← All comparisons
Qwen3 Omni 30B A3B (Reasoning) vs Qwen3.5 0.8B (Non-reasoning)
Alibaba vs Alibaba — side-by-side benchmark comparison
| Qwen3 Omni 30B A3B (Reasoning) | Qwen3.5 0.8B (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 15.6 | 9.9 |
| Coding Index | 12.7 | 1.0 |
| Math Index | 74.0 | — |
| Output speed (tok/s) | 100.1 | 96.3 |
| Blended price ($/1M) | $0.43 | $0.02 |
| Time to first token (s) | 0.97s | 0.26s |
| aime | — | — |
| aime 25 | 74.0% | — |
| artificial analysis coding index | 12.70 | 100.0% |
| artificial analysis intelligence index | 15.60 | 9.90 |
| artificial analysis math index | 74.00 | — |
| gpqa | 72.6% | 23.6% |
| hle | 7.3% | 4.9% |
| ifbench | 43.4% | 21.6% |
| lcr | 0.0% | 6.7% |
| livecodebench | 67.9% | — |
| math 500 | — | — |
| mmlu pro | 79.2% | — |
| scicode | 30.6% | 2.9% |
| tau2 | 21.3% | 65.2% |
| terminalbench hard | 3.8% | 0.0% |
Benchmark data from Artificial Analysis.