← All comparisons
Qwen3.5 122B A10B (Reasoning) vs Qwen3.6 35B A3B (Non-reasoning)
Alibaba vs Alibaba — side-by-side benchmark comparison
| Qwen3.5 122B A10B (Reasoning) | Qwen3.6 35B A3B (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 41.6 | 31.5 |
| Coding Index | 34.7 | 17.6 |
| Math Index | — | — |
| Output speed (tok/s) | 146.7 | 169.5 |
| Blended price ($/1M) | $1.10 | $0.84 |
| Time to first token (s) | 1.05s | 1.47s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 34.70 | 17.60 |
| artificial analysis intelligence index | 41.60 | 31.50 |
| artificial analysis math index | — | — |
| gpqa | 85.7% | 81.7% |
| hle | 23.4% | 12.5% |
| ifbench | 75.7% | 36.2% |
| lcr | 66.7% | 56.7% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 42.0% | 1.3% |
| tau2 | 93.6% | 85.1% |
| terminalbench hard | 31.1% | 25.8% |
Benchmark data from Artificial Analysis.