← All comparisons
GLM-5.1 (Reasoning) vs Qwen3.6 27B (Non-reasoning)
Z AI vs Alibaba — side-by-side benchmark comparison
| GLM-5.1 (Reasoning) | Qwen3.6 27B (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 51.4 | 37.1 |
| Coding Index | 43.4 | 26.6 |
| Math Index | — | — |
| Output speed (tok/s) | 61.2 | 60.7 |
| Blended price ($/1M) | $2.15 | $1.35 |
| Time to first token (s) | 0.86s | 1.55s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 43.40 | 26.60 |
| artificial analysis intelligence index | 51.40 | 37.10 |
| artificial analysis math index | — | — |
| gpqa | 86.8% | 82.9% |
| hle | 28.0% | 13.6% |
| ifbench | 76.3% | 45.7% |
| lcr | 62.3% | 55.0% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 43.8% | 37.3% |
| tau2 | 97.7% | 93.6% |
| terminalbench hard | 43.2% | 21.2% |
Benchmark data from Artificial Analysis.