Alibaba (Qwen) · model
Qwen3.5 Flash benchmark scores
As of 2026-10-07, Qwen3.5 Flash (Alibaba (Qwen)) has measured scores on 6 benchmarks and estimated scores on 36 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 84.1% | estimated ± 4.2 pp, high confidence |
| AA-HLE | 25.7% | estimated ± 7.4 pp, medium confidence |
| AA-SciCode | 45.2% | estimated ± 4.3 pp, medium confidence |
| AIME26 | 95.5% | estimated ± 0.6 pp, low confidence |
| Artificial Analysis Intelligence Index | 22.3% | estimated ± 7.9 pp, medium confidence |
| CritPt | 4.0% | estimated ± 6.6 pp, medium confidence |
| GPQA Diamond | 86.6% | estimated ± 1.7 pp, medium confidence |
| HLE | 39.5% | estimated ± 9.8 pp, low confidence |
| AA-Omniscience Accuracy | 27.0% | estimated ± 7.7 pp, medium confidence |
| SciCode | 43.3% | estimated ± 2.9 pp, low confidence |
| AA Coding Index | 45.3% | estimated ± 5.8 pp, medium confidence |
| SWE-bench Verified | 76.3% | estimated ± 4.4 pp, high confidence |
| SWE-bench Pro | 57.0% | estimated ± 4.8 pp, high confidence |
| FrontierMath v2 (Tier 4) | 0.0% | measured |
| FrontierMath v2 (Tiers 1-3) | 6.2% | measured |
| GPQA | 88.0% | estimated ± 1.6 pp, high confidence |
| ARC-AGI-1 | 75.1% | estimated ± 5.9 pp, medium confidence |
| ARC-AGI-2 | 29.8% | estimated ± 12.6 pp, low confidence |
| CursorBench 3.1 | 38.1% | estimated ± 5.8 pp, low confidence |
| CursorBench 3.2 | 49.6% | estimated ± 5.4 pp, low confidence |
| FrontierCode 1.1 Main | 16.6% | estimated ± 5.2 pp, low confidence |
| FrontierSWE v2 | 5.0% | estimated ± 9.5 pp, low confidence |
| Vals GPQA Diamond | 82.8% | measured |
| Vals LiveCodeBench | 83.3% | measured |
| Vals MMLU-Pro | 84.1% | measured |
| Vals SWE-bench | 64.4% | measured |
| VulcanBench v3 | 82.6% | estimated ± 5.6 pp, low confidence |
| CursorBench 4.0 | 22.2% | estimated ± 4.4 pp, low confidence |
| DeepSWE | 56.3% | estimated ± 7.2 pp, low confidence |
| HLE w/o tools | 28.1% | estimated ± 5.1 pp, medium confidence |
| PostTrainBench v1.1 | 15.8% | estimated ± 2.7 pp, high confidence |
| HMMT Nov 2025 | 99.9% | estimated ± 2.6 pp, low confidence |
| MMAnswerBench | 81.9% | estimated ± 1.3 pp, low confidence |
| NL2Repo | 38.9% | estimated ± 4.7 pp, medium confidence |
| React Native Evals | 57.9% | estimated ± 2.4 pp, low confidence |
| ARC-AGI-3 | 0.0% | estimated ± 9.2 pp, low confidence |
| FrontierMath (legacy) | 7.3% | estimated ± 0.7 pp, low confidence |
| FrontierCode 1.1 Extended | 10.1% | estimated ± 2.4 pp, low confidence |
| HealthBench Professional | 50.9% | estimated ± 1.3 pp, low confidence |
| HLE-Verified | 0.0% | estimated ± 4.6 pp, low confidence |
| LABBench2 | 79.8% | estimated ± 1.8 pp, low confidence |
| OpenHarmony Bench | 49.4% | estimated ± 3.2 pp, medium confidence |