← All comparisons
Claude 3.5 Sonnet (June '24) vs Kimi K2 0905
Anthropic vs Kimi — side-by-side benchmark comparison
| Claude 3.5 Sonnet (June '24) | Kimi K2 0905 | |
|---|---|---|
| Intelligence Index | 14.2 | 30.9 |
| Coding Index | 26.0 | 25.9 |
| Math Index | — | 57.3 |
| Output speed (tok/s) | 0.0 | 24.6 |
| Blended price ($/1M) | $6.56 | $1.07 |
| Time to first token (s) | 0.00s | 1.44s |
| aime | 9.7% | — |
| aime 25 | — | 57.3% |
| artificial analysis coding index | 26.00 | 25.90 |
| artificial analysis intelligence index | 14.20 | 30.90 |
| artificial analysis math index | — | 57.30 |
| gpqa | 56.0% | 76.7% |
| hle | 3.7% | 6.3% |
| ifbench | — | 41.7% |
| lcr | — | 52.3% |
| livecodebench | — | 61.0% |
| math 500 | 69.5% | — |
| mmlu pro | 75.1% | 81.9% |
| scicode | 31.6% | 30.7% |
| tau2 | — | 73.4% |
| terminalbench hard | — | 23.5% |
Benchmark data from Artificial Analysis.