← All comparisons
o4-mini (high) vs Claude 4.1 Opus (Reasoning)
OpenAI vs Anthropic — side-by-side benchmark comparison
| o4-mini (high) | Claude 4.1 Opus (Reasoning) | |
|---|---|---|
| Intelligence Index | 33.1 | 42.0 |
| Coding Index | 25.6 | 36.5 |
| Math Index | 90.7 | 80.3 |
| Output speed (tok/s) | 160.5 | 44.5 |
| Blended price ($/1M) | $1.93 | $32.81 |
| Time to first token (s) | 23.07s | 8.55s |
| aime | 94.0% | — |
| aime 25 | 90.7% | 80.3% |
| artificial analysis coding index | 25.60 | 36.50 |
| artificial analysis intelligence index | 33.10 | 42.00 |
| artificial analysis math index | 90.70 | 80.30 |
| gpqa | 78.4% | 80.9% |
| hle | 17.5% | 11.9% |
| ifbench | 68.7% | 55.4% |
| lcr | 55.0% | 66.3% |
| livecodebench | 85.9% | 65.4% |
| math 500 | 98.9% | — |
| mmlu pro | 83.2% | 88.0% |
| scicode | 46.5% | 40.9% |
| tau2 | 55.6% | 71.4% |
| terminalbench hard | 15.2% | 34.3% |
Benchmark data from Artificial Analysis.