OpenAI
o1 is OpenAI's flagship reasoning model, designed for complex problems that require deep thinking. It provides strong reasoning capabilities with improved accuracy for complex multi-step tasks.
OpenAI model releasesRank #141 across 526
Rank #211 across 436
Rank #347 across 357
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Higher bars mean stronger relative placement.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 30.7 | #141 |
| Artificial Analysis Coding Index | coding | 20.5 | #211 |
| MMLU-Pro | reasoning | 84.1% | #42 |
| GPQA | reasoning | 74.7% | #180 |
| Humanity's Last Exam |
| reasoning |
| 7.7% |
| #211 |
| LiveCodeBench | coding | 67.9% | #83 |
| SciCode | coding, reasoning | 35.8% | #197 |
| MATH-500 | math | 97.0% | #27 |
| AIME | math | 72.3% | #35 |
| Output Speed | speed | 123.2 tok/s | #111 |
| Time to First Token | speed | 16.00s | #275 |
| Blended Price | cost | $26.25/M | #347 |
| Input Price | cost | $15.00/M | #347 |
| Output Price | cost | $60.00/M | #348 |
| Value Index | cost, overall | 1.2 | #347 |