OpenAI / MODEL EVIDENCE
2 benchmarks · 3 observations · 2 sources
2 benchmarks · large dot: o3-mini-2025-01-31; small dots: closest models where reported
o3-mini-2025-01-31_high · FrontierMath-2025-02-28-Public · FrontierMath public · 10 questions · source run score · Epoch AI · public February 2025 sample · historical release ↗
11.3% · o3-mini-2025-01-31_medium · FrontierMath-2025-02-28-Public · FrontierMath public · 10 questions · source run score · Epoch AI · public February 2025 sample · historical release · A Rosetta Stone for AI Benchmarks — released Epoch evaluation runs ↗
o3-mini-2025-01-31† · Overall difficulty-adjusted Brier index ↗
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
There are not enough shared scored settings to identify close comparisons reliably.
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
o3-mini-2025-01-31_high · o3-mini-2025-01-31_medium · o3-mini-2025-01-31†