← All comparisons
DeepSeek V4 Pro (Reasoning, Max Effort) vs Claude 4.1 Opus (Non-reasoning)
DeepSeek vs Anthropic — side-by-side benchmark comparison
| DeepSeek V4 Pro (Reasoning, Max Effort) | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 51.5 | 36.0 |
| Coding Index | 47.5 | — |
| Math Index | — | — |
| Output speed (tok/s) | 51.8 | 44.7 |
| Blended price ($/1M) | $0.54 | $32.81 |
| Time to first token (s) | 1.21s | 1.63s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 47.50 | — |
| artificial analysis intelligence index | 51.50 | 36.00 |
| artificial analysis math index | — | — |
| gpqa | 88.8% | — |
| hle | 35.9% | — |
| ifbench | 76.5% | — |
| lcr | 66.3% | — |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 50.0% | — |
| tau2 | 96.2% | — |
| terminalbench hard | 46.2% | — |
Benchmark data from Artificial Analysis.