← All comparisons
Mistral Medium 3.5 vs Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)
Mistral vs Google — side-by-side benchmark comparison
| Mistral Medium 3.5 | Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) | |
|---|---|---|
| Intelligence Index | 39.2 | 21.6 |
| Coding Index | 35.4 | 18.2 |
| Math Index | — | 68.7 |
| Output speed (tok/s) | 169.9 | 0.0 |
| Blended price ($/1M) | $3.00 | $0.17 |
| Time to first token (s) | 0.52s | 0.00s |
| aime | — | — |
| aime 25 | — | 68.7% |
| artificial analysis coding index | 35.40 | 18.20 |
| artificial analysis intelligence index | 39.20 | 21.60 |
| artificial analysis math index | — | 68.70 |
| gpqa | 74.8% | 70.9% |
| hle | 12.8% | 6.6% |
| ifbench | 68.8% | 52.6% |
| lcr | 61.0% | 59.0% |
| livecodebench | — | 68.8% |
| math 500 | — | — |
| mmlu pro | — | 80.8% |
| scicode | 39.6% | 28.7% |
| tau2 | 94.2% | 30.7% |
| terminalbench hard | 33.3% | 12.9% |
Benchmark data from Artificial Analysis.