← All comparisons
Magistral Medium 1.2 vs Nemotron 3 Nano Omni 30B A3B Reasoning
Mistral vs NVIDIA — side-by-side benchmark comparison
| Magistral Medium 1.2 | Nemotron 3 Nano Omni 30B A3B Reasoning | |
|---|---|---|
| Intelligence Index | 27.1 | 21.4 |
| Coding Index | 21.7 | 14.8 |
| Math Index | 82.0 | — |
| Output speed (tok/s) | 39.4 | 285.9 |
| Blended price ($/1M) | $2.75 | $0.13 |
| Time to first token (s) | 0.54s | 0.58s |
| aime | — | — |
| aime 25 | 82.0% | — |
| artificial analysis coding index | 21.70 | 14.80 |
| artificial analysis intelligence index | 27.10 | 21.40 |
| artificial analysis math index | 82.00 | — |
| gpqa | 73.9% | 46.9% |
| hle | 9.6% | 5.3% |
| ifbench | 43.0% | 63.2% |
| lcr | 51.3% | 35.7% |
| livecodebench | 75.0% | — |
| math 500 | — | — |
| mmlu pro | 81.5% | — |
| scicode | 39.2% | 27.8% |
| tau2 | 52.0% | 45.3% |
| terminalbench hard | 12.9% | 8.3% |
Benchmark data from Artificial Analysis.