← All comparisons
Qwen3.5 122B A10B (Non-reasoning) vs GLM-4.5-Air
Alibaba vs Z AI — side-by-side benchmark comparison
| Qwen3.5 122B A10B (Non-reasoning) | GLM-4.5-Air | |
|---|---|---|
| Intelligence Index | 35.9 | 23.2 |
| Coding Index | 31.6 | 23.8 |
| Math Index | — | 80.7 |
| Output speed (tok/s) | 165.9 | 86.9 |
| Blended price ($/1M) | $1.10 | $0.37 |
| Time to first token (s) | 1.06s | 1.72s |
| aime | — | 67.3% |
| aime 25 | — | 80.7% |
| artificial analysis coding index | 31.60 | 23.80 |
| artificial analysis intelligence index | 35.90 | 23.20 |
| artificial analysis math index | — | 80.70 |
| gpqa | 82.7% | 73.3% |
| hle | 14.8% | 6.8% |
| ifbench | 50.8% | 37.6% |
| lcr | 56.0% | 43.7% |
| livecodebench | — | 68.4% |
| math 500 | — | 96.5% |
| mmlu pro | — | 81.5% |
| scicode | 35.6% | 30.6% |
| tau2 | 84.5% | 46.5% |
| terminalbench hard | 29.5% | 20.5% |
Benchmark data from Artificial Analysis.