Alibaba (Qwen) · model
Qwen3.8-Flash-Next benchmark scores
As of 2026-10-07, Qwen3.8-Flash-Next (Alibaba (Qwen)) has measured scores on 30 benchmarks and estimated scores on 85 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 92.3% | measured |
| AA-HLE | 38.0% | measured |
| AA-SciCode | 50.6% | measured |
| Artificial Analysis Intelligence Index | 39.8% | measured |
| CritPt | 11.1% | measured |
| GDPval-AA | 56.6% | measured |
| GPQA Diamond | 91.7% | measured |
| HLE | 35.9% | measured |
| IFBench | 81.3% | measured |
| AA-LCR | 79.7% | measured |
| LiveCodeBench v6 | 91.9% | measured |
| AA-Omniscience Accuracy | 24.5% | measured |
| SciCode | 50.3% | estimated ± 3.2 pp, high confidence |
| BrowseComp | 82.8% | estimated ± 2.2 pp, high confidence |
| HLE w/ tools | 58.0% | estimated ± 5.9 pp, medium confidence |
| IFEval | 92.8% | estimated ± 3.5 pp, medium confidence |
| LongBench v2 | 61.5% | estimated ± 5.9 pp, low confidence |
| AA Coding Index | 73.1% | measured |
| AA-MMMU-Pro | 79.8% | measured |
| APEX-Agents | 45.3% | estimated ± 10.0 pp, low confidence |
| APEX-Agents-AA | 36.3% | estimated ± 2.9 pp, medium confidence |
| BioMysteryBench (human-difficult) | 30.9% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 90.4% | estimated ± 8.4 pp, medium confidence |
| SWE-bench Verified | 80.2% | estimated ± 2.4 pp, high confidence |
| AutomationBench | 44.5% | estimated ± 9.7 pp, low confidence |
| BFCL v4 | 77.9% | estimated ± 2.6 pp, medium confidence |
| CyberGym | 100.0% | estimated ± 5.4 pp, low confidence |
| JobBench | 55.7% | measured |
| SWE-bench Pro | 62.5% | measured |
| WideResearch | 82.5% | estimated ± 1.2 pp, medium confidence |
| AA Agentic Index | 51.4% | estimated ± 2.8 pp, high confidence |
| MMLU-Pro | 85.5% | estimated ± 2.5 pp, medium confidence |
| GPQA | 91.7% | measured |
| AA-IFBench | 80.3% | estimated ± 8.5 pp, medium confidence |
| Gert Labs | 71.9% | estimated ± 3.7 pp, medium confidence |
| AA-AnalystAgent | 53.9% | estimated ± 5.5 pp, medium confidence |
| AA EnterpriseOps-Gym | 47.0% | estimated ± 6.7 pp, low confidence |
| AA Harvey LAB | 89.7% | estimated ± 1.3 pp, medium confidence |
| ApprenticeBench | 19.0% | estimated ± 5.6 pp, low confidence |
| ARC-AGI-1 | 91.6% | estimated ± 2.7 pp, high confidence |
| ARC-AGI-2 | 63.8% | estimated ± 10.1 pp, low confidence |
| CursorBench 3.1 | 45.5% | estimated ± 3.4 pp, low confidence |
| CursorBench 3.2 | 61.1% | estimated ± 3.6 pp, high confidence |
| FrontierCode 1.1 Main | 37.7% | estimated ± 3.7 pp, low confidence |
| FrontierSWE v2 | 19.6% | estimated ± 9.0 pp, medium confidence |
| OfficeQA Pro | 54.7% | estimated ± 7.2 pp, medium confidence |
| OSWorld-Verified | 82.8% | estimated ± 3.0 pp, high confidence |
| Vals GPQA Diamond | 91.0% | estimated ± 2.0 pp, high confidence |
| Vals LiveCodeBench | 85.8% | estimated ± 4.7 pp, medium confidence |
| Vals MMLU-Pro | 87.7% | estimated ± 1.2 pp, high confidence |
| Vals SWE-bench | 82.1% | estimated ± 5.4 pp, medium confidence |
| AA AutomationBench | 55.2% | estimated ± 5.0 pp, medium confidence |
| GDP.pdf | 24.4% | estimated ± 3.4 pp, high confidence |
| AA Tau3 Banking | 47.5% | estimated ± 5.8 pp, medium confidence |
| CursorBench 4.0 | 36.5% | estimated ± 1.6 pp, high confidence |
| CWE-bench v1 | 60.0% | estimated ± 6.9 pp, medium confidence |
| DeepSWE | 58.7% | measured |
| HLE w/o tools | 35.9% | measured |
| OSWorld 2.0 | 19.4% | measured |
| PostTrainBench v1.1 | 27.2% | estimated ± 4.7 pp, high confidence |
| SWE Multilingual | 81.0% | measured |
| Toolathlon-Verified | 73.5% | measured |
| Vibe Code Bench | 61.2% | estimated ± 10.3 pp, low confidence |
| CharXiv | 90.6% | measured |
| CharXiv w/o tools | 84.6% | measured |
| ExploitGym | 5.2% | estimated ± 6.9 pp, low confidence |
| C-Eval | 93.1% | estimated ± 0.8 pp, low confidence |
| Claw-Eval | 66.2% | estimated ± 5.6 pp, low confidence |
| MathVision | 90.6% | measured |
| MCP Atlas | 80.9% | estimated ± 7.8 pp, medium confidence |
| MMLU-ProX | 87.0% | estimated ± 1.7 pp, low confidence |
| MMLU-Redux | 94.5% | estimated ± 1.1 pp, medium confidence |
| MMMU-Pro | 81.5% | estimated ± 1.4 pp, medium confidence |
| NL2Repo | 48.1% | measured |
| NOVA-63 | 59.6% | estimated ± 1.6 pp, low confidence |
| QwenClawBench | 100.0% | estimated ± 6.0 pp, low confidence |
| ScreenSpot Pro | 75.6% | estimated ± 4.5 pp, medium confidence |
| SuperGPQA | 69.5% | estimated ± 7.5 pp, medium confidence |
| Toolathlon | 55.9% | estimated ± 6.3 pp, low confidence |
| V* | 97.4% | estimated ± 5.1 pp, low confidence |
| VideoMMMU | 87.3% | estimated ± 1.5 pp, high confidence |
| ERQA | 72.3% | measured |
| HealthBench Hard | 23.3% | estimated ± 5.1 pp, low confidence |
| LiveCodeBench Pro | 85.6% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (MM) | 78.5% | estimated ± 4.2 pp, medium confidence |
| MedXpertQA (Text) | 59.2% | estimated ± 4.5 pp, medium confidence |
| MMLU-Pro (Arcee) | 87.4% | estimated ± 3.4 pp, low confidence |
| React Native Evals | 82.4% | estimated ± 3.5 pp, high confidence |
| ResearchClawBench | 19.9% | estimated ± 2.2 pp, low confidence |
| SWE-Rebench | 58.1% | estimated ± 8.9 pp, low confidence |
| ARC-AGI-3 | 0.0% | estimated ± 2.1 pp, medium confidence |
| BioMysteryBench (human-solvable) | 84.3% | estimated ± 0.6 pp, low confidence |
| DRACO | 84.8% | estimated ± 3.0 pp, medium confidence |
| FrontierCode 1.1 Extended | 56.8% | estimated ± 3.0 pp, low confidence |
| HealthBench (raw) | 47.2% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, medium confidence |
| HealthBench Professional | 53.5% | estimated ± 4.8 pp, low confidence |
| HealthBench Professional (raw) | 57.7% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 49.9% | estimated ± 2.0 pp, medium confidence |
| LABBench2 | 80.7% | estimated ± 1.8 pp, low confidence |
| MMMU | 87.1% | estimated ± 0.9 pp, medium confidence |
| LiveCodeBench | 100.0% | estimated ± 8.9 pp, low confidence |
| Agents' Last Exam | 51.2% | measured |
| OpenHarmony Bench | 56.4% | estimated ± 2.4 pp, high confidence |
| BabyVision | 64.7% | estimated ± 4.3 pp, medium confidence |
| MMVU | 78.1% | estimated ± 2.9 pp, medium confidence |
| SimpleVQA | 72.1% | estimated ± 7.4 pp, low confidence |
| ZeroBench | 17.5% | estimated ± 4.7 pp, low confidence |
| MMMLU | 90.4% | estimated ± 1.1 pp, medium confidence |
| MMLU | 88.7% | estimated ± 1.1 pp, medium confidence |
| MMMU-Pro w/ Python | 81.6% | estimated ± 1.6 pp, high confidence |
| MathVision w/ Python | 95.7% | measured |
| RealWorldQA | 88.5% | measured |
| Video-MME (with subtitle) | 89.5% | estimated ± 0.9 pp, medium confidence |
| OmniDocBench 1.5 | 92.0% | estimated ± 6.4 pp, low confidence |