← All comparisons
Claude 3.5 Sonnet (Oct '24) vs DeepSeek-V2.5 (Dec '24)
Anthropic vs DeepSeek — side-by-side benchmark comparison
| Claude 3.5 Sonnet (Oct '24) | DeepSeek-V2.5 (Dec '24) | |
|---|---|---|
| Intelligence Index | 15.9 | 12.5 |
| Coding Index | 30.2 | — |
| Math Index | — | — |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $6.56 | $0.00 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | 15.7% | — |
| aime 25 | — | — |
| artificial analysis coding index | 30.20 | — |
| artificial analysis intelligence index | 15.90 | 12.50 |
| artificial analysis math index | — | — |
| gpqa | 59.9% | — |
| hle | 3.9% | — |
| ifbench | — | — |
| lcr | — | — |
| livecodebench | 38.1% | — |
| math 500 | 77.1% | 76.3% |
| mmlu pro | 77.2% | — |
| scicode | 36.6% | — |
| tau2 | — | — |
| terminalbench hard | — | — |
Benchmark data from Artificial Analysis.