← All comparisons
Qwen3 Next 80B A3B (Reasoning) vs GLM-4.7 (Non-reasoning)
Alibaba vs Z AI — side-by-side benchmark comparison
| Qwen3 Next 80B A3B (Reasoning) | GLM-4.7 (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 26.7 | 34.2 |
| Coding Index | 19.5 | 32.0 |
| Math Index | 84.3 | 48.0 |
| Output speed (tok/s) | 149.4 | 84.8 |
| Blended price ($/1M) | $1.88 | $1.00 |
| Time to first token (s) | 1.23s | 0.75s |
| aime | — | — |
| aime 25 | 84.3% | 48.0% |
| artificial analysis coding index | 19.50 | 32.00 |
| artificial analysis intelligence index | 26.70 | 34.20 |
| artificial analysis math index | 84.30 | 48.00 |
| gpqa | 75.9% | 66.4% |
| hle | 11.7% | 6.1% |
| ifbench | 60.7% | 54.6% |
| lcr | 60.3% | 36.3% |
| livecodebench | 78.4% | 56.2% |
| math 500 | — | — |
| mmlu pro | 82.4% | 79.4% |
| scicode | 38.8% | 35.4% |
| tau2 | 41.5% | 94.2% |
| terminalbench hard | 9.8% | 30.3% |
Benchmark data from Artificial Analysis.