← All comparisons
GLM-5.1 (Non-reasoning) vs DeepSeek R1 Distill Qwen 32B
Z AI vs DeepSeek — side-by-side benchmark comparison
| GLM-5.1 (Non-reasoning) | DeepSeek R1 Distill Qwen 32B | |
|---|---|---|
| Intelligence Index | 43.8 | 17.2 |
| Coding Index | 35.8 | — |
| Math Index | — | 63.0 |
| Output speed (tok/s) | 48.7 | 0.0 |
| Blended price ($/1M) | $2.15 | $0.00 |
| Time to first token (s) | 1.02s | 0.00s |
| aime | — | 68.7% |
| aime 25 | — | 63.0% |
| artificial analysis coding index | 35.80 | — |
| artificial analysis intelligence index | 43.80 | 17.20 |
| artificial analysis math index | — | 63.00 |
| gpqa | 83.9% | 61.5% |
| hle | 25.6% | 5.5% |
| ifbench | 52.0% | 22.9% |
| lcr | 44.3% | 9.7% |
| livecodebench | — | 27.0% |
| math 500 | — | 94.1% |
| mmlu pro | — | 73.9% |
| scicode | 36.1% | 37.6% |
| tau2 | 97.1% | — |
| terminalbench hard | 35.6% | — |
Benchmark data from Artificial Analysis.