← All comparisons
o1 vs Claude 3.5 Sonnet (Oct '24)
OpenAI vs Anthropic — side-by-side benchmark comparison
| o1 | Claude 3.5 Sonnet (Oct '24) | |
|---|---|---|
| Intelligence Index | 30.7 | 15.9 |
| Coding Index | 20.5 | 30.2 |
| Math Index | — | — |
| Output speed (tok/s) | 119.6 | 0.0 |
| Blended price ($/1M) | $26.25 | $6.56 |
| Time to first token (s) | 15.07s | 0.00s |
| aime | 72.3% | 15.7% |
| aime 25 | — | — |
| artificial analysis coding index | 20.50 | 30.20 |
| artificial analysis intelligence index | 30.70 | 15.90 |
| artificial analysis math index | — | — |
| gpqa | 74.7% | 59.9% |
| hle | 7.7% | 3.9% |
| ifbench | 70.3% | — |
| lcr | 59.3% | — |
| livecodebench | 67.9% | 38.1% |
| math 500 | 97.0% | 77.1% |
| mmlu pro | 84.1% | 77.2% |
| scicode | 35.8% | 36.6% |
| tau2 | 62.6% | — |
| terminalbench hard | 12.9% | — |
Benchmark data from Artificial Analysis.