← All comparisons
o3-mini (high) vs Claude 3.5 Sonnet (Oct '24)
OpenAI vs Anthropic — side-by-side benchmark comparison
| o3-mini (high) | Claude 3.5 Sonnet (Oct '24) | |
|---|---|---|
| Intelligence Index | 25.2 | 15.9 |
| Coding Index | 17.3 | 30.2 |
| Math Index | — | — |
| Output speed (tok/s) | 187.0 | 0.0 |
| Blended price ($/1M) | $1.93 | $6.56 |
| Time to first token (s) | 15.73s | 0.00s |
| aime | 86.0% | 15.7% |
| aime 25 | — | — |
| artificial analysis coding index | 17.30 | 30.20 |
| artificial analysis intelligence index | 25.20 | 15.90 |
| artificial analysis math index | — | — |
| gpqa | 77.3% | 59.9% |
| hle | 12.3% | 3.9% |
| ifbench | 67.1% | — |
| lcr | 39.3% | — |
| livecodebench | 73.4% | 38.1% |
| math 500 | 98.5% | 77.1% |
| mmlu pro | 80.2% | 77.2% |
| scicode | 39.8% | 36.6% |
| tau2 | 31.3% | — |
| terminalbench hard | 6.1% | — |
Benchmark data from Artificial Analysis.