← All comparisons
Claude 4.1 Opus (Reasoning) vs Mistral Small 3.1
Anthropic vs Mistral — side-by-side benchmark comparison
| Claude 4.1 Opus (Reasoning) | Mistral Small 3.1 | |
|---|---|---|
| Intelligence Index | 42.0 | 14.5 |
| Coding Index | 36.5 | 13.9 |
| Math Index | 80.3 | 3.7 |
| Output speed (tok/s) | 44.5 | 163.2 |
| Blended price ($/1M) | $32.81 | $0.14 |
| Time to first token (s) | 8.55s | 0.49s |
| aime | — | 9.3% |
| aime 25 | 80.3% | 3.7% |
| artificial analysis coding index | 36.50 | 13.90 |
| artificial analysis intelligence index | 42.00 | 14.50 |
| artificial analysis math index | 80.30 | 3.70 |
| gpqa | 80.9% | 45.4% |
| hle | 11.9% | 4.8% |
| ifbench | 55.4% | 29.9% |
| lcr | 66.3% | 19.7% |
| livecodebench | 65.4% | 21.2% |
| math 500 | — | 70.7% |
| mmlu pro | 88.0% | 65.9% |
| scicode | 40.9% | 26.5% |
| tau2 | 71.4% | 25.1% |
| terminalbench hard | 34.3% | 7.6% |
Benchmark data from Artificial Analysis.