{"api":"v1","id":"frontier.clock","title":"Benchmark saturation clock","section":"frontier","row":"benchmark","page":"https://jesseahawkins.com/frontier/","fields":[{"name":"benchmark","type":"string","tier":null},{"name":"released","type":"string","tier":null},{"name":"superseded_by","type":"string","tier":null},{"name":"reached_90_on","type":"string","tier":null},{"name":"days_to_90","type":"number","tier":"derived"},{"name":"first_model_at_90","type":"string","tier":null},{"name":"its_score","type":"number","tier":"quoted"},{"name":"best_score","type":"number","tier":"quoted"},{"name":"best_model","type":"string","tier":null},{"name":"days_running","type":"number","tier":"derived"},{"name":"page","type":"string","tier":null},{"name":"source","type":"string","tier":null}],"tiers":["quoted","derived"],"provenance":"Scores as Epoch AI publishes them; the day counts are this site’s.","freshness":{"state":"due","asOf":"2026-11-12","oldestCheck":"2026-10-30","next":"2026-11-06","late":"2026-11-13","status":"https://jesseahawkins.com/status/","sources":["frontier"],"notice":"Due: the source of Arena leaderboards and benchmarks (LMArena, Epoch AI) publishes new data on 2026-11-06, or did already. This site last checked it on 2026-10-30. It is late from 2026-11-13."},"rowCount":15,"terms":["CC BY 4.0"],"checked":"2026-10-30","nextCheckBy":"2026-11-06","links":{"rows":"https://jesseahawkins.com/data/v1/datasets/frontier.clock.json","csv":"https://jesseahawkins.com/frontier/clock.csv","releases":"https://jesseahawkins.com/data/v1/datasets/frontier.clock/releases.json"},"latestRelease":{"id":"2026-10-30","date":"2026-10-30","sha256":"feed8ea9b018c92f91f0ceaa16c6fecec07ad5c09885efd07059358a01a9cf44","json":"https://jesseahawkins.com/data/v1/datasets/frontier.clock/releases/2026-10-30.json","csv":"https://jesseahawkins.com/data/releases/frontier/clock/2026-10-30.csv"},"csvSha256":"feed8ea9b018c92f91f0ceaa16c6fecec07ad5c09885efd07059358a01a9cf44","matchesLatestRelease":true,"rows":[{"benchmark":"FrontierMath-Tier-4-v2-Private","released":"2026-06-12","superseded_by":null,"reached_90_on":"2026-06-12","days_to_90":0,"first_model_at_90":"claude-fable-5_max","its_score":0.902,"best_score":1,"best_model":"gpt-6.1-sol_max","days_running":null,"page":"https://jesseahawkins.com/frontier/","source":"Epoch AI, Capabilities & benchmarking, retrieved 2026-10-30. CC BY 4.0"},{"benchmark":"FrontierMath-Tiers-1-3-v2-Private","released":"2026-06-12","superseded_by":null,"reached_90_on":"2026-09-01","days_to_90":81,"first_model_at_90":"claude-fable-5-1_max","its_score":0.9017543859649123,"best_score":0.9368421052631579,"best_model":"gpt-6-astra_max","days_running":null,"page":"https://jesseahawkins.com/frontier/","source":"Epoch AI, Capabilities & benchmarking, retrieved 2026-10-30. CC BY 4.0"},{"benchmark":"OTIS Mock AIME 2024-2025","released":"2024-12-19","superseded_by":null,"reached_90_on":"2025-08-07","days_to_90":231,"first_model_at_90":"gpt-5-2025-08-07_high","its_score":0.9138888888888889,"best_score":1,"best_model":"gpt-5.5-pro-pre-release_xhigh","days_running":null,"page":"https://jesseahawkins.com/frontier/","source":"Epoch AI, Capabilities & benchmarking, retrieved 2026-10-30. CC BY 4.0"},{"benchmark":"GPQA diamond","released":"2023-11-20","superseded_by":null,"reached_90_on":"2025-11-18","days_to_90":729,"first_model_at_90":"gemini-3-pro-preview","its_score":0.9261363636363636,"best_score":0.9640151515151515,"best_model":"gemini-4-argon_high","days_running":null,"page":"https://jesseahawkins.com/frontier/","source":"Epoch AI, Capabilities & benchmarking, retrieved 2026-10-30. CC BY 4.0"},{"benchmark":"MATH level 5","released":"2021-03-05","superseded_by":null,"reached_90_on":"2024-12-17","days_to_90":1383,"first_model_at_90":"o1-2024-12-17_high","its_score":0.947129909365559,"best_score":0.9813066465256798,"best_model":"gpt-5-2025-08-07_high","days_running":null,"page":"https://jesseahawkins.com/frontier/","source":"Epoch AI, Capabilities & benchmarking, retrieved 2026-10-30. CC BY 4.0"},{"benchmark":"SWE-Bench verified","released":"2024-08-13","superseded_by":null,"reached_90_on":null,"days_to_90":null,"first_model_at_90":null,"its_score":null,"best_score":0.8347107438016529,"best_model":"claude-opus-4-7_max","days_running":808,"page":"https://jesseahawkins.com/frontier/","source":"Epoch AI, Capabilities & benchmarking, retrieved 2026-10-30. CC BY 4.0"},{"benchmark":"FrontierMath-2025-02-28-Private","released":"2025-02-28","superseded_by":"FrontierMath-Tiers-1-3-v2-Private","reached_90_on":null,"days_to_90":null,"first_model_at_90":null,"its_score":null,"best_score":0.524,"best_model":"gpt-5.5-pro-pre-release_high","days_running":609,"page":"https://jesseahawkins.com/frontier/","source":"Epoch AI, Capabilities & benchmarking, retrieved 2026-10-30. CC BY 4.0"},{"benchmark":"FrontierMath-Tier-4-2025-07-01-Private","released":"2025-07-11","superseded_by":"FrontierMath-Tier-4-v2-Private","reached_90_on":null,"days_to_90":null,"first_model_at_90":null,"its_score":null,"best_score":0.479,"best_model":"gdm-ai-co-mathematician","days_running":476,"page":"https://jesseahawkins.com/frontier/","source":"Epoch AI, Capabilities & benchmarking, retrieved 2026-10-30. CC BY 4.0"},{"benchmark":"SimpleQA Verified","released":"2025-09-09","superseded_by":null,"reached_90_on":null,"days_to_90":null,"first_model_at_90":null,"its_score":null,"best_score":0.76,"best_model":"gemini-4-argon_high","days_running":416,"page":"https://jesseahawkins.com/frontier/","source":"Epoch AI, Capabilities & benchmarking, retrieved 2026-10-30. CC BY 4.0"},{"benchmark":"Chess Puzzles","released":"2025-12-10","superseded_by":null,"reached_90_on":null,"days_to_90":null,"first_model_at_90":null,"its_score":null,"best_score":0.76,"best_model":"gpt-6-astra_promax","days_running":324,"page":"https://jesseahawkins.com/frontier/","source":"Epoch AI, Capabilities & benchmarking, retrieved 2026-10-30. CC BY 4.0"},{"benchmark":"MirrorCode","released":"2026-06-26","superseded_by":null,"reached_90_on":null,"days_to_90":null,"first_model_at_90":null,"its_score":null,"best_score":0.7889,"best_model":"claude-opus-5-5_high","days_running":126,"page":"https://jesseahawkins.com/frontier/","source":"Epoch AI, Capabilities & benchmarking, retrieved 2026-10-30. CC BY 4.0"},{"benchmark":"EBR-bench","released":"2026-07-01","superseded_by":null,"reached_90_on":null,"days_to_90":null,"first_model_at_90":null,"its_score":null,"best_score":0.780952380952381,"best_model":"gpt-6.1-terra_max","days_running":121,"page":"https://jesseahawkins.com/frontier/","source":"Epoch AI, Capabilities & benchmarking, retrieved 2026-10-30. CC BY 4.0"},{"benchmark":"Mystery Game Puzzles","released":"2026-07-30","superseded_by":null,"reached_90_on":null,"days_to_90":null,"first_model_at_90":null,"its_score":null,"best_score":0.84,"best_model":"gpt-6-astra_max","days_running":92,"page":"https://jesseahawkins.com/frontier/","source":"Epoch AI, Capabilities & benchmarking, retrieved 2026-10-30. CC BY 4.0"},{"benchmark":"Furniture Assembly","released":"2026-09-23","superseded_by":null,"reached_90_on":null,"days_to_90":null,"first_model_at_90":null,"its_score":null,"best_score":0.8333333333333334,"best_model":"claude-opus-5-5_max","days_running":37,"page":"https://jesseahawkins.com/frontier/","source":"Epoch AI, Capabilities & benchmarking, retrieved 2026-10-30. CC BY 4.0"},{"benchmark":"SpireClimb","released":"2026-10-14","superseded_by":null,"reached_90_on":null,"days_to_90":null,"first_model_at_90":null,"its_score":null,"best_score":0.25666666666666665,"best_model":"gpt-6-astra_max","days_running":16,"page":"https://jesseahawkins.com/frontier/","source":"Epoch AI, Capabilities & benchmarking, retrieved 2026-10-30. CC BY 4.0"}]}
