← All comparisons
Qwen3.5 35B A3B (Reasoning) vs Qwen3 VL 235B A22B (Reasoning)
Alibaba vs Alibaba — side-by-side benchmark comparison
| Qwen3.5 35B A3B (Reasoning) | Qwen3 VL 235B A22B (Reasoning) | |
|---|---|---|
| Intelligence Index | 37.1 | 27.6 |
| Coding Index | 30.3 | 20.9 |
| Math Index | — | 88.3 |
| Output speed (tok/s) | 135.9 | 35.6 |
| Blended price ($/1M) | $0.69 | $2.17 |
| Time to first token (s) | 1.23s | 5.14s |
| aime | — | — |
| aime 25 | — | 88.3% |
| artificial analysis coding index | 30.30 | 20.90 |
| artificial analysis intelligence index | 37.10 | 27.60 |
| artificial analysis math index | — | 88.30 |
| gpqa | 84.5% | 77.2% |
| hle | 19.7% | 10.1% |
| ifbench | 72.5% | 56.5% |
| lcr | 62.7% | 58.7% |
| livecodebench | — | 64.6% |
| math 500 | — | — |
| mmlu pro | — | 83.6% |
| scicode | 37.7% | 39.9% |
| tau2 | 89.2% | 54.1% |
| terminalbench hard | 26.5% | 11.4% |
Benchmark data from Artificial Analysis.