← All comparisons
Qwen3 Omni 30B A3B (Reasoning) vs Mistral Small 3.1
Alibaba vs Mistral — side-by-side benchmark comparison
| Qwen3 Omni 30B A3B (Reasoning) | Mistral Small 3.1 | |
|---|---|---|
| Intelligence Index | 15.6 | 14.5 |
| Coding Index | 12.7 | 13.9 |
| Math Index | 74.0 | 3.7 |
| Output speed (tok/s) | 100.1 | 163.2 |
| Blended price ($/1M) | $0.43 | $0.14 |
| Time to first token (s) | 0.97s | 0.49s |
| aime | — | 9.3% |
| aime 25 | 74.0% | 3.7% |
| artificial analysis coding index | 12.70 | 13.90 |
| artificial analysis intelligence index | 15.60 | 14.50 |
| artificial analysis math index | 74.00 | 3.70 |
| gpqa | 72.6% | 45.4% |
| hle | 7.3% | 4.8% |
| ifbench | 43.4% | 29.9% |
| lcr | 0.0% | 19.7% |
| livecodebench | 67.9% | 21.2% |
| math 500 | — | 70.7% |
| mmlu pro | 79.2% | 65.9% |
| scicode | 30.6% | 26.5% |
| tau2 | 21.3% | 25.1% |
| terminalbench hard | 3.8% | 7.6% |
Benchmark data from Artificial Analysis.