← All comparisons
GPT-5.1 Codex mini (high) vs Claude 4.1 Opus (Reasoning)
OpenAI vs Anthropic — side-by-side benchmark comparison
| GPT-5.1 Codex mini (high) | Claude 4.1 Opus (Reasoning) | |
|---|---|---|
| Intelligence Index | 38.6 | 42.0 |
| Coding Index | 36.4 | 36.5 |
| Math Index | 91.7 | 80.3 |
| Output speed (tok/s) | 218.5 | 44.5 |
| Blended price ($/1M) | $0.69 | $32.81 |
| Time to first token (s) | 3.35s | 8.55s |
| aime | — | — |
| aime 25 | 91.7% | 80.3% |
| artificial analysis coding index | 36.40 | 36.50 |
| artificial analysis intelligence index | 38.60 | 42.00 |
| artificial analysis math index | 91.70 | 80.30 |
| gpqa | 81.3% | 80.9% |
| hle | 16.9% | 11.9% |
| ifbench | 67.9% | 55.4% |
| lcr | 62.7% | 66.3% |
| livecodebench | 83.6% | 65.4% |
| math 500 | — | — |
| mmlu pro | 82.0% | 88.0% |
| scicode | 42.6% | 40.9% |
| tau2 | 62.9% | 71.4% |
| terminalbench hard | 33.3% | 34.3% |
Benchmark data from Artificial Analysis.