← All comparisons
Magistral Small 1 vs Hermes 3 - Llama-3.1 70B
Mistral vs Nous Research — side-by-side benchmark comparison
| Magistral Small 1 | Hermes 3 - Llama-3.1 70B | |
|---|---|---|
| Intelligence Index | 16.8 | 10.6 |
| Coding Index | 11.1 | — |
| Math Index | 41.3 | — |
| Output speed (tok/s) | 0.0 | 33.2 |
| Blended price ($/1M) | $0.00 | $0.30 |
| Time to first token (s) | 0.00s | 0.38s |
| aime | 71.3% | 2.3% |
| aime 25 | 41.3% | — |
| artificial analysis coding index | 11.10 | — |
| artificial analysis intelligence index | 16.80 | 10.60 |
| artificial analysis math index | 41.30 | — |
| gpqa | 64.1% | 40.1% |
| hle | 7.2% | 4.1% |
| ifbench | 24.8% | — |
| lcr | 0.0% | — |
| livecodebench | 51.4% | 18.8% |
| math 500 | 96.3% | 53.8% |
| mmlu pro | 74.6% | 57.1% |
| scicode | 24.1% | 23.1% |
| tau2 | 26.6% | — |
| terminalbench hard | 4.5% | — |
Benchmark data from Artificial Analysis.