← All comparisons
Claude 3.5 Sonnet (June '24) vs Kimi K2.5 (Reasoning)
Anthropic vs Kimi — side-by-side benchmark comparison
| Claude 3.5 Sonnet (June '24) | Kimi K2.5 (Reasoning) | |
|---|---|---|
| Intelligence Index | 14.2 | 46.8 |
| Coding Index | 26.0 | 39.6 |
| Math Index | — | — |
| Output speed (tok/s) | 0.0 | 33.7 |
| Blended price ($/1M) | $6.56 | $1.19 |
| Time to first token (s) | 0.00s | 1.29s |
| aime | 9.7% | — |
| aime 25 | — | — |
| artificial analysis coding index | 26.00 | 39.60 |
| artificial analysis intelligence index | 14.20 | 46.80 |
| artificial analysis math index | — | — |
| gpqa | 56.0% | 87.9% |
| hle | 3.7% | 29.4% |
| ifbench | — | 70.2% |
| lcr | — | 65.3% |
| livecodebench | — | — |
| math 500 | 69.5% | — |
| mmlu pro | 75.1% | — |
| scicode | 31.6% | 49.0% |
| tau2 | — | 95.9% |
| terminalbench hard | — | 34.8% |
Benchmark data from Artificial Analysis.