← All comparisons
Claude 4.5 Haiku (Reasoning) vs Kimi K2.6
Anthropic vs Kimi — side-by-side benchmark comparison
| Claude 4.5 Haiku (Reasoning) | Kimi K2.6 | |
|---|---|---|
| Intelligence Index | 37.1 | 53.9 |
| Coding Index | 32.6 | 47.1 |
| Math Index | 83.7 | — |
| Output speed (tok/s) | 142.2 | 42.0 |
| Blended price ($/1M) | $2.19 | $1.71 |
| Time to first token (s) | 10.48s | 1.30s |
| aime | — | — |
| aime 25 | 83.7% | — |
| artificial analysis coding index | 32.60 | 47.10 |
| artificial analysis intelligence index | 37.10 | 53.90 |
| artificial analysis math index | 83.70 | — |
| gpqa | 67.2% | 91.1% |
| hle | 9.7% | 35.9% |
| ifbench | 54.3% | 76.0% |
| lcr | 70.3% | 69.7% |
| livecodebench | 61.5% | — |
| math 500 | — | — |
| mmlu pro | 76.0% | — |
| scicode | 43.3% | 53.5% |
| tau2 | 54.7% | 95.9% |
| terminalbench hard | 27.3% | 43.9% |
Benchmark data from Artificial Analysis.