← All comparisons
Claude 4.1 Opus (Non-reasoning) vs DeepSeek R1 (Jan '25)
Anthropic vs DeepSeek — side-by-side benchmark comparison
| Claude 4.1 Opus (Non-reasoning) | DeepSeek R1 (Jan '25) | |
|---|---|---|
| Intelligence Index | 36.0 | 18.8 |
| Coding Index | — | 15.9 |
| Math Index | — | 68.0 |
| Output speed (tok/s) | 44.7 | 0.0 |
| Blended price ($/1M) | $32.81 | $2.43 |
| Time to first token (s) | 1.63s | 0.00s |
| aime | — | 68.3% |
| aime 25 | — | 68.0% |
| artificial analysis coding index | — | 15.90 |
| artificial analysis intelligence index | 36.00 | 18.80 |
| artificial analysis math index | — | 68.00 |
| gpqa | — | 70.8% |
| hle | — | 9.3% |
| ifbench | — | 39.0% |
| lcr | — | 52.3% |
| livecodebench | — | 61.7% |
| math 500 | — | 96.6% |
| mmlu pro | — | 84.4% |
| scicode | — | 35.7% |
| tau2 | — | 11.4% |
| terminalbench hard | — | 6.1% |
Benchmark data from Artificial Analysis.