← All comparisons
Claude 4.1 Opus (Non-reasoning) vs Magistral Small 1
Anthropic vs Mistral — side-by-side benchmark comparison
| Claude 4.1 Opus (Non-reasoning) | Magistral Small 1 | |
|---|---|---|
| Intelligence Index | 36.0 | 16.8 |
| Coding Index | — | 11.1 |
| Math Index | — | 41.3 |
| Output speed (tok/s) | 44.7 | 0.0 |
| Blended price ($/1M) | $32.81 | $0.00 |
| Time to first token (s) | 1.63s | 0.00s |
| aime | — | 71.3% |
| aime 25 | — | 41.3% |
| artificial analysis coding index | — | 11.10 |
| artificial analysis intelligence index | 36.00 | 16.80 |
| artificial analysis math index | — | 41.30 |
| gpqa | — | 64.1% |
| hle | — | 7.2% |
| ifbench | — | 24.8% |
| lcr | — | 0.0% |
| livecodebench | — | 51.4% |
| math 500 | — | 96.3% |
| mmlu pro | — | 74.6% |
| scicode | — | 24.1% |
| tau2 | — | 26.6% |
| terminalbench hard | — | 4.5% |
Benchmark data from Artificial Analysis.