← All comparisons
Claude 3.5 Sonnet (June '24) vs Mistral Small 3.2
Anthropic vs Mistral — side-by-side benchmark comparison
| Claude 3.5 Sonnet (June '24) | Mistral Small 3.2 | |
|---|---|---|
| Intelligence Index | 14.2 | 15.1 |
| Coding Index | 26.0 | 13.3 |
| Math Index | — | 27.0 |
| Output speed (tok/s) | 0.0 | 133.0 |
| Blended price ($/1M) | $6.56 | $0.13 |
| Time to first token (s) | 0.00s | 0.36s |
| aime | 9.7% | 32.3% |
| aime 25 | — | 27.0% |
| artificial analysis coding index | 26.00 | 13.30 |
| artificial analysis intelligence index | 14.20 | 15.10 |
| artificial analysis math index | — | 27.00 |
| gpqa | 56.0% | 50.5% |
| hle | 3.7% | 4.3% |
| ifbench | — | 33.5% |
| lcr | — | 17.3% |
| livecodebench | — | 27.5% |
| math 500 | 69.5% | 88.3% |
| mmlu pro | 75.1% | 68.1% |
| scicode | 31.6% | 26.4% |
| tau2 | — | 29.5% |
| terminalbench hard | — | 6.8% |
Benchmark data from Artificial Analysis.