Alibaba (Qwen) · model
Qwen3.8-27B benchmark scores
As of 2026-11-22, Qwen3.8-27B (Alibaba (Qwen)) has measured scores on 56 benchmarks and estimated scores on 138 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 90.5% | measured |
| AA-HLE | 33.9% | measured |
| AA-SciCode | 46.6% | measured |
| Artificial Analysis Intelligence Index | 20.1% | measured |
| CritPt | 5.4% | measured |
| GDPval-AA | 45.9% | measured |
| GPQA Diamond | 89.2% | measured |
| HLE | 30.8% | measured |
| IFBench | 79.5% | measured |
| AA-LCR | 82.0% | measured |
| LiveCodeBench v6 | 90.3% | measured |
| AA-Omniscience Accuracy | 17.3% | measured |
| SciCode | 44.7% | estimated ± 2.9 pp, medium confidence |
| Terminal-Bench 2.1 | 73.0% | measured |
| BrowseComp | 84.8% | estimated ± 4.0 pp, high confidence |
| HLE w/ tools | 51.2% | estimated ± 5.1 pp, medium confidence |
| IFEval | 94.6% | estimated ± 3.6 pp, high confidence |
| LongBench v2 | 67.4% | estimated ± 5.5 pp, medium confidence |
| AA Coding Index | 68.1% | measured |
| AA-MMMU-Pro | 76.3% | measured |
| APEX-Agents | 38.2% | estimated ± 9.4 pp, low confidence |
| APEX-Agents-AA | 31.5% | estimated ± 3.6 pp, medium confidence |
| BioMysteryBench (human-difficult) | 38.0% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 92.9% | estimated ± 4.5 pp, high confidence |
| SWE-bench Verified | 79.4% | estimated ± 2.3 pp, high confidence |
| AutomationBench | 47.1% | estimated ± 6.1 pp, low confidence |
| BFCL v4 | 76.3% | estimated ± 2.7 pp, medium confidence |
| CyberGym | 84.4% | estimated ± 3.1 pp, low confidence |
| JobBench | 33.4% | measured |
| SWE-bench Pro | 61.7% | measured |
| WideResearch | 77.6% | estimated ± 1.2 pp, medium confidence |
| AA Agentic Index | 46.5% | measured |
| MMLU-Pro | 85.2% | estimated ± 2.5 pp, medium confidence |
| AA-IFBench | 80.3% | estimated ± 7.4 pp, medium confidence |
| FailureSensorIQ | 65.4% | estimated ± 1.7 pp, high confidence |
| GPQA | 89.2% | measured |
| MMLU | 80.6% | estimated ± 0.9 pp, high confidence |
| Vals GPQA Diamond | 88.9% | measured |
| Vals LiveCodeBench | 84.0% | measured |
| Vals MMLU-Pro | 84.3% | measured |
| MMMLU | 88.5% | estimated ± 0.7 pp, medium confidence |
| MMMU | 84.2% | estimated ± 2.7 pp, high confidence |
| Chess Puzzles | 48.2% | estimated ± 10.8 pp, low confidence |
| AA MMLU-Pro | 83.9% | estimated ± 0.7 pp, medium confidence |
| Gert Labs | 34.5% | measured |
| AA-AnalystAgent | 44.8% | estimated ± 5.9 pp, low confidence |
| AA EnterpriseOps-Gym | 44.2% | measured |
| AA Harvey LAB v1.0 | 93.2% | estimated ± 1.2 pp, medium confidence |
| AA Tau3 Banking | 48.0% | measured |
| AA Terminal-Bench 2.1 | 79.8% | measured |
| ApprenticeBench | 4.5% | estimated ± 6.0 pp, low confidence |
| ARC-AGI-1 | 88.1% | estimated ± 2.5 pp, high confidence |
| ARC-AGI-2 | 52.6% | estimated ± 9.7 pp, medium confidence |
| BabaIsBench | 21.0% | measured |
| CursorBench 3.1 | 35.6% | estimated ± 3.4 pp, low confidence |
| CursorBench 3.2 | 64.9% | estimated ± 3.3 pp, medium confidence |
| EBR-bench | 43.4% | estimated ± 11.3 pp, low confidence |
| Terminal-Bench 3.0 | 4.9% | estimated ± 6.9 pp, low confidence |
| FrontierCode 1.1 Main | 36.6% | estimated ± 4.6 pp, high confidence |
| FrontierSWE v2 | 18.5% | estimated ± 8.3 pp, medium confidence |
| Furniture Assembly | 46.5% | estimated ± 12.4 pp, low confidence |
| MaxxBench | 57.6% | estimated ± 5.7 pp, medium confidence |
| MazeBench | 0.0% | measured |
| Mystery Game Puzzles | 25.9% | estimated ± 12.4 pp, low confidence |
| NYT Connections | 54.5% | measured |
| OfficeQA Pro | 50.3% | estimated ± 6.8 pp, low confidence |
| OSWorld-Verified | 84.3% | measured |
| ParseBench-1 | 69.0% | measured |
| Terminal-Bench 4.1 | 9.6% | estimated ± 5.8 pp, medium confidence |
| Terminal-Bench Hard | 47.2% | estimated ± 3.9 pp, high confidence |
| Vals SWE-bench | 86.0% | measured |
| Terminal-Bench 2.1 (Vals AI) | 58.4% | measured |
| VulcanBench v3 | 82.6% | measured |
| CWE-Bench-AA | 26.7% | measured |
| AA Cyber Index | 12.7% | measured |
| DeepsecBench-AA | 11.5% | measured |
| Harvey LAB-AA v1.1 | 0.0% | estimated ± 3.5 pp, low confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 51.9% | estimated ± 4.3 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 43.4% | estimated ± 0.8 pp, low confidence |
| AA ITBench | 44.2% | estimated ± 3.2 pp, high confidence |
| Bug Hunt Bench | 15.0% | measured |
| Chartography (tools) | 81.1% | estimated ± 4.1 pp, low confidence |
| CursorBench 4.0 | 27.2% | estimated ± 2.0 pp, medium confidence |
| CWE-bench v1 | 57.4% | estimated ± 5.1 pp, medium confidence |
| DeepSWE | 42.2% | measured |
| DRACO | 86.9% | estimated ± 0.7 pp, low confidence |
| FrontierCode 2.0 | 21.8% | estimated ± 6.7 pp, medium confidence |
| FrontierPhysics | 4.7% | estimated ± 4.7 pp, high confidence |
| HLE w/o tools | 30.8% | measured |
| OSWorld 2.0 | 19.2% | estimated ± 3.6 pp, high confidence |
| OSWorld 2.1 | 22.5% | estimated ± 3.6 pp, medium confidence |
| OSWorld 2.1 Offline | 47.5% | estimated ± 1.9 pp, low confidence |
| PostTrainBench v1.1 | 28.9% | estimated ± 3.7 pp, high confidence |
| SpireClimb | 5.8% | estimated ± 7.2 pp, low confidence |
| StealthMark | 51.5% | measured |
| SWE-bench Multimodal | 56.5% | estimated ± 5.6 pp, low confidence |
| Terminal-Bench 4.0 | 35.7% | estimated ± 6.1 pp, low confidence |
| Toolathlon-Verified | 72.2% | estimated ± 2.3 pp, medium confidence |
| VulcanBench Frontier v4 | 81.0% | estimated ± 4.0 pp, low confidence |
| AA AutomationBench | 48.2% | measured |
| GDP.pdf | 16.4% | measured |
| AA Terminal-Bench 4.0 | 5.6% | measured |
| ARC-AGI-3 | 0.7% | estimated ± 7.2 pp, low confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| cursorBench41 | 44.8% | estimated ± 3.7 pp, medium confidence |
| CWE-bench | 36.6% | estimated ± 6.2 pp, low confidence |
| MKA | 33.1% | estimated ± 4.6 pp, medium confidence |
| SkillsBench official leaderboard (BenchFlow) | 49.4% | estimated ± 6.1 pp, medium confidence |
| BinaryAudit | 35.8% | estimated ± 12.1 pp, low confidence |
| OTelBench | 22.5% | estimated ± 6.6 pp, medium confidence |
| Vibe Code Bench | 48.9% | estimated ± 10.0 pp, low confidence |
| FACTS Multimodal | 31.7% | estimated ± 4.0 pp, medium confidence |
| Hermes Bench | 70.6% | estimated ± 1.5 pp, medium confidence |
| Hermes Index | 37.4% | estimated ± 2.7 pp, medium confidence |
| ParseBench-2 | 74.5% | measured |
| CharXiv | 90.2% | measured |
| CharXiv w/o tools | 83.7% | measured |
| ExploitBench | 52.3% | estimated ± 12.6 pp, low confidence |
| ExploitGym | 11.7% | estimated ± 2.7 pp, high confidence |
| AI2D_TEST | 93.5% | estimated ± 0.9 pp, low confidence |
| C-Eval | 93.4% | estimated ± 0.9 pp, medium confidence |
| Claw-Eval | 62.8% | estimated ± 4.5 pp, medium confidence |
| CountBench | 97.3% | estimated ± 1.3 pp, low confidence |
| DynaMath | 88.0% | estimated ± 0.8 pp, low confidence |
| ERQA | 65.5% | measured |
| MathVision | 90.0% | measured |
| MCP Atlas | 83.1% | estimated ± 6.0 pp, low confidence |
| MLVU (M-Avg) | 87.4% | estimated ± 1.5 pp, high confidence |
| MMLU-Redux | 93.2% | estimated ± 0.8 pp, low confidence |
| MMMU-Pro | 77.4% | estimated ± 1.5 pp, high confidence |
| NL2Repo | 42.3% | measured |
| OmniDocBench 1.5 | 91.1% | measured |
| PostTrainBench v1 | 31.8% | estimated ± 3.6 pp, high confidence |
| QwenClawBench | 93.2% | estimated ± 6.0 pp, low confidence |
| RealWorldQA | 85.9% | measured |
| ScreenSpot Pro | 77.0% | estimated ± 4.8 pp, medium confidence |
| SimpleVQA | 72.0% | estimated ± 7.1 pp, low confidence |
| SuperGPQA | 71.2% | estimated ± 7.2 pp, medium confidence |
| Terminal-Bench 2.0 | 65.1% | estimated ± 5.8 pp, medium confidence |
| Toolathlon | 55.9% | estimated ± 6.3 pp, medium confidence |
| V* | 100.0% | estimated ± 7.5 pp, medium confidence |
| Video-MME (w/o subtitle) | 84.0% | estimated ± 1.7 pp, medium confidence |
| Video-MME (with subtitle) | 88.6% | estimated ± 1.9 pp, high confidence |
| VideoMMMU | 87.3% | estimated ± 1.5 pp, medium confidence |
| We-Math | 87.5% | estimated ± 2.1 pp, low confidence |
| AA LiveCodeBench | 95.2% | estimated ± 2.6 pp, medium confidence |
| HealthBench Hard | 0.4% | estimated ± 5.1 pp, low confidence |
| LiveCodeBench Pro | 85.0% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (MM) | 76.3% | estimated ± 4.2 pp, medium confidence |
| MedXpertQA (Text) | 51.5% | estimated ± 4.5 pp, medium confidence |
| MMLU-Pro (Arcee) | 86.6% | estimated ± 3.4 pp, medium confidence |
| React Native Evals | 81.2% | estimated ± 3.2 pp, high confidence |
| ResearchClawBench | 20.9% | estimated ± 1.9 pp, medium confidence |
| SWE-Rebench | 58.1% | estimated ± 8.9 pp, low confidence |
| PostTrainBench | 27.0% | estimated ± 3.7 pp, high confidence |
| DAYJOB | 7.3% | estimated ± 3.2 pp, high confidence |
| DAYJOB Healthcare | 5.2% | estimated ± 4.7 pp, high confidence |
| Finance Agent v2 | 55.2% | estimated ± 2.4 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.8% | estimated ± 0.6 pp, low confidence |
| FrontierCode 1.1 Extended | 56.5% | estimated ± 3.0 pp, low confidence |
| HealthBench (raw) | 42.9% | estimated ± 6.0 pp, low confidence |
| HealthBench (length-adjusted) | 51.3% | estimated ± 3.4 pp, low confidence |
| HealthBench Professional | 40.9% | estimated ± 4.2 pp, low confidence |
| HealthBench Professional (raw) | 53.8% | estimated ± 4.5 pp, medium confidence |
| HLE-Verified | 21.9% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 79.9% | estimated ± 1.8 pp, low confidence |
| ScarfBench | 60.8% | estimated ± 3.8 pp, low confidence |
| BlenderWorld (text-only) | 32.2% | estimated ± 4.3 pp, low confidence |
| Cookie-Bench | 48.4% | estimated ± 4.8 pp, low confidence |
| STEMBench | 2.3% | estimated ± 0.2 pp, low confidence |
| SimpleQA | 14.4% | estimated ± 4.3 pp, medium confidence |
| Agents' Last Exam | 42.9% | measured |
| BabyVision w/ Python | 85.6% | measured |
| OpenHarmony Bench v1.0 | 51.0% | estimated ± 2.4 pp, high confidence |
| OpenHarmony Bench v1.2 | 45.7% | estimated ± 11.0 pp, low confidence |
| SEC-Bench Pro | 61.2% | estimated ± 9.3 pp, medium confidence |
| ZeroBench w/ Python | 38.0% | estimated ± 7.0 pp, low confidence |
| BabyVision | 65.7% | measured |
| MMVU | 79.1% | estimated ± 3.3 pp, medium confidence |
| PerceptionBench | 55.9% | estimated ± 2.5 pp, low confidence |
| ZeroBench | 15.7% | estimated ± 3.6 pp, medium confidence |
| MRCRv2 | 85.9% | estimated ± 11.3 pp, low confidence |
| LVBench | 77.3% | estimated ± 8.2 pp, low confidence |
| CC-OCR | 81.7% | estimated ± 3.7 pp, medium confidence |
| MMLongBench-Doc | 61.5% | estimated ± 2.6 pp, low confidence |
| RefCOCO (avg) | 90.7% | estimated ± 3.1 pp, low confidence |
| OCRBench V2 | 70.9% | estimated ± 5.4 pp, low confidence |
| SWE-Marathon | 39.3% | estimated ± 2.1 pp, low confidence |
| BioBasicsBench | 19.8% | estimated ± 2.2 pp, low confidence |
| LifeVal | 75.2% | estimated ± 3.8 pp, medium confidence |
| MMMU-Pro w/ Python | 79.4% | estimated ± 2.0 pp, high confidence |
| ExploitBench Internal Port | 5.5% | estimated ± 6.8 pp, low confidence |
| MathVision w/ Python | 94.6% | measured |
| SWE-Atlas Codebase QnA | 30.4% | estimated ± 4.8 pp, medium confidence |