","reasoning_enabled":true,"strategy":"token_budget","token_budget":32000},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"bfcl-v4":{"benchmark_release_id":"release_7d2560723dba9d549cd10b25","benchmark_version":"v4-ede5081a24bc","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":64,"at":"2026-08-28T22:03:18Z","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8013768229a3cc785b42af94b8f2abd61336905c5bf7a9e08793b3dd2fe792b5","measurement_key":"8be2470735c7cac759b8fd2c82aec0833a0fe989bea150374005cd2e6c495bee","metric":"overall_accuracy","protocol_fingerprint":"6a9c99bccbca11748bdf70a2bdd6eb864726c94bf4a029f84ab95898fe96d192","run_fingerprint":"5138670fb30340f44ea041f2b385ac1d9423726f5b82fa67b2e7658de6b09e92","score":73.24,"score_display":"73.24","source":{"id":"bfcl-v4","name":"BFCL V4","url":"https://gorilla.cs.berkeley.edu/leaderboard.html"},"source_authority_tier":"A","split_or_window":"overall","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_a5edc006937c8df2d2cc0448","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T13:43:54.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"2f162691456aee6435bc16e68a86d8a8dcde0fc116b87a0430868395e3486960","measurement_key":"333879667e7397245ca88c7b144a50ce78807289501af102b3c846aaf433953d","metric":"mean_score","protocol_fingerprint":"9e10fa9584f4d877af324f2420f4db6e051b664a3d633dc8e22aeea815a71a6f","run_fingerprint":"d4856e803f6701b17e6eb6b3b178339a4bc9361df2f02e66a76d59fe29343c80","score":6.0,"score_display":"6.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6a469e49a01c32309c33941b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:41Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bb3e72ef6a01474b23dbb3a421302af3988f00c2dda4ba67f6121a5a8b720922","measurement_key":"7799284b6d3aae46047faf83f90080c9f1f9ee7fb10ae8c30ebefbb16643e234","metric":"accuracy","protocol_fingerprint":"0dc06ea062155b9a4ba5cbf0d3ea98569889dd8b4f016dcf20079beca3db48cb","run_fingerprint":"a87022c58082620898f2d2e8786fc98054338a656ae805fcce087c680533a693","score":1.1428571428571401,"score_display":"1.1","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_3faedfeaf2b018b3d825930d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f0356247130976dd13fba619ec2b29704a06813cf5abe947616121b3d28f414e","measurement_key":"67df0a9bae80b2f4e74b6a4e22ee230f2949d813252c92f98f083e827126c846","metric":"eci","protocol_fingerprint":"59347700fac44206bb52fe80476be25aa9d8da91467d2e8dd0382d5ca6deb7e8","run_fingerprint":"ed5afd66f870c1901e22d636a5471cf71c3550ae42039606858174f52b63dda1","score":146.8,"score_display":"146.80","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d4c6e9282aafa0f6c5e6104b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":142,"at":"2026-06-11T21:10:25.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f11935c3b003fb2a4f6e004617bd1b082f3b7b10c842c1a17940a6e70dd35ed1","measurement_key":"cc5fb8a6c59ab94ca9a7ad679a86d92b4f99849fc3f69cf4cace663471b08d97","metric":"mean_score","protocol_fingerprint":"2ef49575354bf730e05acc6ad0cd5064457f40531f1dbdd9ad25e49f1ceedef2","run_fingerprint":"4a50bf3fd641df212b6a616f1e30a465db30ab659c5acc42521f53ff7379dfaa","score":23.859649122807017,"score_display":"23.9","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_34919f24dc735cc9bea725dd","raw_label":"thinking-32k","reasoning_enabled":null,"strategy":"token_budget","token_budget":32000},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":142,"at":"2026-06-11T21:10:25.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8329d1ded5feb70440816df5dcc2e63dc3cf204904f69672e339775f89c167b1","measurement_key":"0f55bc573c980711eb4b1901f13c95dfb3da093a1d9d8ad2d599d51286a598c7","metric":"mean_score","protocol_fingerprint":"b012c400b53926d881db508924e56cc34a6750fad8cb9a2c32cefa8a1c6bebd3","run_fingerprint":"3ffef1983586cb775cfded7875b1c400a74aecacb099609f5a0cef878a3b026a","score":2.4390243902439024,"score_display":"2.4","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1749eab61af56fe6c62ab77a","raw_label":"thinking-32k","reasoning_enabled":null,"strategy":"token_budget","token_budget":32000},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval":{"benchmark_release_id":"release_730527fa346470703bd19e21","benchmark_version":"GDPval official leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:05Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f6b38ea287a003bca656f4f20d6f595f4ec814e1a592ac6373c49421f1bdcba7","measurement_key":"92e5bf875da18b5f9bce2963ce34b1aa4113426c676bb583f6504951232f32f2","metric":"win_rate","protocol_fingerprint":"739dfefac2e9651bb5c3941cdd027d7dc9b413f02dc8f80441112582eb9505cb","run_fingerprint":"eb1ddddbe01d4883ee3575f694a340daaa0e6cf67b010e820664d30e8de76320","score":42.5,"score_display":"42.5","source":{"id":"epoch-gdpval","name":"Epoch AI mirror · GDPval","url":"https://epoch.ai/benchmarks/gdpval"},"source_authority_tier":"B","split_or_window":"expert-comparison-win-rate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2ef94f4849290d1cb68eb0ba","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"98ba99e50cf883dbff741b0063aeff69cd361d8ecde0bc6e19eec0e68b39e103","measurement_key":"152c989bfdcb1c779f21875ba70974383f953785582bac4de0dae597daf30c29","metric":"elo","protocol_fingerprint":"146ecd0614616970e59ca1f3b030d587e15097d46f410a08716a1dda9656be65","run_fingerprint":"49e883531384e48de606b1543f6e8ad30c1546a7e7d15bbafcbdc641a2e74eef","score":915.41,"score_display":"915","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_642e3a37222b1abf74918908","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9d3054c2c587c743ab50277961c2d4ba73a3371dd37cd7baad0b28032b504cf1","measurement_key":"dc4790716a5e0b889a5fccc0c3ee9a366c2ae423ff09f7d83100353baec12f4f","metric":"accuracy","protocol_fingerprint":"2c6ee499dbdf07f14ad443b7e13b5062c65a6b8a12fb81e1d2da59655aa6c4ae","run_fingerprint":"8dee653c1f35ff5eb7d2b91bbc230bed33d29b572849fcaba6dbc6f8d3891a59","score":81.633,"score_display":"81.63","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_642e3a37222b1abf74918908","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gso":{"benchmark_release_id":"release_176f07ea4e9e0b8dfeede990","benchmark_version":"GSO current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:04Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9f3898a313e2a8ea73acdcd9f468e11dc57826bd6be14876934f4e46eb2d44a3","measurement_key":"7aac572a71f60928de549e16ea340f7250eee54e797b762c8f69c80a7e19c97e","metric":"opt_at_1","protocol_fingerprint":"d0523de259379b25230c65ac521c8505beb7b2d3c498b5f68d64e26dccb9991e","run_fingerprint":"61e31c5724f9630cd74a92bb4eff6a83c54caf3bc1cc49aee004e140a7d37a0b","score":14.7,"score_display":"14.7","source":{"id":"epoch-gso","name":"Epoch AI mirror · GSO","url":"https://epoch.ai/benchmarks/gso"},"source_authority_tier":"B","split_or_window":"official-set-opt-at-1","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6590a3699935a47fe2f51b4c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5ebdb50f51a0678dc9402cdf99a643d154478236f5fd904cd135d164e5aa78b4","measurement_key":"a8399500023df5a8de33809394a006ef429ddcf4dd09dd131ed799219b80bd1c","metric":"pass_at_1","protocol_fingerprint":"aa69fb327b16920f19fd28a36f2d74136082ac628e2d40ab9e92dfabcb3c67cb","run_fingerprint":"6cf4dd7321c68ab4be76822b95cfb7f6a736aa1b80f0eae715f6328d29b4697e","score":72.996,"score_display":"73.0","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_642e3a37222b1abf74918908","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mcp-atlas":{"benchmark_release_id":"release_6481c5033c8c5bc6dab70199","benchmark_version":"MCP-Atlas April 2026 rescored protocol","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":319,"at":"2025-12-16T18:09:14Z","last_confirmed_at":"2026-11-01T07:28:08Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"e6d41069d3e7a5229e899d61a898f097213c20687d3191d1d5bf5d8845285199","measurement_key":"705f6d9e0e461c762ff7994149f44b49a9915600ef497baebd6b3cb97a189685","metric":"pass_rate","protocol_fingerprint":"88f5cfc098ca032089b6138a3758322e6a4b77cc94eed29020513bc0845f2363","run_fingerprint":"74226af9e382ca9ff39cdb457a0710e596e5df61a15dc62aa780974d2678c7dc","score":59.5,"score_display":"59.5","source":{"id":"scale-mcp-atlas","name":"Scale AI Labs · MCP-Atlas","url":"https://labs.scale.com/leaderboard/mcp_atlas"},"source_authority_tier":"A+","split_or_window":"all-1000-public-500-private-500","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_47645ffae78b747c6516878c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3ffa7c291ec9fcc518a2f184f5b9299a9e229a6fb96c09413d06b4ce5bddc46a","measurement_key":"514e34fe3e6813fe9ece0987d1d6ef70b502743db96f3a28b4c74f68c3ce41d3","metric":"accuracy","protocol_fingerprint":"fe3e35cb3d9898f9395a5e010edd85176dd26026ac66a23654a2298ecbaa5a88","run_fingerprint":"a50f6fb9a9011342347ef4dccc9bf8566f0cba2c89b6c07da8bb48146b55dbe1","score":87.357,"score_display":"87.4","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_642e3a37222b1abf74918908","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"94eb6729ba56d1aa51b0b4a728a4608d868d618164d10486dadc051a357bf951","measurement_key":"c6548523bc6882fa21ca5e76fb112dee00d75f3a404495e1adb2cada6ff81b25","metric":"accuracy","protocol_fingerprint":"acab67f0d779c48c32e1847f295c19d0ea2418192711a26094aa59ebd021a23a","run_fingerprint":"a6db2f818db5eccafc2802c3f413ec0e6c6bbde0602466cd3a9c78379fb9b0a1","score":79.306,"score_display":"79.3","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_642e3a37222b1abf74918908","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":18,"at":"2026-10-14T07:48:12Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"fd5cd324ad7f434402b8cbad97a1f1de75e112466d82632556a4033771974d49","measurement_key":"036b91ec242999b5c98c7c5f1fd60c31429a640152fdde066808fa5dc613420c","metric":"subproblem_accuracy","protocol_fingerprint":"17dab62fbce1564a83a9656d5ed96f4dab04756e23fd6b8fd62c27bb13d51030","run_fingerprint":"a51b216c47d6661d67e06f92044ce7bc48f329fc2d20d9a579fb68394b0773cf","score":45.717592592592595,"score_display":"45.7","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_6fe722919cfa837c93d9a4c3","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ae2bd244bdb1584ac5da3d0ce1c236fa8115b99a8ec665b8fb7ee06a98826130","measurement_key":"bd85ec6bd27cbdc2b7aadcded7fe156b54d96b0a966339c7fa11e23cf095696d","metric":"accuracy_avg_at_5","protocol_fingerprint":"5cd245fe69b46f91f733fb3a26f963748494b2b134260f93e466648553703f57","run_fingerprint":"3142e05b214523871a6bd1a3e09cfe70b6cbb178067cb1301a9066c5b04a2ecc","score":54.300000000000004,"score_display":"54.3","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8c431ef1c3357f4933de067d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":82,"at":"2026-08-10T22:42:10.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7212929dca6875e70f1d45e89b7f0b724df10e74185bacfa0e8b73c6dfb6e88d","measurement_key":"aec2aa3a1a499443cb2886127c208f55676b1bbf35a4b0f5b3b23a04208cee86","metric":"accuracy","protocol_fingerprint":"17365a273d377061f9af1db8b6ceea460b5ef524be9d11495cc86c480c6dae13","run_fingerprint":"5a8c6d572c6e46b19102287b076122ec781ec26e1dc13ed41e7b712e9dfc3881","score":23.7,"score_display":"23.7","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_1ce9cf4baebaf695f5b05969","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-live":{"benchmark_release_id":"release_9d2de9d5be7e9822af19f7b3","benchmark_version":"SWE-bench-Live Lite","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":125,"at":"2026-06-29","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"36cba32cffc68cf93eea67c914f50debcd4dce8e850ebecc1144a5918a862659","measurement_key":"8a5a6667cdc9152e0f0560bb62a4c981066cb660469cac21eb18e4541e1d3674","metric":"resolved_rate","protocol_fingerprint":"d33b6160d8c4f5486c61d6719087c8fc1608c55248bf81a1934a392463fb972b","run_fingerprint":"c65bd3ada82529bcd2795bbfca9a082dddebdabfe3904a0204fabb780c57c41f","score":12.0,"score_display":"12.0","source":{"id":"swe-bench-live","name":"SWE-bench-Live · Lite","url":"https://swe-bench-live.github.io/reports-0605.jsonl"},"source_authority_tier":"A","split_or_window":"lite-300-python","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4d43287ed026bd0acbdb0e15","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"09906b3fd9593b9471c0a993ebab84d5d8a904eb95005f73d014018efceb2d79","measurement_key":"d325a19152e78a2e1d166f761a1adeeb13da13908814956873cf268fcbda3e52","metric":"resolved_rate","protocol_fingerprint":"53806692743f1c24060f5200b18166415904dd2f1b3f27e3073b67829bc285e5","run_fingerprint":"5e3612fb5759c9b1136273503e9b2506bd47979da036a22618ef746da40af950","score":70.0,"score_display":"70.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_642e3a37222b1abf74918908","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"09906b3fd9593b9471c0a993ebab84d5d8a904eb95005f73d014018efceb2d79","measurement_key":"d325a19152e78a2e1d166f761a1adeeb13da13908814956873cf268fcbda3e52","metric":"resolved_rate","protocol_fingerprint":"53806692743f1c24060f5200b18166415904dd2f1b3f27e3073b67829bc285e5","reporting_origin":"organizer","run_fingerprint":"5e3612fb5759c9b1136273503e9b2506bd47979da036a22618ef746da40af950","score":70.0,"score_display":"70.0","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_642e3a37222b1abf74918908","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"swe-rebench-v2":{"benchmark_release_id":"release_f0409f3e3e823115a9e78774","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":245,"at":"2026-03-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"fb2797a42649e5118de073994352126ab96b85c093ab401f0fee5d5e675abb9f","measurement_key":"95416131e715432c1949e95960b1f8df6174a2ea80e4f85a3a295b5f7f9389f9","metric":"resolved_rate","protocol_fingerprint":"afa1c5db8191e3968fbe9572001c1e06f3535024e3785db30a617ee2b341f91b","run_fingerprint":"f80df3436e6ca59bfa5b94d001f53be83c97dba213069c91e7e77a983d9e66e5","score":54.0,"score_display":"54.00","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2025-10-01/2026-03-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_8a4d978fd009422ee97e7041","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"tau3-banking":{"benchmark_release_id":"release_dc4a6b19eb552354004439bf","benchmark_version":"1.0.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":250,"at":"2026-02-24","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"6e03c270dd636117b551c23cc07598fd4e4652911cca75ab264bc32eb8e9fae5","measurement_key":"e4a88039cdfe8053de444d7e4eb9e53e1d461f494740aca33853a0628096a15c","metric":"pass_1","protocol_fingerprint":"ff01b22ab20c5e42ea4cd21f5a09af629c356c4279c5f9921d42a8a43e64b968","run_fingerprint":"8a773c0b52f5437bef7e0c4f4bab22e33138911aa1b6564948ca0979e706d35d","score":25.26,"score_display":"25.3","source":{"id":"tau3-bench","name":"τ³-Banking","url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/web/leaderboard/public/submissions/manifest.json"},"source_authority_tier":"A","split_or_window":"banking_knowledge","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4a73c29927d902c07689647e","raw_label":"enabled","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-submission","verified_status":"official-submission"},"unit":"percent","verification_status":"official-submission"},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c1268e0d69edc2d740b6d73036d76fa28d19039e785028fa461d5ca8f5ce34da","measurement_key":"76abd68c279946f93f16bbfbc0fb4541f39ddd84cc6f9772772188c0e91419f0","metric":"mean_final_balance_usd","protocol_fingerprint":"990637a02b64bd8eac62a2e1fc535612686efac216914c730ecfc273dbc4f6ad","run_fingerprint":"71ebe1de50c6a5879a8d6174b987ad2428aabf5de3518be4a985144988badbd8","score":3838.7400000000002,"score_display":"3838.74","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_f2188ef14be4e31531958a1b","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:23Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a0b5dcd6b67298f4bd74cffaab849221ada76f2a8cef45555d580351884b746c","measurement_key":"af0749af739721a4566c082c98da02f1488eab2a8c69a181709b6c2178851586","metric":"score","protocol_fingerprint":"7017681f55118948ad1826539c971c51957609d993b961c5955a8d66b14cc6f2","run_fingerprint":"b2356f238ca389c149d24431ac4e040639e7eaa5e382d9e435aac21afd03c3f0","score":22.621,"score_display":"22.6","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_642e3a37222b1abf74918908","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3b82186e54a8332ab295ef4d5c6068fc9a6627d1c55ab26449ed6446f8a1498b","measurement_key":"9d3f576128ad4acb8eb6adfe0162be0f9cc6b989f99b41be145dee5f6440e929","metric":"arena_score","protocol_fingerprint":"3bfc93b849f4dd2f1976e05b3db4a8c9679101d1975e4377e856af36a85d3bcd","run_fingerprint":"c9f0b41a61f16d9cdb650db728adfcaa4926a22a1092ecaf429fd72a0e70f317","score":1393.5404164128754,"score_display":"1394","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_cf2150debee34b4d5f1bf4b9","raw_label":"high","reasoning_enabled":true,"strategy":"token_budget","token_budget":32000},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"6bbd151c4a04421ab456de1ecfaae3128940c94597cfa5274e19f4f04eb69e2c","measurement_key":"a00f47e7dd05f1c099e6b3afdf79290d4951e649f8fd6cf54eced1d72d7c5f46","metric":"accuracy","protocol_fingerprint":"ec89876074787b4343e85caed455c416b2dc7bd739646f50439caa15ac87e753","run_fingerprint":"fc83ea6eaf3e6c1a1444a5b219dac4f8527cea7e0f57530fb6949dd9495a2979","score":46.7,"score_display":"46.7","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_ccf30264fde8350df3c208b8","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"anthropic/claude-sonnet-4-5","model_name":"Claude Sonnet 4.5","parameter_count_active":null,"parameter_count_total":null,"provider":"Anthropic","selection_rank":97,"weights_status":"closed"},{"cells":{"ale-bench":{"benchmark_release_id":"release_a4c08439e33767077f5fed9a","benchmark_version":"ALE-Bench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:01Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8a6e98ece7d8cd69519f91f59574ee5ff008d622c4ec8e2b7a8c207373c0afe5","measurement_key":"4714fa76ec91008289fc097394869e39e53463897238e734e40f48ec5316afa8","metric":"performance_rating","protocol_fingerprint":"a6d89d9cdc6b737bffc5b0b25b7cef378a9abd72faf61acd5608974604fa4ad6","run_fingerprint":"aa96670f674d6a2c3b277e8fca43aec98a0c1c7505cb7011d6692d2edbeaf255","score":1192.15,"score_display":"1192.15","source":{"id":"epoch-ale-bench","name":"Epoch AI mirror · ALE-Bench","url":"https://epoch.ai/benchmarks/ale-bench"},"source_authority_tier":"B","split_or_window":"atcoder-heuristic-contest-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"points","verification_status":"official-secondary-verification"},"arc-agi-1":{"benchmark_release_id":"release_2e65e63d3852e53d984c2949","benchmark_version":"ARC-AGI-1 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:47Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f76d75f319838d97c8a4d7d69b3212b7fc629d361685c39dd6e174a9ca7110ef","measurement_key":"99b2ef3500a6e859c583989457c69edf56658e30b2540104df2900077ff9884b","metric":"pass_at_2_accuracy","protocol_fingerprint":"eb04a4be031c049fb589d6777a50cf93f1483a73693dc20532c216d64482e27e","run_fingerprint":"4b18a6af4725f0f92e149f88e91e3dc344284b4d189d37647169e2aac6777dfe","score":72.83,"score_display":"72.8","source":{"id":"epoch-arc-agi-1","name":"Epoch AI mirror · ARC-AGI-1","url":"https://epoch.ai/benchmarks/arc-agi"},"source_authority_tier":"B","split_or_window":"semi-private-evaluation-pass-at-2","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"arc-agi-2":{"benchmark_release_id":"release_1e2eafde2dbfd20577b0aed1","benchmark_version":"v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":65,"at":"2026-08-27T22:30:41Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8262c9cfc169a68e3b698746caf974e04a1e7f8f0368c6fa7af6707ee9e72131","measurement_key":"fd32e49ffef60de37bc8a7623f79cd35b55db9f57ba38a953d95cae675ce6d4c","metric":"accuracy","protocol_fingerprint":"e1fad15c71d90a914eccc3e146a77b63abce2bec16f2cf125a4be0372e9d72e1","run_fingerprint":"57a50c0d19780d4fcda3edaedabb572293761706401e12bdd96eb36084686463","score":17.64,"score_display":"18","source":{"id":"arc-agi-2","name":"ARC-AGI-2","url":"https://arcprize.org/media/data/leaderboard/v2.json"},"source_authority_tier":"A","split_or_window":"semi-private-120","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-verified-leaderboard","verified_status":"official-verified-leaderboard"},"unit":"percent","verification_status":"official-verified-leaderboard"},"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e49492e214d5fa0427e3abd97c56928022f897a22b1a2f0ec95e0fd5ecf0db74","measurement_key":"3ebe46ce4ed213dc3fbe5b12d2a7eafca1c71283d17f228e64ecfa4acdf7104c","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"dbb76fa691d33c2b6198205a92f9fc854672443f25c69c1be0a535a2099dac67","score":1455.7030125963045,"score_display":"1456","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"chess-puzzles":{"benchmark_release_id":"release_9f5f95bd857f9929b98d6528","benchmark_version":"Epoch AI Chess Puzzles v2","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":18,"at":"2026-10-13T14:05:29.000Z","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"433e49fe271a4b36fe4879342a91a79eabd3c94919b546a3e8b1fe6c8e864f26","measurement_key":"451b8adea2d6083e83ae0bd50cac098974b37a7b05da3ba956ef7fa7ef68bfc0","metric":"mean_score","protocol_fingerprint":"431454578a2ed48fcee7e4c783986d5645a5b8ea55481c258c71960e1aebfc95","run_fingerprint":"63af0784aa6e30312dfd994d8e0f55dac567cebbfffa468ee032be5f425d8108","score":42.0,"score_display":"42.0","source":{"id":"epoch-chess-puzzles","name":"Epoch AI · Chess Puzzles","url":"https://epoch.ai/benchmarks/chess-puzzles"},"source_authority_tier":"A","split_or_window":"100-engine-generated-single-best-move-puzzles","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"critpt":{"benchmark_release_id":"release_079aaa34e0885e15655a2847","benchmark_version":"CritPt current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:41Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"378a2a9f7260eb4fb0e6c0898e78ab5252779204789533624d380525179b9a59","measurement_key":"5577e50b68a5491118ff40e1cc21121af88be02075da21a5ae7b4cf9fd065f09","metric":"accuracy","protocol_fingerprint":"0853f78b9e289cc0e250f444712e8dd3a8901363a4379256fd72468a457f8cae","run_fingerprint":"14606e3cbfc292ef554859437b362d228284e9c022b89612d223194c834f45c3","score":4.857142857142859,"score_display":"4.9","source":{"id":"epoch-critpt","name":"Epoch AI mirror · CritPt","url":"https://epoch.ai/benchmarks/critpt"},"source_authority_tier":"B","split_or_window":"71-challenges-checkpoint-accuracy","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"16f5db136a914e70b7d600003a0aea4d890592770d5290b567df48fbdb66e1f8","measurement_key":"147c408a9582350948025fa7a20dc8f193ff19da8d9c66c5f95d217abc82946f","metric":"eci","protocol_fingerprint":"a204e15366cc10c1300dac03f6867aa02125b761018aa4f31d9ddc2b0079cd80","run_fingerprint":"4883a85c0c0558ab849243f948352a1e47c94b4dfd1c5bef8bbd0df10f7311b1","score":149.89,"score_display":"149.89","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_feeea085ab7763bb52bc3cc1","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":1,"at":"2026-10-31T04:32:28Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"8f30bfa4e32dbe85773a3c2ef50565ff7d135cccb42c9cf9e314eef8ef7a21c7","measurement_key":"c89b834f6072e1534f64246ea724c040cac3fb2cd64bff8dd413e2e5b563712e","metric":"elo","protocol_fingerprint":"b7aaa2498276050a4a4bfd46e4fc628034454fa6aafc3a2397d0f4e61bcf8229","run_fingerprint":"c68fe87f3f9f299aee31757dff57fb40083c5e1fe694f1b8a5495597eb238754","score":833.9,"score_display":"834","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"804708f17f8d8eb8f8febf0d2fbd79392b9857808583986b61c48930a930e757","measurement_key":"394e585778fd416ddf61b41f347f29ba941cc42ba0d6c3fc7211321d1cae1e8a","metric":"accuracy","protocol_fingerprint":"46906de3aae232bf19a1e0f1d696a6c4ed7f2312c92b10fe40be1db74ed195e4","run_fingerprint":"81c799ff2e8136ae5981937a95c37df96d72ade6b3b3777e1d98fce3a58ef5ef","score":86.616,"score_display":"86.62","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gso":{"benchmark_release_id":"release_176f07ea4e9e0b8dfeede990","benchmark_version":"GSO current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:04Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c36ed8c687ac44142c5a7fdea3aca464866573846f2f460225c9bbfe36f91694","measurement_key":"ccec37b922ccaf3d378f85d54157153418846c78ecebcd7c341dce5eb58e7362","metric":"opt_at_1","protocol_fingerprint":"01cb454390bd6d82cb9a851b14464ba4a4864e6d59cf0d74408c793b8ea05cf4","run_fingerprint":"335601fd4d05cdebc6f3bf5b73fa70c4779482c0e216fdb8ecb9f5c18af8351a","score":13.700000000000001,"score_display":"13.7","source":{"id":"epoch-gso","name":"Epoch AI mirror · GSO","url":"https://epoch.ai/benchmarks/gso"},"source_authority_tier":"B","split_or_window":"official-set-opt-at-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"hle":{"benchmark_release_id":"release_8817af9d9a0235bce0826e22","benchmark_version":"HLE finalized 2,500 · Scale protocol 2025-04-03","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":339,"at":"2025-11-26T20:24:19Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"4ae26b9b961e97e6984a8e7d7de4efe083da9f1a3e83c8a4bc9b6d6816396819","measurement_key":"2c89555eb91b4126d8e3111b4a53d65aa225a55ac2714a7e7ff8de6671506ed0","metric":"accuracy","protocol_fingerprint":"ad5d94d9572f3f245f60c65ee55dca44e3045a8bdd46fcf6dcf8427c80ab0037","run_fingerprint":"1cd402eb6c2eb9f5808ed554446782b0fc49195dc984ef5f2358fef7f2eed9bc","score":23.68,"score_display":"23.68","source":{"id":"scale-hle","name":"Scale AI Labs · Humanity's Last Exam Full","url":"https://labs.scale.com/leaderboard/humanitys_last_exam"},"source_authority_tier":"A+","split_or_window":"full-multimodal-2500-no-tools","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_e92c503ca7d7c630bd73c098","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":3,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"baadaf1f2639d51842977c6da657ada986e5160c7063766dd778d454c8e6fa52","measurement_key":"8b31c330de7b745894b0a1aeb92b8bbfb8141216785e28ee799abf28339ba548","metric":"pass_at_1","protocol_fingerprint":"4195f0cb3428db1894426c72ad20b08f45ffcff313c8bf87dc83ee9259ea1ff6","run_fingerprint":"42eb3e8a62e4e7918213f5c48bedc7defeda2f4166be00e71a9003502f9df62e","score":86.486,"score_display":"86.5","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"de2540af20000fd9188239e78f7ed56be44eee2f2c37f06a56f0f0820505d65b","measurement_key":"cf406f970d518302f7c4a081a5e6ad3586c5770fb5ac881d01676884d997899b","metric":"accuracy","protocol_fingerprint":"c598aacf77ca73dc50388c6275f2354c7cca6b36686847370e3441ecec78a574","run_fingerprint":"2d1178e8fdd84308fb320679e2a334043a4b6b3abb6bed7ecf9b01ca751e8a90","score":86.377,"score_display":"86.4","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:41Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b7bdc66f77a01d7e6a1b9da44f1075eab2980612ba5ae3e01f1fe3c572911e82","measurement_key":"b372b70a6c6c0e96a038613586b5d87e6ba56539004125f1cd049f374e578528","metric":"accuracy","protocol_fingerprint":"44f96346dd2bd4fd48185f9c3b6d15fff4b677f23aa919d70d1d3aab0ed42b0b","run_fingerprint":"7be23ad7025b7368bde36ad1e9905de4959ed90c4f2bb6118b1d44a00538e339","score":83.179,"score_display":"83.2","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"otis-mock-aime":{"benchmark_release_id":"release_071fe253e79f87573f6d22b0","benchmark_version":"2024–2025","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":352,"at":"2025-11-13T19:52:15.595Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"25f32caf886ecd5df67d252529348d2ae06e37575799439f8934b9ff994ea7b1","measurement_key":"1b1305c8ac70f9084b221f88841a916707e25204c8516e8db2fee99f9c8b90eb","metric":"mean_score","protocol_fingerprint":"b2b66eb3c4c6788182a673f4582d4c4e64ce5ea5e7355e9721b1b7a059b65779","run_fingerprint":"3c1ddf04203780ef8da5d2e6a94451a2af97d2e372256417a0c231dad923ace4","score":88.61111111111111,"score_display":"88.6","source":{"id":"epoch-otis-mock-aime","name":"Epoch AI · OTIS Mock AIME 2024–2025","url":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025"},"source_authority_tier":"A","split_or_window":"official-45-problem-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_6d948ae7a2a0a695cbdf21f9","benchmark_version":"SciCode current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":64,"at":"2026-08-28T22:47:54Z","last_confirmed_at":"2026-11-01T07:28:09Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d54fbe3f82015faf316c4ce7595093835df1880935e3047bffa2c4b2e3c161a5","measurement_key":"7225023a4c86ea71319e6bcbfadb638d7929f6a470854a37e1f814f9ba34cfe8","metric":"subproblem_accuracy","protocol_fingerprint":"b1c2fa312286f3d10996ed85c71f12bd264c20e0b9ccbc43fe486fd6e266e88b","run_fingerprint":"e5dd38cfe41185fd2973437e9c46a5977bafd16e50abdd3e03bb7291f7a3dfeb","score":43.287037037037,"score_display":"43.3","source":{"id":"epoch-scicode","name":"Epoch AI mirror · SciCode","url":"https://epoch.ai/benchmarks/scicode"},"source_authority_tier":"B","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3dfbb43cf68157a8244eb7e79f3e5c496aa11fadec681da6affc9a92c56f2838","measurement_key":"4f88c0c330e039a22a6111a2c58bb9f6232dc8f99ca33e728e567d7812cc11c0","metric":"accuracy_avg_at_5","protocol_fingerprint":"2ef4f664bc752406a303de62e789284339a6581f4537d42978aa376d823bcc66","run_fingerprint":"4b16b3334fa01221f540df867cbc586722bf73c953dd1c4b07cf17d1a322e8c7","score":53.2,"score_display":"53.2","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"simpleqa-verified":{"benchmark_release_id":"release_7bf989f19fbe70ed22a4a50b","benchmark_version":"Epoch independent Inspect runs","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T19:28:24.000Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"66ef421f73e537432bca3f44986bd95511bba32bf4619ac84d7d356826a145d3","measurement_key":"441d781bb2379107b8f1f96283fbb7ef422151ce0130552b145f85028ebb00d6","metric":"accuracy","protocol_fingerprint":"5ad4fb8ad8c4948f2431ce9816a32c2e10e39c3605456ba246ae3d4dc99f004d","run_fingerprint":"c335dcf0dd43872eb06f5c4ddd5d319ce5a844a29dd65031235db8e61faa9f76","score":48.0,"score_display":"48.0","source":{"id":"epoch-simpleqa-verified","name":"Epoch AI SimpleQA Verified","url":"https://epoch.ai/benchmarks/simpleqa-verified"},"source_authority_tier":"A","split_or_window":"verified-1000-epoch-inspect","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"swe-bench-verified":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1e1d682678f5810ac425368fa48599ce788aa0dd1e53f2da9f4b3fdd80d663e6","measurement_key":"f35c7969ce0a1a485ba38e9767b80dcc271b0602acf70bba7fec250ea31188ba","metric":"resolved_rate","protocol_fingerprint":"362b7ad838f32f83ba9345c2d0bc89e59f922a2565c2143c2e9cf194c867206f","run_fingerprint":"184f2c0059aa038dc3729bd7a73f2578a3e6f12c062a30d1aa58f98e39e77268","score":69.8,"score_display":"69.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":{"benchmark_release_id":"release_2242ce390e0c2cd53f1b3a5b","benchmark_version":"SWE-bench Verified v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":65,"at":"2026-08-27T22:30:44Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1e1d682678f5810ac425368fa48599ce788aa0dd1e53f2da9f4b3fdd80d663e6","measurement_key":"f35c7969ce0a1a485ba38e9767b80dcc271b0602acf70bba7fec250ea31188ba","metric":"resolved_rate","protocol_fingerprint":"362b7ad838f32f83ba9345c2d0bc89e59f922a2565c2143c2e9cf194c867206f","reporting_origin":"organizer","run_fingerprint":"184f2c0059aa038dc3729bd7a73f2578a3e6f12c062a30d1aa58f98e39e77268","score":69.8,"score_display":"69.8","source":{"id":"vals-swe-bench-verified","name":"Vals AI SWE-bench Verified","url":"https://www.vals.ai/benchmarks/swebench"},"source_authority_tier":"B","split_or_window":"verified-500-vals-mini-swe-agent","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"}}},"vending-bench-2":{"benchmark_release_id":"release_143d5eb012c28bfa29646c4c","benchmark_version":"Vending-Bench 2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:59Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"192b502afef0b6480f37700041c06c2bb2a22ecb10051d10395de1eac7c5e89f","measurement_key":"f21f665ed7b92f7169234babb5a074f1918d00c5803826b17084ee618954d598","metric":"mean_final_balance_usd","protocol_fingerprint":"b2fc64da721ffa54d136f2e30205fd93a251d487411373d4ee28a27083d42d9d","run_fingerprint":"ab877d14ba4a4b3f6a4a4fe2680927867c451e624165f39403d9b68f42004269","score":1473.432,"score_display":"1473.43","source":{"id":"epoch-vending-bench-2","name":"Epoch AI mirror · Vending-Bench 2","url":"https://epoch.ai/benchmarks/vending-bench-2"},"source_authority_tier":"B","split_or_window":"one-simulated-year-mean-final-balance","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_cd54c0156f4acd0d4d181e31","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"USD","verification_status":"official-secondary-verification"},"vibe-code-bench":{"benchmark_release_id":"release_ee527953b92b7b6f6f1beb2d","benchmark_version":"Vals Vibe Code Bench v1.1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:47:44Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"21d6583342d88d7030ced45fd0326058260ec135f1b6438c4b2955ab1e0b234b","measurement_key":"657fb2cbf877514b7f75cefdada04fb1049fd99ccd6fa677abd19bb9a9d5f780","metric":"score","protocol_fingerprint":"e5bd652018221cf6cd3467f3047d879aeeaf3fdb89c340ec95e6c8bfd9b97456","run_fingerprint":"489c244c1ee48b39f9fa01abda4854cabbd7604e90ac7ad67ff120c0c802d8a4","score":24.606,"score_display":"24.6","source":{"id":"vals-vibe-code-bench","name":"Vals AI · Vibe Code Bench","url":"https://www.vals.ai/benchmarks/vibe-code"},"source_authority_tier":"B","split_or_window":"vals-vibe-code-bench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"a93b918a1a998e2c3f9454260b7ca0ad9bdb1cb19a97cf7ec41ece2826309fff","measurement_key":"d31990a4f1fdd01ca2f701044ab3129e8c0595cec8b8a2a00dd32528c697de3f","metric":"arena_score","protocol_fingerprint":"2b9f0cbce594c67913005d67f3a3ba04b9bf59f9c186a74a7120602e3306f4dc","run_fingerprint":"d8ad86118f77d58db75f14ecaa73f44fd0574f82e700be2b404db6b65006366a","score":1395.6212231615589,"score_display":"1396","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"medium","profile_id":"profile_01f55deedf8de2a463a745ff","raw_label":"medium","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"weirdml":{"benchmark_release_id":"release_ed6368cba447631077bb553f","benchmark_version":"WeirdML v2 current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:51Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1cb557284cca5802dafff3b02871cc031f4dd051f1946b9f6893b881bafc7e47","measurement_key":"080e963d3253241bb6393fc48620e6df404d62f61769a7aaeb2b53c2a62433d5","metric":"accuracy","protocol_fingerprint":"b6a4d86486624be5cca6ad8599ec08e1124238eb955a20cfbad728c24bd3796c","run_fingerprint":"db4df31bc3468e838bc271f6716f5a964d2967748678a908aa80e9147814b5d2","score":60.77,"score_display":"60.8","source":{"id":"epoch-weirdml","name":"Epoch AI mirror · WeirdML","url":"https://epoch.ai/benchmarks/weirdml"},"source_authority_tier":"B","split_or_window":"weirdml-v2-task-set","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"high","profile_id":"profile_30f1bfb383c02c782db74a79","raw_label":"high","reasoning_enabled":true,"strategy":"fixed_effort","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"}},"local_open_weight_essential":false,"model_id":"openai/gpt-5-1","model_name":"GPT 5.1","parameter_count_active":null,"parameter_count_total":null,"provider":"OpenAI","selection_rank":98,"weights_status":"closed"},{"cells":{"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"86aea1fca4eb86a9ce2aed76c636f4f5c58798758048dd5327362dad05c6fea3","measurement_key":"2d8f8455afbc3b83fb3765251eb415a656f6b22442d0a19efa5a849e27a557ed","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"2110659971275710a2cdc28dd4d8441b312fab8e7397c41349e1c3486d8e1824","score":1452.2892381987065,"score_display":"1452","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_2a1871ad8f8b32a3d2496758","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"critpt":{"benchmark_release_id":"release_a71cc2d98bd454276f8e6ed8","benchmark_version":"CritPt (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"cd9d46e1d9af609be3d03ec63dc9ebad06c33b482869487068ddcef4421d863d","measurement_key":"2a78c6cece5bc95f07b221c8602737b84b2e28e53dcd8a25226cc4550d21b19f","metric":"accuracy","protocol_fingerprint":"bf184735759ce0ec8d6d8a0b14c6c8cc329f4d58b343218f782a125f7345b2a2","run_fingerprint":"a098cd1640d608908838e6aafb9a1b8dff4544a87b30252b586b7323f706d024","score":1.428571,"score_display":"1.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"70-challenges-official-grading","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_19bb152ad555330fda392da5","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval-aa-v2.1":{"benchmark_release_id":"release_2b38a48aaf3cb40aca8959b1","benchmark_version":"GDPval-AA v2.1 (Crowd-BT Elo, DeepSeek V4.1 Flash (max) at 1600)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":2,"at":"2026-10-29T17:25:13Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3429e7b1eff53c331a19ad5f402b4fa366b258bccf30428011ca229659c6722d","measurement_key":"f03e8028123d2470c868bd3b22e723c9487ef90b85b51fd16814758f458bc940","metric":"elo","protocol_fingerprint":"938eed1e68edafc7a732bfad1af0285e449fdba9d99fa3fe2e2d11aa7e40f617","run_fingerprint":"d572c9507b03fcef28c7e5c5ec5edb4cc8d17eebae1b7cee6254e6e09255af3d","score":626.77,"score_display":"627","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/evaluations/gdpval-aa"},"source_authority_tier":"A","split_or_window":"220-tasks-elo-v2-1","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_19bb152ad555330fda392da5","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"points","verification_status":"independent-evaluation"},"gpqa-diamond":{"benchmark_release_id":"release_f83cfc2a9e19b8d654d7b58e","benchmark_version":"GPQA Diamond (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"0258091482e3712468d5a7ce2dace3dfb71f0b5e6bea5a9147faa29c532ce2d2","measurement_key":"f4e33053b6234bf4c13746cd033cac2635a8457b26273a16ff53f5729ed50c04","metric":"accuracy","protocol_fingerprint":"077fb0f0faab782835c9f7bfe28335643bb93776086bf93c619e68f7e2781fb6","run_fingerprint":"1437bf75f3ce05b9467adc8add10dd652b9e5109a133d9c3cf3b8c45cd316e69","score":85.656566,"score_display":"85.7","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"diamond-198-zero-shot-5-repeats","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_19bb152ad555330fda392da5","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"hle-text":{"benchmark_release_id":"release_def1fd244db3612317ca0108","benchmark_version":"HLE text-only (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T00:52:24Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"b7253125f049e261eefebbac239d0cf90be3605356f662b49205a48bfa04c785","measurement_key":"6a7e42bcdc0dbaa5f5d003371835175e06a78b3fa7af986e3c96c42e5ba35fa0","metric":"accuracy","protocol_fingerprint":"3b696e35852ae8aeca6f62ba64b68adde47e8a9657c04c50073322ab819e730c","run_fingerprint":"2098aed4017bebd26ae1fddc25e519b325d3a04760a38e49746c2dfb6882e0be","score":23.632994,"score_display":"23.6","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"text-only-2158-no-tools","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_19bb152ad555330fda392da5","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_46396ea50bd4792fc96cf001","benchmark_version":"MMMU-Pro (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"bb916308dcfd798993d968a74b0b67c88ff6bc278e787bd08868a870cd2ef68d","measurement_key":"4358d044fa1fac44f2acc3855dc478fe0d9c778a0b931ddb6a4ce69367569af6","metric":"accuracy","protocol_fingerprint":"8c5883ee3cfeab07c88669ed8d7bc36ab78c038c79412e35b4694c92c6776797","run_fingerprint":"1add8432d15b90efce68a7907fe9707fcccd79ce811fd1615afd74cb22de86f4","score":73.410405,"score_display":"73.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"aa-mmmu-pro","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_19bb152ad555330fda392da5","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"scicode":{"benchmark_release_id":"release_de40c66bd40a7b5483b40f9a","benchmark_version":"SciCode v1.0.1 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":56,"at":"2026-09-05T17:21:27Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9403844b3ec158662a799c2a9f37244dac80ba6f62dc91f904dd717c338a79cf","measurement_key":"8c785228bbf8765694f74b61a0b2ce8811c121bc17fa7dfd2d2f52f76c2b92b9","metric":"subproblem_accuracy","protocol_fingerprint":"bc01027d39523f00a61ff825a56baa1605c8f518dd718bba3bd0fceafe2c05b4","run_fingerprint":"bf6cdf859bf19d922ae01cce0b64128bc87b92e7172c4791369597a4808a700c","score":45.486111,"score_display":"45.5","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"scientific-research-coding-subproblems","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_19bb152ad555330fda392da5","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"simpleqa-verified":{"benchmark_release_id":"release_ccacd6f679c9142b534364b4","benchmark_version":"task-v7","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":152,"at":"2026-06-01T11:15:20.646874Z","last_confirmed_at":"2026-11-01T07:28:14Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7fce75697ae036d6fbf22299042bf87a2e97fcd6873217c0cfc32a830b8dbf37","measurement_key":"e8627ab2fcf720fe58237e43f1b1a2d7df3c7fdccd4f06730e99f54159b1e88d","metric":"accuracy","protocol_fingerprint":"80ee7690245a67a4e25f4db6369059e8b8b8fe3bad89432648ac923f3b47c398","run_fingerprint":"e613ea24e26a9c6d3025330ccd588f61dd4c343add3fa7b3563930238ce8bd71","score":10.683760683760683,"score_display":"10.7","source":{"id":"simpleqa-verified","name":"SimpleQA Verified","url":"https://www.kaggle.com/api/v1/benchmarks/deepmind/simpleqa-verified/leaderboard"},"source_authority_tier":"A","split_or_window":"verified","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_d495975af2f81492de3a7940","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":0,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"percent","verification_status":"official-benchmark-platform"},"swe-rebench-v2":{"benchmark_release_id":"release_1f8553cc12d8235844f1a578","benchmark_version":"rolling-v2","comparison_lane":"supplemental-post-release-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"929bd5982ea3d47d29cc9bb1c2c8461e12257f6b7edd487f5b820ed41052bd1b","measurement_key":"010698a05b33bf08c6fc16924c0a4f6ad5cc659f8d20caa344198419801219e0","metric":"resolved_rate","protocol_fingerprint":"716d95b37f928778ed736abc0cc74aaf85e769a20276a1ac7fbf52aecae953dd","rebench_views":{"comparison_rule":"same_window_only","current_window":"2026-05-15/2026-07-01","windows":{"2026-03-01/2026-05-15":{"benchmark_release_id":"release_72d764965dd7baf34f983249","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"C","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"9baa992e40e44e8157887dffa15a8cb647275ac6603e1283721ba4487353692d","measurement_key":"825b2ad88f663e07f847e3f959f96aec16e2653eb15f556805d4d02432b16771","metric":"resolved_rate","protocol_fingerprint":"662332765a9ebff9d2aaab450af1ab776ec950df89e06593ae06276be1656580","run_fingerprint":"66cf164e2efad81b244d8f41b0a907427bbea2eed398aade8eb8f07e752cfbb3","score":16.545454545454543,"score_display":"16.55","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-03-01/2026-05-15","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_95be02b559104aaf55501db0","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"C","evidence_rank":7,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"potential-contamination","verified_status":"potential-contamination"},"unit":"percent","verification_status":"potential-contamination"},"2026-04-15/2026-05-15":{"benchmark_release_id":"release_1f8553cc12d8235844f1a578","benchmark_version":"rolling-v2","comparison_lane":"supplemental-post-release-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":170,"at":"2026-05-15T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"929bd5982ea3d47d29cc9bb1c2c8461e12257f6b7edd487f5b820ed41052bd1b","measurement_key":"010698a05b33bf08c6fc16924c0a4f6ad5cc659f8d20caa344198419801219e0","metric":"resolved_rate","protocol_fingerprint":"716d95b37f928778ed736abc0cc74aaf85e769a20276a1ac7fbf52aecae953dd","run_fingerprint":"7fb574026c65a7c2dd145513da22ab30597fc39d6ee1375c86ef6fc6b323e56b","score":16.410256410256412,"score_display":"16.41","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-04-15/2026-05-15","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_95be02b559104aaf55501db0","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"}}},"run_fingerprint":"7fb574026c65a7c2dd145513da22ab30597fc39d6ee1375c86ef6fc6b323e56b","score":16.410256410256412,"score_display":"16.41","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2026-04-15/2026-05-15","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_95be02b559104aaf55501db0","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"tau3-banking-aa":{"benchmark_release_id":"release_786d72c2e6dda7b72acc4040","benchmark_version":"τ³-Banking (Artificial Analysis)","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":58,"at":"2026-09-04T09:03:13Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"1fa3c0cfe05a8a2838fd4440b289329bf51d685a1b4d725608f6eab5f3a53035","measurement_key":"e2076e91ff8714847fa7b35bde698591cb03dc8fa4a170f706f18943d30024a4","metric":"pass_at_1","protocol_fingerprint":"726cb0966b46b174339f6cf4f1aaef8a6160b2984ccd900ccdd9c3f3b084c43e","run_fingerprint":"3f555090c12b141c2ffd74e65e706f005b466baebc654c71548860d9505c8cc9","score":14.845361,"score_display":"14.8","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"banking-97-tasks-gpt-5-4-mini-simulator","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_19bb152ad555330fda392da5","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-2.1":{"benchmark_release_id":"release_c53c830678318dc1763793c8","benchmark_version":"Terminal-Bench 2.1 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T13:33:07Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"ad885264f77518f7b1b6fada5377b9894026e0d3edd4c4a356c07896fc723ec9","measurement_key":"714f6c43643fc9dbdf12a677e241abd62ef123d15aa3bea6248338955caf1583","metric":"pass_at_1","protocol_fingerprint":"17028b2a7321b4d1be03b6756ded6e84f7faf259b747db3071110df727184327","run_fingerprint":"dee374054f2358005bb1a6660380071aeb1ca31b80e008e1c3d8647d2a4d5094","score":43.445693,"score_display":"43.4","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"terminus-2-89-tasks","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_19bb152ad555330fda392da5","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"terminal-bench-4":{"benchmark_release_id":"release_b7d9ab744ffac0cb856e114d","benchmark_version":"Terminal-Bench 4.0 (Artificial Analysis)","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":10,"at":"2026-10-21T23:21:17Z","last_confirmed_at":"2026-11-01T03:42:30Z","source_freshness":"current","source_observation_age_hours":5.64,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"889f19bc21527a943215164c273f14c14794dd4586a78ca8b7a1a695f11511fe","measurement_key":"1117144de971ad3fcda81ce33755e4106189c0041406f0e32b9d4e50f4e09c00","metric":"pass_at_1","protocol_fingerprint":"7ba5119d29b93344b7a8f6da0817d11aa98b8ccebf254c12ef9825cf15af5b3a","run_fingerprint":"bbac00547575b721314e0a95821c96ed5a47accef34c83953bb2214443c14e1c","score":0.0,"score_display":"0.0","source":{"id":"artificial-analysis","name":"Artificial Analysis · Intelligence Index evaluations","url":"https://artificialanalysis.ai/leaderboards/models"},"source_authority_tier":"A","split_or_window":"mini-swe-agent-66-tasks-500-steps","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_19bb152ad555330fda392da5","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"c8d0c0a1f3e09c8ee633624df33b28a2692dd43e59313a46ef2338ce1eaaaec9","measurement_key":"3e15a4ae570e827e122ea060cee6657ef20dc5c36e6197b8837d12d50ce618c1","metric":"arena_score","protocol_fingerprint":"d9ab878fcc878ac812cc8fd92c382609692e2b534ea037af912dd4f876d6dcfe","run_fingerprint":"d83b532e70e8319cb250bc802515bfa174b674000b6b80e932bc1ec062fdf6c5","score":1368.6624108190852,"score_display":"1369","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_5156ce72059ef2337abe25ad","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"google/gemma-4-31b","model_name":"Gemma 4 31B","parameter_count_active":null,"parameter_count_total":null,"provider":"Google","selection_rank":99,"weights_status":"open"},{"cells":{"arena-text":{"benchmark_release_id":"release_482c53e63fe96f7e715bb0f5","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:12Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"72e0c0ccb95d4237c31a4d257ee3ef5ce25a35a65c5537bc3b92afff28d5a607","measurement_key":"ef5a7e07c5eb249da69461a119043f80c33cc7c3fee44b837c497872a9314216","metric":"arena_score","protocol_fingerprint":"ffbf0922679e4aa0b4bec1c541f932b1c512061f56ecc5ebc569b49807caa020","run_fingerprint":"4a00f5535e91d873e919708539862c3f160986d6e3e874673ccbe8ebf2980286","score":1448.0134195918026,"score_display":"1448","source":{"id":"arena-text","name":"Arena Text","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/text_style_control/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-style-control","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_aa1f16a5a40da24207af00f4","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"},"epoch-eci":{"benchmark_release_id":"release_139e6a0a9905605b7ed14674","benchmark_version":"Epoch ECI snapshot 2026-11-01","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":0,"at":"2026-11-01","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7a4b2e954616e1c4c333900913747f029f9ce4046c502991d5a4cbd00c70fd43","measurement_key":"c8d4e758a6a51181d1a402c3a8002cc7f67df260ff1c62ba35881b70dd1f977d","metric":"eci","protocol_fingerprint":"14226ff6d4f36f6d9b6090b420212bce2e20f6b6260c7e70d44f9d3063be385c","run_fingerprint":"394eaf4e505928b34bd3b6e864c45c01fa3989e30c69a5a60f506211e1893d53","score":143.93,"score_display":"143.93","source":{"id":"epoch-eci","name":"Epoch Capabilities Index","url":"https://epoch.ai/eci"},"source_authority_tier":"A","split_or_window":"official-composite-fit","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_887d48f324f77d968eaecc1d","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":5,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-benchmark-platform","verified_status":"official-benchmark-platform"},"unit":"index_points","verification_status":"official-benchmark-platform"},"frontiermath":{"benchmark_release_id":"release_fd01c0ab187a88391c43ea9f","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":142,"at":"2026-06-11T21:15:07.000Z","last_confirmed_at":"2026-11-01T07:28:06Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"73d80f61332f67f221690497baf00e9a255c88726901d12384669bc86a50e3d9","measurement_key":"44ee08067376d208a4bd74c7b4002dd7032e55aae00bb810a3f46821ab4c89ca","metric":"mean_score","protocol_fingerprint":"5b3536a86ff25f5a7597b213ff2cdf948aea0b0996d8daccf3472da9e0577a56","run_fingerprint":"5c06bd1da8dc65637d368f43918015a17243ca5236184fa131a6aede0d3faf81","score":12.631578947368421,"score_display":"12.6","source":{"id":"epoch-frontiermath","name":"Epoch AI · FrontierMath Tiers 1–3 v2","url":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2"},"source_authority_tier":"A","split_or_window":"private-285-of-295-problem-tiers-1-3-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_01129548b25adbb9776ec287","raw_label":"thinking-32k","reasoning_enabled":null,"strategy":"token_budget","token_budget":32000},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"frontiermath-tier-4":{"benchmark_release_id":"release_4d025b5eeb2f6b23fd7b19cb","benchmark_version":"2.0.0","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":142,"at":"2026-06-11T21:15:07.000Z","last_confirmed_at":"2026-11-01T07:28:07Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"5ea1f355eaa80b08ae1ae1426cdf49266c9d9b65cac51bca91a5fbeeac260b71","measurement_key":"7753a346ed008fcc48379cf6b34ba876bc8923a5780b9b6b69177aa5fb58989d","metric":"mean_score","protocol_fingerprint":"ae135bcb39223edd49e0623f9c0ce7bc8c33cf3ee2ca71e01b0b431feced8c16","run_fingerprint":"34c9f7d5feface035ef6a54552b5116d139f70d7e68d53c809242bad9f61f4e6","score":2.4390243902439024,"score_display":"2.4","source":{"id":"epoch-frontiermath-tier-4","name":"Epoch AI · FrontierMath Tier 4 v2","url":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2"},"source_authority_tier":"A","split_or_window":"private-41-of-43-problem-tier-4-set","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_539047413da7106e5111873d","raw_label":"thinking-32k","reasoning_enabled":null,"strategy":"token_budget","token_budget":32000},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"gdpval":{"benchmark_release_id":"release_730527fa346470703bd19e21","benchmark_version":"GDPval official leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:27:05Z","last_confirmed_at":"2026-11-01T07:28:11Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"d1fe3e2c4bf2762a2383f9414bf420890571b0c430274fee462ef793796c5ca6","measurement_key":"6a4644b9ff4d7cfb81ee60ef3b0d08b0d85ebf6b5bdf2937c46cf47a68dcd4ad","metric":"win_rate","protocol_fingerprint":"2b9517ae4828c51845ede7bca6aadbc8eb35e299be4327218a6131dee37ed9fb","run_fingerprint":"955814e05796e63726cdea69007c67fd84c8ecabc11973ba8519e95ddf3ff289","score":43.6,"score_display":"43.6","source":{"id":"epoch-gdpval","name":"Epoch AI mirror · GDPval","url":"https://epoch.ai/benchmarks/gdpval"},"source_authority_tier":"B","split_or_window":"expert-comparison-win-rate","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_73ca51c1241eb639e187e8eb","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"gpqa-diamond":{"benchmark_release_id":"release_aa2f2a6181ec4d1bc71a32f8","benchmark_version":"GPQA Diamond v1 · Vals dual-prompt","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":62,"at":"2026-08-30T23:35:12Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"e31e32663a242cac00eb00ed785e1f65436621148e12c2b868b95eb0deaff73c","measurement_key":"a1bbbd3315a7d787a6385aefd9a11e575583f833ac2e3486556990a8076017af","metric":"accuracy","protocol_fingerprint":"d0e5c8fe1e46628e66d220e813b80a61c67420010f87ce00aaad4d7aac448d42","run_fingerprint":"8cb8f3536ddc1bf09d87d525f1b7d1ed198749f77148cb5314cd3f9effd5d20a","score":76.263,"score_display":"76.26","source":{"id":"vals-gpqa-diamond","name":"Vals AI GPQA Diamond","url":"https://www.vals.ai/benchmarks/gpqa"},"source_authority_tier":"B","split_or_window":"diamond-198-zero-and-five-shot-cot","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_99dd806d3a14424dd2a38e68","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"livecodebench":{"benchmark_release_id":"release_a2492ed53dd6d8c4d33d5ae5","benchmark_version":"Vals LiveCodeBench v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:32Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"3c694f1bee4db4a8476981048f361cfdc1ca70954a659f4a213034e5ebfd5f90","measurement_key":"abb5a8e014378faf1acbe5cfc54bfb79a8ef61ad1bdfc5e297462684993b7f0f","metric":"pass_at_1","protocol_fingerprint":"a93d4c3dde012a7d2fb80c568e83c4c7745915c2757016dd2d0fb1a39ff361da","run_fingerprint":"b98cb153d75b2486bff8be384096e06862f3815a518b77a122f8c5d27e9fbd20","score":66.456,"score_display":"66.5","source":{"id":"vals-livecodebench","name":"Vals AI · LiveCodeBench","url":"https://www.vals.ai/benchmarks/lcb"},"source_authority_tier":"B","split_or_window":"vals-livecodebench-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_99dd806d3a14424dd2a38e68","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmlu-pro":{"benchmark_release_id":"release_187c8201a49a6385bb527d7d","benchmark_version":"Vals MMLU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":59,"at":"2026-09-02T09:40:37Z","last_confirmed_at":"2026-11-01T07:28:16Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"f2512b4b94e058422aadc8361a1f21e7e1d622042a10aa99e845774cca603bd9","measurement_key":"53ccb246b9f07756da33e5abefbbd943a23c71f239c4a978b338dbfe9db0ea4f","metric":"accuracy","protocol_fingerprint":"65862a584a4422b9d9ef6c99a9d4fef3b04b48a3e7c375f14406331208167a33","run_fingerprint":"68199229cb5c90078b16ff6989933af6b824f5e92dfbb0693d41b36deadbbc2c","score":87.924,"score_display":"87.9","source":{"id":"vals-mmlu-pro","name":"Vals AI · MMLU-Pro","url":"https://www.vals.ai/benchmarks/mmlu_pro"},"source_authority_tier":"B","split_or_window":"vals-mmlu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_99dd806d3a14424dd2a38e68","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"mmmu-pro":{"benchmark_release_id":"release_c4828ed5eb385de228d39263","benchmark_version":"Vals MMMU-Pro v1","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A","freshness":{"age_days":23,"at":"2026-10-08T22:23:22Z","last_confirmed_at":"2026-11-01T07:28:17Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"eedaddb7adc349bd6dd5afa8ee94e4f4fe0d33318e5521ba5d773bf5920c32aa","measurement_key":"35b57ea1275aea57e8e33886f9ec1caf6b3fc151aa5df6bb6f5405feed8d6b73","metric":"accuracy","protocol_fingerprint":"1dc13b2caaf2b852bef31bf6ea73b3bab0bdc1b0693a254502b57a105da24c42","run_fingerprint":"e936072964a06c00397553515f6b1935d52f185754768fae3b1318e63f83ce8a","score":77.514,"score_display":"77.5","source":{"id":"vals-mmmu-pro","name":"Vals AI · MMMU-Pro","url":"https://www.vals.ai/benchmarks/mmmu"},"source_authority_tier":"B","split_or_window":"vals-mmmu-pro-overall","thinking":{"disclosure_status":"observed","is_provider_default":false,"normalized_effort":"adaptive","profile_id":"profile_99dd806d3a14424dd2a38e68","raw_label":"adaptive","reasoning_enabled":true,"strategy":"adaptive","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation"},"simplebench":{"benchmark_release_id":"release_af5e4653e36272fb4c37bce2","benchmark_version":"SimpleBench current leaderboard","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"B","freshness":{"age_days":59,"at":"2026-09-02T09:26:45Z","last_confirmed_at":"2026-11-01T07:28:10Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"13f05786427f998de535c10418ee499b5b1db5fae5ef8d36177cb832f6e1df96","measurement_key":"fa5e12a7a51b4719ca5a81595d6c2f2a10ea61356719720f928117266cd4c1ee","metric":"accuracy_avg_at_5","protocol_fingerprint":"56504c70f5d45eef26f9b98e3fb6f9f02f5f3a2076da3de5c1556a7ca296352b","run_fingerprint":"6b2c522046cad1c232c0bebc6e1cce4f8d18e4538238d206f994be990979c780","score":60.0,"score_display":"60.0","source":{"id":"epoch-simplebench","name":"Epoch AI mirror · SimpleBench","url":"https://epoch.ai/benchmarks/simplebench"},"source_authority_tier":"B","split_or_window":"official-set-avg-at-5","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_dfc3eed7d38c3a0d0a68268a","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":6,"evidence_grade":"B","evidence_rank":3,"source_authority_rank":2,"source_authority_tier":"B","trust_rank":2,"trust_tier":"B","verification_status":"official-secondary-verification","verified_status":"official-secondary-verification"},"unit":"percent","verification_status":"official-secondary-verification"},"swe-bench-verified":{"benchmark_release_id":"release_ab91f0254cf52d5b135599b2","benchmark_version":"Epoch independent runs","comparison_lane":"supplemental-source","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A","freshness":{"age_days":262,"at":"2026-02-11T21:33:53.502Z","last_confirmed_at":"2026-11-01T07:28:15Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"eb9348120b6b5399bc7f2916104f0a8ece71cf01f039a6619b6c6f8b94a90c3d","measurement_key":"fa3eb7617775cc36d4788069dd7b0d137b382bec363fcb784b05a0e784728e9f","metric":"resolved_rate","protocol_fingerprint":"a2b04faf2230205e13b4c801da0beea2e8239f0cb8ddc3954f0007d9771dd68b","run_fingerprint":"391888eea54099d97dece71c99690601bb5a1cda21cb09c7bbb6c0a3a29cd99b","score":73.34710743801654,"score_display":"73.3","source":{"id":"epoch-swe-bench-verified","name":"Epoch AI SWE-bench Verified","url":"https://epoch.ai/data/benchmark_data.zip"},"source_authority_tier":"A","split_or_window":"verified-484","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_832ee21d16c8e7eaa53c7f7c","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":1,"evidence_grade":"A","evidence_rank":1,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"independent-evaluation","verified_status":"independent-evaluation"},"unit":"percent","verification_status":"independent-evaluation","views":{"reported_system":null,"strict":null}},"swe-rebench-v2":{"benchmark_release_id":"release_e8fc75e5c8482265dbca3d4c","benchmark_version":"rolling-v2","comparison_lane":"supplemental-prior-window","conflict":null,"directly_comparable":false,"display_role":"other-supplemental","evidence_grade":"A+","freshness":{"age_days":335,"at":"2025-12-01T00:00:00Z","last_confirmed_at":"2026-11-01T07:28:18Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"stale"},"higher_is_better":true,"measurement_id":"c59ed59dc77980cb9cab597acd02da0e58240ba1e5d0a74df6415e4b36bc1a66","measurement_key":"1b8e76bf6b6e99a223d7eba80993a86025b9772086b216cff24d1463b5348380","metric":"resolved_rate","protocol_fingerprint":"122b54f28b6294368d79a290bafcab91ec40542b45f7262adfc41a652c854b80","run_fingerprint":"0bcd0ff83cf8dbf795666b3b01cd87a0be2bc0433dd24521f2ecc20138ad87fb","score":43.46193271829281,"score_display":"43.46","source":{"id":"swe-rebench","name":"SWE-rebench","url":"https://swe-rebench.com/"},"source_authority_tier":"A+","split_or_window":"2025-09-01/2025-12-01","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_4efca96ee4b3e901a2b47082","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":2,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":0,"source_authority_tier":"A+","trust_rank":0,"trust_tier":"A+","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"percent","verification_status":"official-leaderboard"},"webdev-arena":{"benchmark_release_id":"release_254ac63a5db19f0802d10f9f","benchmark_version":"2026-10-28","comparison_lane":"canonical-source","conflict":null,"directly_comparable":true,"display_role":"exact","evidence_grade":"A+","freshness":{"age_days":4,"at":"2026-10-28","last_confirmed_at":"2026-11-01T07:28:13Z","source_freshness":"current","source_observation_age_hours":1.88,"source_observation_status":"current","status":"fresh"},"higher_is_better":true,"measurement_id":"7b194f6079c9005fc070d934cda6bbfbdccd889862cea27a67302d7356339204","measurement_key":"685748e2114ccb77065a9ae575ba73a51fea2f1b88e096839fb7dd3b80e8413a","metric":"arena_score","protocol_fingerprint":"d818bf781585955b264603ddf7816ce1a68a99d200a5e6e6c703d1ecdd0823be","run_fingerprint":"c40e3ea20f0d9467d1d15468eef16aa07ce4d64a6917244d84716fbac0caef40","score":1390.1558311618264,"score_display":"1390","source":{"id":"arena-webdev","name":"LMArena WebDev Arena","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/323062f70843f40e3f739865c3fe9d806126e412/webdev/latest-00000-of-00001.parquet?download=true"},"source_authority_tier":"A","split_or_window":"overall-code-arena","thinking":{"disclosure_status":"undisclosed","is_provider_default":false,"normalized_effort":"unknown","profile_id":"profile_0447edc48ed9dd787c5b6bc9","raw_label":"reported","reasoning_enabled":null,"strategy":"unknown","token_budget":null},"trust":{"date_rank":4,"evidence_grade":"A+","evidence_rank":0,"source_authority_rank":1,"source_authority_tier":"A","trust_rank":1,"trust_tier":"A","verification_status":"official-leaderboard","verified_status":"official-leaderboard"},"unit":"points","verification_status":"official-leaderboard"}},"local_open_weight_essential":false,"model_id":"anthropic/claude-opus-4-1","model_name":"Claude Opus 4.1","parameter_count_active":null,"parameter_count_total":null,"provider":"Anthropic","selection_rank":100,"weights_status":"closed"}]}