← All comparisons
GPT-5 mini (minimal) vs Claude 4.1 Opus (Reasoning)
OpenAI vs Anthropic — side-by-side benchmark comparison
| GPT-5 mini (minimal) | Claude 4.1 Opus (Reasoning) | |
|---|---|---|
| Intelligence Index | 20.7 | 42.0 |
| Coding Index | 21.9 | 36.5 |
| Math Index | 46.7 | 80.3 |
| Output speed (tok/s) | 89.3 | 44.5 |
| Blended price ($/1M) | $0.69 | $32.81 |
| Time to first token (s) | 0.73s | 8.55s |
| aime | — | — |
| aime 25 | 46.7% | 80.3% |
| artificial analysis coding index | 21.90 | 36.50 |
| artificial analysis intelligence index | 20.70 | 42.00 |
| artificial analysis math index | 46.70 | 80.30 |
| gpqa | 68.7% | 80.9% |
| hle | 5.0% | 11.9% |
| ifbench | 45.6% | 55.4% |
| lcr | 35.7% | 66.3% |
| livecodebench | 54.5% | 65.4% |
| math 500 | — | — |
| mmlu pro | 77.5% | 88.0% |
| scicode | 36.9% | 40.9% |
| tau2 | 31.9% | 71.4% |
| terminalbench hard | 14.4% | 34.3% |
Benchmark data from Artificial Analysis.