← All comparisons
Kimi K2.6 vs Claude 4.1 Opus (Reasoning)
Kimi vs Anthropic — side-by-side benchmark comparison
| Kimi K2.6 | Claude 4.1 Opus (Reasoning) | |
|---|---|---|
| Intelligence Index | 53.9 | 42.0 |
| Coding Index | 47.1 | 36.5 |
| Math Index | — | 80.3 |
| Output speed (tok/s) | 42.0 | 44.5 |
| Blended price ($/1M) | $1.71 | $32.81 |
| Time to first token (s) | 1.30s | 8.55s |
| aime | — | — |
| aime 25 | — | 80.3% |
| artificial analysis coding index | 47.10 | 36.50 |
| artificial analysis intelligence index | 53.90 | 42.00 |
| artificial analysis math index | — | 80.30 |
| gpqa | 91.1% | 80.9% |
| hle | 35.9% | 11.9% |
| ifbench | 76.0% | 55.4% |
| lcr | 69.7% | 66.3% |
| livecodebench | — | 65.4% |
| math 500 | — | — |
| mmlu pro | — | 88.0% |
| scicode | 53.5% | 40.9% |
| tau2 | 95.9% | 71.4% |
| terminalbench hard | 43.9% | 34.3% |
Benchmark data from Artificial Analysis.