OpenAI·released 2024-09-121 source
o1-mini benchmark scores: 11 benchmarks tracked. 36% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 11 benchmarks·best result 89.18 on MATH level 5 (reproduced)·4 of 11 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| MATH level 5 | 89.18accuracy (%) | reproduced· optimizedT1 | 2024-09-12Epoch AI |
| Lech Mazur Writing | 64.9accuracy (%) | unverifiedT1 | 2024-09-12lechmazur/writing Github repository |
| GPQA diamond | 49.83accuracy (%) | reproduced· optimizedT1 | 2024-09-12Epoch AI |
| OTIS Mock AIME 2024-2025 | 46.89accuracy (%) | reproduced· optimizedT1 | 2024-09-12Epoch AI |
| WeirdML | 36.32accuracy (%) | unverifiedT1 | 2024-09-12https://htihle.github.io/weirdml.html |
| Aider polyglot | 32.9accuracy (%) | unverified· optimizedT1 | 2024-09-12https://aider.chat/docs/leaderboards/ |
| ARC-AGI | 14accuracy (%) | unverified· optimizedT1 | 2024-09-12ARC Prize Leaderboard |
| Cybench | 10accuracy (%) | unverified· optimizedT1 | 2024-09-12Cybench leaderboard |
| FrontierMath-2025-02-28-Private | 3.02accuracy (%) | reproduced· optimizedT1 | 2024-09-12Epoch AI |
| SimpleBench | 1.72accuracy (%) | unverifiedT1 | 2024-09-12SimpleBench Leaderboard |
| ARC-AGI-2 | 0.83accuracy (%) | unverifiedT2 | 2024-09-12 |
Claims drawn from cited facts, not live model generation.
This model was developed by OpenAI and released in 2024, continuing that developer's line of general-purpose language models.
2 cited facts
This model is evaluated across 11 tracked benchmarks, and it currently holds no top score on any of them. Because those results have been independently reproduced, the record can be trusted as verified rather than vendor-reported.
3 cited facts
On the disclosed harness, the model trails the state-of-the-art leader by an average of 58.03 points, a wide gap that places it well behind the front of the pack. It does not hold the top score on any tracked benchmark, so there is no category leadership yet.
2 cited facts
1 facts cross-checked across data sources: 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks
o1-mini is an AI model developed by OpenAI, released 2024-09-12. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
o1-mini has recorded scores on 11 benchmarks, each shown with its evidence status.
o1-mini has recorded scores on 11 benchmarks — Lech Mazur Writing, GPQA diamond, MATH level 5, OTIS Mock AIME 2024-2025, WeirdML, Cybench, and 5 more. The full table above shows each score with its evidence status.
4 of 11 recorded scores (36%) are independently reproduced rather than self-reported by the lab.
o1-mini has 11 tracked claims: 4 independently reproduced, 7 unverified.