← All comparisons
Claude 4.1 Opus (Non-reasoning) vs Kimi K2
Anthropic vs Kimi — side-by-side benchmark comparison
| Claude 4.1 Opus (Non-reasoning) | Kimi K2 | |
|---|---|---|
| Intelligence Index | 36.0 | 26.3 |
| Coding Index | — | 22.1 |
| Math Index | — | 57.0 |
| Output speed (tok/s) | 44.7 | 23.9 |
| Blended price ($/1M) | $32.81 | $1.04 |
| Time to first token (s) | 1.63s | 1.59s |
| aime | — | 69.3% |
| aime 25 | — | 57.0% |
| artificial analysis coding index | — | 22.10 |
| artificial analysis intelligence index | 36.00 | 26.30 |
| artificial analysis math index | — | 57.00 |
| gpqa | — | 76.6% |
| hle | — | 7.0% |
| ifbench | — | 41.5% |
| lcr | — | 51.0% |
| livecodebench | — | 55.6% |
| math 500 | — | 97.1% |
| mmlu pro | — | 82.4% |
| scicode | — | 34.5% |
| tau2 | — | 61.1% |
| terminalbench hard | — | 15.9% |
Benchmark data from Artificial Analysis.