← All comparisons
Claude 4.1 Opus (Non-reasoning) vs DeepSeek V3.2 (Non-reasoning)
Anthropic vs DeepSeek — side-by-side benchmark comparison
| Claude 4.1 Opus (Non-reasoning) | DeepSeek V3.2 (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 36.0 | 32.1 |
| Coding Index | — | 34.6 |
| Math Index | — | 59.0 |
| Output speed (tok/s) | 44.7 | 0.0 |
| Blended price ($/1M) | $32.81 | $0.78 |
| Time to first token (s) | 1.63s | 0.00s |
| aime | — | — |
| aime 25 | — | 59.0% |
| artificial analysis coding index | — | 34.60 |
| artificial analysis intelligence index | 36.00 | 32.10 |
| artificial analysis math index | — | 59.00 |
| gpqa | — | 75.1% |
| hle | — | 10.5% |
| ifbench | — | 49.0% |
| lcr | — | 39.0% |
| livecodebench | — | 59.3% |
| math 500 | — | — |
| mmlu pro | — | 83.7% |
| scicode | — | 38.7% |
| tau2 | — | 78.9% |
| terminalbench hard | — | 32.6% |
Benchmark data from Artificial Analysis.