← All comparisons
Claude 4.1 Opus (Reasoning) vs Kimi K2 0905
Anthropic vs Kimi — side-by-side benchmark comparison
| Claude 4.1 Opus (Reasoning) | Kimi K2 0905 | |
|---|---|---|
| Intelligence Index | 42.0 | 30.9 |
| Coding Index | 36.5 | 25.9 |
| Math Index | 80.3 | 57.3 |
| Output speed (tok/s) | 44.5 | 24.6 |
| Blended price ($/1M) | $32.81 | $1.07 |
| Time to first token (s) | 8.55s | 1.44s |
| aime | — | — |
| aime 25 | 80.3% | 57.3% |
| artificial analysis coding index | 36.50 | 25.90 |
| artificial analysis intelligence index | 42.00 | 30.90 |
| artificial analysis math index | 80.30 | 57.30 |
| gpqa | 80.9% | 76.7% |
| hle | 11.9% | 6.3% |
| ifbench | 55.4% | 41.7% |
| lcr | 66.3% | 52.3% |
| livecodebench | 65.4% | 61.0% |
| math 500 | — | — |
| mmlu pro | 88.0% | 81.9% |
| scicode | 40.9% | 30.7% |
| tau2 | 71.4% | 73.4% |
| terminalbench hard | 34.3% | 23.5% |
Benchmark data from Artificial Analysis.