← All comparisons
o3-mini (high) vs Claude 4.1 Opus (Reasoning)
OpenAI vs Anthropic — side-by-side benchmark comparison
| o3-mini (high) | Claude 4.1 Opus (Reasoning) | |
|---|---|---|
| Intelligence Index | 25.2 | 42.0 |
| Coding Index | 17.3 | 36.5 |
| Math Index | — | 80.3 |
| Output speed (tok/s) | 187.0 | 44.5 |
| Blended price ($/1M) | $1.93 | $32.81 |
| Time to first token (s) | 15.73s | 8.55s |
| aime | 86.0% | — |
| aime 25 | — | 80.3% |
| artificial analysis coding index | 17.30 | 36.50 |
| artificial analysis intelligence index | 25.20 | 42.00 |
| artificial analysis math index | — | 80.30 |
| gpqa | 77.3% | 80.9% |
| hle | 12.3% | 11.9% |
| ifbench | 67.1% | 55.4% |
| lcr | 39.3% | 66.3% |
| livecodebench | 73.4% | 65.4% |
| math 500 | 98.5% | — |
| mmlu pro | 80.2% | 88.0% |
| scicode | 39.8% | 40.9% |
| tau2 | 31.3% | 71.4% |
| terminalbench hard | 6.1% | 34.3% |
Benchmark data from Artificial Analysis.