← All comparisons
Kimi K2.6 (Non-reasoning) vs Mistral Large (Feb '24)
Kimi vs Mistral — side-by-side benchmark comparison
| Kimi K2.6 (Non-reasoning) | Mistral Large (Feb '24) | |
|---|---|---|
| Intelligence Index | 42.9 | 9.9 |
| Coding Index | 38.4 | — |
| Math Index | — | — |
| Output speed (tok/s) | 39.0 | 0.0 |
| Blended price ($/1M) | $1.71 | $6.00 |
| Time to first token (s) | 1.28s | 0.00s |
| aime | — | 0.0% |
| aime 25 | — | — |
| artificial analysis coding index | 38.40 | — |
| artificial analysis intelligence index | 42.90 | 9.90 |
| artificial analysis math index | — | — |
| gpqa | 78.8% | 35.1% |
| hle | 18.2% | 3.4% |
| ifbench | 44.3% | — |
| lcr | 57.7% | — |
| livecodebench | — | 17.8% |
| math 500 | — | 52.7% |
| mmlu pro | — | 51.5% |
| scicode | 39.5% | 20.8% |
| tau2 | 93.9% | — |
| terminalbench hard | 37.9% | — |
Benchmark data from Artificial Analysis.