← All comparisons
Qwen3 Next 80B A3B (Reasoning) vs Qwen3.5 2B (Non-reasoning)
Alibaba vs Alibaba — side-by-side benchmark comparison
| Qwen3 Next 80B A3B (Reasoning) | Qwen3.5 2B (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 26.7 | 14.7 |
| Coding Index | 19.5 | 4.9 |
| Math Index | 84.3 | — |
| Output speed (tok/s) | 149.4 | 272.0 |
| Blended price ($/1M) | $1.88 | $0.04 |
| Time to first token (s) | 1.23s | 0.27s |
| aime | — | — |
| aime 25 | 84.3% | — |
| artificial analysis coding index | 19.50 | 4.90 |
| artificial analysis intelligence index | 26.70 | 14.70 |
| artificial analysis math index | 84.30 | — |
| gpqa | 75.9% | 43.8% |
| hle | 11.7% | 4.9% |
| ifbench | 60.7% | 29.1% |
| lcr | 60.3% | 13.7% |
| livecodebench | 78.4% | — |
| math 500 | — | — |
| mmlu pro | 82.4% | — |
| scicode | 38.8% | 7.2% |
| tau2 | 41.5% | 81.6% |
| terminalbench hard | 9.8% | 3.8% |
Benchmark data from Artificial Analysis.