← All comparisons
Kimi K2.6 vs Claude 3.5 Sonnet (Oct '24)
Kimi vs Anthropic — side-by-side benchmark comparison
| Kimi K2.6 | Claude 3.5 Sonnet (Oct '24) | |
|---|---|---|
| Intelligence Index | 53.9 | 15.9 |
| Coding Index | 47.1 | 30.2 |
| Math Index | — | — |
| Output speed (tok/s) | 42.0 | 0.0 |
| Blended price ($/1M) | $1.71 | $6.56 |
| Time to first token (s) | 1.30s | 0.00s |
| aime | — | 15.7% |
| aime 25 | — | — |
| artificial analysis coding index | 47.10 | 30.20 |
| artificial analysis intelligence index | 53.90 | 15.90 |
| artificial analysis math index | — | — |
| gpqa | 91.1% | 59.9% |
| hle | 35.9% | 3.9% |
| ifbench | 76.0% | — |
| lcr | 69.7% | — |
| livecodebench | — | 38.1% |
| math 500 | — | 77.1% |
| mmlu pro | — | 77.2% |
| scicode | 53.5% | 36.6% |
| tau2 | 95.9% | — |
| terminalbench hard | 43.9% | — |
Benchmark data from Artificial Analysis.