Alibaba (Qwen) · model
Qwen3.8-Omni-Flash benchmark scores
As of 2026-11-22, Qwen3.8-Omni-Flash (Alibaba (Qwen)) has measured scores on 16 benchmarks and estimated scores on 75 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 90.5% | estimated ± 4.4 pp, high confidence |
| AA-HLE | 37.6% | estimated ± 3.9 pp, high confidence |
| AA-SciCode | 49.7% | estimated ± 3.1 pp, high confidence |
| Artificial Analysis Intelligence Index | 33.6% | estimated ± 7.4 pp, medium confidence |
| CritPt | 11.7% | estimated ± 4.0 pp, high confidence |
| GPQA Diamond | 91.0% | measured |
| HLE | 36.5% | measured |
| IFBench | 81.5% | measured |
| LiveCodeBench v6 | 92.6% | measured |
| AA-Omniscience Accuracy | 36.4% | estimated ± 8.4 pp, medium confidence |
| SciCode | 56.3% | estimated ± 4.9 pp, high confidence |
| IFEval | 94.9% | estimated ± 3.6 pp, high confidence |
| AA Coding Index | 72.4% | estimated ± 2.5 pp, high confidence |
| AA-MMMU-Pro | 80.1% | estimated ± 1.9 pp, high confidence |
| SWE-bench Verified | 80.7% | estimated ± 2.3 pp, high confidence |
| SWE-bench Pro | 63.3% | measured |
| MMLU-Pro | 85.0% | estimated ± 4.4 pp, high confidence |
| AA-IFBench | 80.4% | estimated ± 7.4 pp, medium confidence |
| GPQA | 91.0% | measured |
| MMLU | 88.1% | estimated ± 4.2 pp, medium confidence |
| Vals GPQA Diamond | 90.1% | estimated ± 2.1 pp, high confidence |
| Vals LiveCodeBench | 86.1% | estimated ± 3.4 pp, low confidence |
| Vals MMLU-Pro | 87.2% | estimated ± 1.6 pp, high confidence |
| MMMLU | 90.2% | estimated ± 1.1 pp, medium confidence |
| MMMU | 85.8% | estimated ± 3.7 pp, medium confidence |
| AA MMLU-Pro | 87.0% | estimated ± 1.2 pp, low confidence |
| Gert Labs | 100.0% | estimated ± 12.1 pp, low confidence |
| ARC-AGI-1 | 90.8% | estimated ± 2.5 pp, high confidence |
| ARC-AGI-2 | 62.4% | estimated ± 9.7 pp, medium confidence |
| CursorBench 3.1 | 56.8% | estimated ± 5.6 pp, low confidence |
| CursorBench 3.2 | 62.0% | estimated ± 3.6 pp, high confidence |
| FrontierCode 1.1 Main | 43.0% | estimated ± 3.5 pp, low confidence |
| FrontierSWE v2 | 21.3% | estimated ± 8.3 pp, medium confidence |
| ParseBench-1 | 68.3% | estimated ± 1.0 pp, medium confidence |
| Vals SWE-bench | 82.6% | estimated ± 5.2 pp, medium confidence |
| Bug Hunt Bench | 15.5% | estimated ± 7.2 pp, low confidence |
| CursorBench 4.0 | 38.1% | estimated ± 3.3 pp, high confidence |
| DeepSWE | 57.8% | measured |
| FrontierCode 2.0 | 22.4% | estimated ± 6.7 pp, medium confidence |
| HLE w/o tools | 38.2% | estimated ± 4.3 pp, high confidence |
| PostTrainBench v1.1 | 27.7% | estimated ± 4.4 pp, high confidence |
| SWE Multilingual | 80.5% | measured |
| VulcanBench Frontier v4 | 78.1% | estimated ± 5.0 pp, high confidence |
| ARC-AGI-3 | 0.0% | estimated ± 8.3 pp, low confidence |
| CharXiv | 91.4% | measured |
| CharXiv w/o tools | 83.5% | measured |
| AI2D_TEST | 93.5% | estimated ± 0.9 pp, low confidence |
| C-Eval | 94.6% | estimated ± 0.9 pp, low confidence |
| CountBench | 97.3% | estimated ± 1.3 pp, low confidence |
| DynaMath | 88.2% | estimated ± 0.8 pp, low confidence |
| ERQA | 71.0% | measured |
| INCLUDE | 86.6% | estimated ± 2.0 pp, medium confidence |
| MathVision | 91.8% | measured |
| MLVU (M-Avg) | 88.1% | estimated ± 1.5 pp, high confidence |
| MMLU-ProX | 86.9% | estimated ± 1.3 pp, medium confidence |
| MMLU-Redux | 94.9% | estimated ± 1.7 pp, high confidence |
| MMMU-Pro | 80.1% | estimated ± 3.0 pp, high confidence |
| NL2Repo | 48.9% | measured |
| OmniDocBench 1.5 | 91.3% | estimated ± 1.8 pp, medium confidence |
| PostTrainBench v1 | 28.7% | estimated ± 4.6 pp, high confidence |
| RealWorldQA | 87.7% | measured |
| ScreenSpot Pro | 82.6% | estimated ± 4.8 pp, medium confidence |
| SimpleVQA | 75.2% | estimated ± 7.3 pp, medium confidence |
| SuperGPQA | 76.6% | estimated ± 7.2 pp, medium confidence |
| V* | 94.2% | estimated ± 10.1 pp, low confidence |
| Video-MME (w/o subtitle) | 88.4% | estimated ± 4.9 pp, low confidence |
| Video-MME (with subtitle) | 89.5% | estimated ± 1.9 pp, high confidence |
| VideoMMMU | 87.6% | estimated ± 1.5 pp, medium confidence |
| We-Math | 87.5% | estimated ± 2.1 pp, low confidence |
| HealthBench Hard | 11.0% | estimated ± 5.1 pp, low confidence |
| LiveCodeBench Pro | 86.2% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (MM) | 78.2% | estimated ± 4.2 pp, medium confidence |
| MedXpertQA (Text) | 56.8% | estimated ± 4.5 pp, medium confidence |
| MMLU-Pro (Arcee) | 87.2% | estimated ± 3.4 pp, low confidence |
| PostTrainBench | 25.6% | estimated ± 3.7 pp, high confidence |
| FrontierCode 1.1 Extended | 57.1% | estimated ± 3.0 pp, medium confidence |
| HealthBench Professional | 53.1% | estimated ± 4.2 pp, low confidence |
| ScarfBench | 62.6% | estimated ± 3.8 pp, medium confidence |
| SimpleQA | 38.6% | estimated ± 13.4 pp, low confidence |
| BabyVision w/ Python | 89.0% | estimated ± 3.7 pp, low confidence |
| OpenHarmony Bench v1.0 | 55.8% | estimated ± 2.7 pp, high confidence |
| BabyVision | 67.5% | estimated ± 3.7 pp, high confidence |
| MMVU | 80.3% | estimated ± 3.3 pp, medium confidence |
| PerceptionBench | 59.4% | estimated ± 3.6 pp, medium confidence |
| ZeroBench | 16.2% | estimated ± 3.6 pp, medium confidence |
| LVBench | 76.9% | measured |
| RefCOCO (avg) | 91.2% | estimated ± 3.1 pp, low confidence |
| OCRBench V2 | 74.0% | estimated ± 5.4 pp, low confidence |
| BioBasicsBench | 24.7% | estimated ± 2.2 pp, low confidence |
| MathVision w/ Python | 96.2% | measured |
| SWE-Atlas Codebase QnA | 54.7% | estimated ± 4.8 pp, high confidence |