o1 is a closed-weights model from OpenAI, released December 17, 2024. It has an ECI score of 142 and ranks 98th of 249 tracked models. At the time of its release, it ranked 1st of 101 tracked models. At $15/Mtok for input tokens and $60/Mtok for output tokens, it is more expensive per token than similarly-capable models.
| Domain | Benchmark | ||||
|---|---|---|---|---|---|
ECI scoreBest score 166 | 142 | 136 | 135 | 134 | |
| Ranking | #98 | #130 | #136 | #140 | |
| Conceptual reasoning | SimpleBenchBest score 81.9% | ||||
ARC-AGI-1Best score 98.5% | |||||
| Mathematics | MATH Level 5Best score 98.1% | ||||
OTIS Mock AIME 2024-2025Best score 100.0% | |||||
| Science | Humanity's Last ExamBest score 46.5% | ||||
GPQA DiamondBest score 95.8% | |||||
| Software engineering | METR Time HorizonsBest score 1044.8 | 38.8 | — | — | 20.5 |
Aider PolyglotBest score 88.0% | |||||
| Other | LiveBenchBest score 82.3% |