← All comparisons
DeepSeek R1 Distill Qwen 32B vs Qwen3 235B A22B 2507 Instruct
DeepSeek vs Alibaba — side-by-side benchmark comparison
| DeepSeek R1 Distill Qwen 32B | Qwen3 235B A22B 2507 Instruct | |
|---|---|---|
| Intelligence Index | 17.2 | 25.0 |
| Coding Index | — | 22.1 |
| Math Index | 63.0 | 71.7 |
| Output speed (tok/s) | 0.0 | 57.0 |
| Blended price ($/1M) | $0.00 | $0.36 |
| Time to first token (s) | 0.00s | 1.34s |
| aime | 68.7% | 71.7% |
| aime 25 | 63.0% | 71.7% |
| artificial analysis coding index | — | 22.10 |
| artificial analysis intelligence index | 17.20 | 25.00 |
| artificial analysis math index | 63.00 | 71.70 |
| gpqa | 61.5% | 75.3% |
| hle | 5.5% | 10.6% |
| ifbench | 22.9% | 46.1% |
| lcr | 9.7% | 31.2% |
| livecodebench | 27.0% | 52.4% |
| math 500 | 94.1% | 98.0% |
| mmlu pro | 73.9% | 82.8% |
| scicode | 37.6% | 36.0% |
| tau2 | — | 33.3% |
| terminalbench hard | — | 15.2% |
Benchmark data from Artificial Analysis.