← All comparisons
Qwen3 Omni 30B A3B (Reasoning) vs Qwen3.5 35B A3B (Non-reasoning)
Alibaba vs Alibaba — side-by-side benchmark comparison
| Qwen3 Omni 30B A3B (Reasoning) | Qwen3.5 35B A3B (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 15.6 | 30.7 |
| Coding Index | 12.7 | 16.8 |
| Math Index | 74.0 | — |
| Output speed (tok/s) | 100.1 | 147.9 |
| Blended price ($/1M) | $0.43 | $0.69 |
| Time to first token (s) | 0.97s | 1.18s |
| aime | — | — |
| aime 25 | 74.0% | — |
| artificial analysis coding index | 12.70 | 16.80 |
| artificial analysis intelligence index | 15.60 | 30.70 |
| artificial analysis math index | 74.00 | — |
| gpqa | 72.6% | 81.9% |
| hle | 7.3% | 12.8% |
| ifbench | 43.4% | 44.5% |
| lcr | 0.0% | 55.3% |
| livecodebench | 67.9% | — |
| math 500 | — | — |
| mmlu pro | 79.2% | — |
| scicode | 30.6% | 29.3% |
| tau2 | 21.3% | 86.3% |
| terminalbench hard | 3.8% | 10.6% |
Benchmark data from Artificial Analysis.