← All comparisons
Claude Opus 4.5 (Non-reasoning) vs DeepSeek R1 Distill Qwen 1.5B
Anthropic vs DeepSeek — side-by-side benchmark comparison
| Claude Opus 4.5 (Non-reasoning) | DeepSeek R1 Distill Qwen 1.5B | |
|---|---|---|
| Intelligence Index | 43.1 | 9.1 |
| Coding Index | 42.9 | — |
| Math Index | 62.7 | 22.0 |
| Output speed (tok/s) | 57.0 | 0.0 |
| Blended price ($/1M) | $10.94 | $0.00 |
| Time to first token (s) | 0.93s | 0.00s |
| aime | — | 17.7% |
| aime 25 | 62.7% | 22.0% |
| artificial analysis coding index | 42.90 | — |
| artificial analysis intelligence index | 43.10 | 9.10 |
| artificial analysis math index | 62.70 | 22.00 |
| gpqa | 81.0% | 9.8% |
| hle | 12.9% | 3.3% |
| ifbench | 43.0% | 13.2% |
| lcr | 65.3% | 0.3% |
| livecodebench | 73.8% | 7.0% |
| math 500 | — | 68.7% |
| mmlu pro | 88.9% | 26.9% |
| scicode | 47.0% | 6.6% |
| tau2 | 86.3% | — |
| terminalbench hard | 40.9% | — |
Benchmark data from Artificial Analysis.