← All comparisons
Qwen3.6 27B (Non-reasoning) vs GLM-4.5 (Reasoning)
Alibaba vs Z AI — side-by-side benchmark comparison
| Qwen3.6 27B (Non-reasoning) | GLM-4.5 (Reasoning) | |
|---|---|---|
| Intelligence Index | 37.1 | 26.4 |
| Coding Index | 26.6 | 26.3 |
| Math Index | — | 73.7 |
| Output speed (tok/s) | 60.7 | 53.3 |
| Blended price ($/1M) | $1.35 | $1.00 |
| Time to first token (s) | 1.55s | 1.19s |
| aime | — | 87.3% |
| aime 25 | — | 73.7% |
| artificial analysis coding index | 26.60 | 26.30 |
| artificial analysis intelligence index | 37.10 | 26.40 |
| artificial analysis math index | — | 73.70 |
| gpqa | 82.9% | 78.2% |
| hle | 13.6% | 12.2% |
| ifbench | 45.7% | 44.1% |
| lcr | 55.0% | 48.3% |
| livecodebench | — | 73.8% |
| math 500 | — | 97.9% |
| mmlu pro | — | 83.5% |
| scicode | 37.3% | 34.8% |
| tau2 | 93.6% | 43.0% |
| terminalbench hard | 21.2% | 22.0% |
Benchmark data from Artificial Analysis.