← All comparisons
Magistral Medium 1 vs Llama 3.1 Tulu3 405B
Mistral vs Allen Institute for AI — side-by-side benchmark comparison
| Magistral Medium 1 | Llama 3.1 Tulu3 405B | |
|---|---|---|
| Intelligence Index | 18.8 | 14.1 |
| Coding Index | 16.0 | — |
| Math Index | 40.3 | — |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $0.00 | $0.00 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | 70.0% | 13.3% |
| aime 25 | 40.3% | — |
| artificial analysis coding index | 16.00 | — |
| artificial analysis intelligence index | 18.80 | 14.10 |
| artificial analysis math index | 40.30 | — |
| gpqa | 67.9% | 51.6% |
| hle | 9.5% | 3.5% |
| ifbench | 25.1% | — |
| lcr | 0.0% | — |
| livecodebench | 52.7% | 29.1% |
| math 500 | 91.7% | 77.8% |
| mmlu pro | 75.3% | 71.6% |
| scicode | 29.7% | 30.2% |
| tau2 | 23.1% | — |
| terminalbench hard | 9.1% | — |
Benchmark data from Artificial Analysis.