← All comparisons
Claude 3.7 Sonnet (Reasoning) vs Qwen3 235B A22B 2507 (Reasoning)
Anthropic vs Alibaba — side-by-side benchmark comparison
| Claude 3.7 Sonnet (Reasoning) | Qwen3 235B A22B 2507 (Reasoning) | |
|---|---|---|
| Intelligence Index | 34.7 | 29.5 |
| Coding Index | 27.6 | 23.2 |
| Math Index | 56.3 | 91.0 |
| Output speed (tok/s) | 0.0 | 62.5 |
| Blended price ($/1M) | $0.00 | $0.84 |
| Time to first token (s) | 0.00s | 1.21s |
| aime | 48.7% | 94.0% |
| aime 25 | 56.3% | 91.0% |
| artificial analysis coding index | 27.60 | 23.20 |
| artificial analysis intelligence index | 34.70 | 29.50 |
| artificial analysis math index | 56.30 | 91.00 |
| gpqa | 77.2% | 79.0% |
| hle | 10.3% | 15.0% |
| ifbench | 48.3% | 51.2% |
| lcr | 60.7% | 67.0% |
| livecodebench | 47.3% | 78.8% |
| math 500 | 94.7% | 98.4% |
| mmlu pro | 83.7% | 84.3% |
| scicode | 40.3% | 42.4% |
| tau2 | 54.7% | 53.2% |
| terminalbench hard | 21.2% | 13.6% |
Benchmark data from Artificial Analysis.