← All comparisons
Mistral Medium 3.1 vs OLMo 2 7B
Mistral vs Allen Institute for AI — side-by-side benchmark comparison
| Mistral Medium 3.1 | OLMo 2 7B | |
|---|---|---|
| Intelligence Index | 21.3 | 9.3 |
| Coding Index | 18.3 | 1.2 |
| Math Index | 38.3 | 0.7 |
| Output speed (tok/s) | 64.0 | 0.0 |
| Blended price ($/1M) | $0.80 | $0.00 |
| Time to first token (s) | 0.52s | 0.00s |
| aime | — | — |
| aime 25 | 38.3% | 0.7% |
| artificial analysis coding index | 18.30 | 1.20 |
| artificial analysis intelligence index | 21.30 | 9.30 |
| artificial analysis math index | 38.30 | 70.0% |
| gpqa | 58.8% | 28.8% |
| hle | 4.4% | 5.5% |
| ifbench | 39.8% | 24.4% |
| lcr | 19.7% | 0.0% |
| livecodebench | 40.6% | 4.1% |
| math 500 | — | — |
| mmlu pro | 68.3% | 28.2% |
| scicode | 33.8% | 3.7% |
| tau2 | 40.6% | 0.0% |
| terminalbench hard | 10.6% | 0.0% |
Benchmark data from Artificial Analysis.