← All comparisons
Claude Opus 4.8 (Adaptive Reasoning, Max Effort) vs DeepSeek R1 Distill Qwen 32B
Anthropic vs DeepSeek — side-by-side benchmark comparison
| Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | DeepSeek R1 Distill Qwen 32B | |
|---|---|---|
| Intelligence Index | 61.4 | 17.2 |
| Coding Index | 56.7 | — |
| Math Index | — | 63.0 |
| Output speed (tok/s) | 66.9 | 0.0 |
| Blended price ($/1M) | $10.94 | $0.00 |
| Time to first token (s) | 7.91s | 0.00s |
| aime | — | 68.7% |
| aime 25 | — | 63.0% |
| artificial analysis coding index | 56.70 | — |
| artificial analysis intelligence index | 61.40 | 17.20 |
| artificial analysis math index | — | 63.00 |
| gpqa | 92.0% | 61.5% |
| hle | 45.7% | 5.5% |
| ifbench | 62.2% | 22.9% |
| lcr | 67.7% | 9.7% |
| livecodebench | — | 27.0% |
| math 500 | — | 94.1% |
| mmlu pro | — | 73.9% |
| scicode | 53.5% | 37.6% |
| tau2 | 94.4% | — |
| terminalbench hard | 58.3% | — |
Benchmark data from Artificial Analysis.