Alibaba (Qwen) · model
Qwen3.6-27B benchmark scores
As of 2026-10-07, Qwen3.6-27B (Alibaba (Qwen)) has measured scores on 44 benchmarks and estimated scores on 85 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 84.2% | measured |
| AA-HLE | 23.1% | measured |
| AA-SciCode | 42.8% | measured |
| AIME26 | 94.1% | measured |
| Artificial Analysis Intelligence Index | 21.4% | measured |
| CritPt | 1.1% | measured |
| GDPval-AA | 24.4% | measured |
| GPQA Diamond | 87.8% | estimated ± 0.4 pp, high confidence |
| HLE | 24.0% | measured |
| IFBench | 66.5% | estimated ± 6.9 pp, medium confidence |
| AA-LCR | 77.3% | measured |
| LiveCodeBench v6 | 86.2% | estimated ± 2.1 pp, high confidence |
| AA-Omniscience Accuracy | 19.6% | measured |
| SciCode | 42.7% | estimated ± 3.2 pp, high confidence |
| BrowseComp | 80.0% | estimated ± 5.7 pp, medium confidence |
| HLE w/ tools | 44.1% | estimated ± 6.1 pp, low confidence |
| IFEval | 93.3% | estimated ± 1.3 pp, high confidence |
| LongBench v2 | 61.5% | estimated ± 5.9 pp, medium confidence |
| VITA-Bench | 38.4% | estimated ± 8.2 pp, low confidence |
| τ²-bench results | 94.2% | measured |
| AA Coding Index | 53.7% | measured |
| AA-MMMU-Pro | 74.6% | measured |
| APEX-Agents | 22.4% | estimated ± 10.0 pp, low confidence |
| APEX-Agents-AA | 20.5% | estimated ± 9.1 pp, medium confidence |
| BioMysteryBench (human-difficult) | 26.7% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 84.3% | estimated ± 4.5 pp, high confidence |
| SWE-bench Verified | 77.2% | measured |
| AutomationBench | 28.4% | estimated ± 9.7 pp, low confidence |
| BFCL v4 | 73.9% | estimated ± 2.6 pp, high confidence |
| CyberGym | 61.0% | estimated ± 5.3 pp, low confidence |
| JobBench | 42.3% | estimated ± 8.4 pp, low confidence |
| SWE-bench Pro | 53.5% | measured |
| τ³-bench results | 68.9% | estimated ± 8.9 pp, medium confidence |
| WideResearch | 76.5% | estimated ± 5.9 pp, low confidence |
| AA Agentic Index | 20.1% | measured |
| MMLU-Pro | 86.2% | measured |
| FrontierMath v2 (Tier 4) | 0.0% | estimated ± 3.7 pp, low confidence |
| FrontierMath v2 (Tiers 1-3) | 24.4% | estimated ± 8.4 pp, low confidence |
| GPQA | 87.8% | measured |
| AA-IFBench | 67.6% | measured |
| Gert Labs | 54.8% | measured |
| AA-AnalystAgent | 17.0% | estimated ± 12.0 pp, low confidence |
| AA EnterpriseOps-Gym | 45.1% | estimated ± 3.6 pp, medium confidence |
| AA Harvey LAB | 81.0% | estimated ± 1.2 pp, low confidence |
| ApprenticeBench | 0.0% | estimated ± 3.1 pp, low confidence |
| ARC-AGI-1 | 58.2% | estimated ± 5.4 pp, medium confidence |
| ARC-AGI-2 | 38.8% | estimated ± 11.6 pp, low confidence |
| CursorBench 3.1 | 26.3% | estimated ± 3.4 pp, low confidence |
| CursorBench 3.2 | 47.6% | estimated ± 3.6 pp, medium confidence |
| FrontierCode 1.1 Main | 16.3% | estimated ± 2.7 pp, low confidence |
| FrontierSWE v2 | 3.6% | estimated ± 9.0 pp, low confidence |
| OfficeQA Pro | 50.3% | estimated ± 7.2 pp, low confidence |
| OSWorld-Verified | 64.8% | estimated ± 5.9 pp, medium confidence |
| Vals GPQA Diamond | 83.5% | estimated ± 4.8 pp, high confidence |
| Vals LiveCodeBench | 80.8% | estimated ± 4.7 pp, medium confidence |
| Vals MMLU-Pro | 85.2% | estimated ± 1.2 pp, high confidence |
| Vals SWE-bench | 70.0% | measured |
| Terminal-Bench 2.1 (Vals AI) | 52.0% | estimated ± 6.3 pp, medium confidence |
| AA AutomationBench | 4.1% | estimated ± 7.0 pp, medium confidence |
| GDP.pdf | 9.4% | estimated ± 5.4 pp, medium confidence |
| AA ITBench | 46.1% | estimated ± 3.6 pp, medium confidence |
| AA Tau3 Banking | 22.0% | estimated ± 5.8 pp, medium confidence |
| CursorBench 4.0 | 18.3% | estimated ± 1.6 pp, medium confidence |
| CWE-bench v1 | 34.3% | estimated ± 6.9 pp, low confidence |
| DeepSWE | 20.2% | estimated ± 6.4 pp, low confidence |
| HLE w/o tools | 27.6% | estimated ± 4.9 pp, high confidence |
| OSWorld 2.0 | 3.4% | estimated ± 4.5 pp, low confidence |
| PostTrainBench v1.1 | 20.5% | estimated ± 3.3 pp, medium confidence |
| SWE Multilingual | 71.3% | measured |
| Toolathlon-Verified | 48.3% | estimated ± 2.3 pp, low confidence |
| Vibe Code Bench | 14.7% | estimated ± 8.1 pp, medium confidence |
| CharXiv | 78.4% | measured |
| CharXiv w/o tools | 79.9% | estimated ± 1.8 pp, medium confidence |
| ExploitGym | 0.0% | estimated ± 12.2 pp, low confidence |
| C-Eval | 91.4% | measured |
| Claw-Eval | 72.4% | measured |
| DeepPlanning | 25.3% | estimated ± 11.8 pp, low confidence |
| HMMT Feb 2025 | 93.8% | measured |
| HMMT Feb 2026 | 84.3% | measured |
| HMMT Nov 2025 | 90.7% | measured |
| MathVision | 88.3% | estimated ± 1.4 pp, low confidence |
| MCP Atlas | 64.7% | estimated ± 7.8 pp, low confidence |
| MCP-Tasks | 98.1% | estimated ± 6.4 pp, low confidence |
| MMAnswerBench | 80.8% | measured |
| MMLU-ProX | 83.3% | estimated ± 1.7 pp, medium confidence |
| MMLU-Redux | 93.5% | measured |
| MMMU-Pro | 75.8% | measured |
| NL2Repo | 36.2% | measured |
| NOVA-63 | 55.5% | estimated ± 1.6 pp, low confidence |
| QwenClawBench | 53.4% | measured |
| ScreenSpot Pro | 85.0% | estimated ± 2.5 pp, low confidence |
| SuperGPQA | 66.0% | measured |
| Terminal-Bench 2.0 | 59.3% | measured |
| Toolathlon | 40.4% | estimated ± 6.3 pp, medium confidence |
| V* | 94.7% | measured |
| VideoMMMU | 84.4% | measured |
| ERQA | 62.5% | measured |
| HealthBench Hard | 0.0% | estimated ± 5.1 pp, low confidence |
| LiveCodeBench Pro | 78.4% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (MM) | 65.1% | estimated ± 2.4 pp, high confidence |
| MMLU-Pro (Arcee) | 81.3% | estimated ± 4.0 pp, medium confidence |
| React Native Evals | 65.7% | estimated ± 2.4 pp, low confidence |
| ResearchClawBench | 19.5% | estimated ± 1.3 pp, high confidence |
| SWE-Rebench | 60.2% | estimated ± 3.6 pp, medium confidence |
| ARC-AGI-3 | 0.0% | estimated ± 2.1 pp, medium confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| DRACO | 71.6% | estimated ± 3.0 pp, medium confidence |
| FrontierCode 1.1 Extended | 15.8% | estimated ± 2.4 pp, low confidence |
| HealthBench (raw) | 31.6% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 45.9% | estimated ± 4.8 pp, low confidence |
| HealthBench Professional (raw) | 43.3% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 68.5% | estimated ± 1.8 pp, low confidence |
| AIME 2025 | 94.8% | estimated ± 1.5 pp, medium confidence |
| MMMU | 82.9% | measured |
| LiveCodeBench | 83.9% | measured |
| OpenHarmony Bench | 51.0% | estimated ± 2.4 pp, medium confidence |
| IMOAnswerBench | 80.5% | estimated ± 5.9 pp, medium confidence |
| SimpleVQA | 56.1% | measured |
| ZeroBench | 47.9% | estimated ± 6.4 pp, low confidence |
| MMLU | 85.9% | estimated ± 1.1 pp, medium confidence |
| MMMU-Pro w/ Python | 77.2% | estimated ± 0.6 pp, high confidence |
| RefCOCO (avg) | 92.5% | measured |
| MATH-500 | 97.5% | estimated ± 3.1 pp, medium confidence |
| MathVision w/ Python | 76.8% | estimated ± 0.9 pp, low confidence |
| RealWorldQA | 84.1% | measured |
| Video-MME (with subtitle) | 87.7% | measured |
| OmniDocBench 1.5 | 91.0% | estimated ± 5.9 pp, low confidence |