Alibaba (Qwen) · model
Qwen3.6 Plus benchmark scores
As of 2026-11-22, Qwen3.6 Plus (Alibaba (Qwen)) has measured scores on 62 benchmarks and estimated scores on 142 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 88.2% | measured |
| AA-HLE | 27.8% | measured |
| AA-SciCode | 45.2% | estimated ± 3.1 pp, high confidence |
| AIME26 | 95.3% | measured |
| Artificial Analysis Intelligence Index | 27.0% | measured |
| CritPt | 2.9% | measured |
| GDPval-AA | 24.5% | measured |
| GPQA Diamond | 90.4% | estimated ± 0.1 pp, high confidence |
| HLE | 28.8% | measured |
| IFBench | 75.8% | measured |
| AA-LCR | 78.3% | measured |
| LiveCodeBench v6 | 87.1% | measured |
| AA-Omniscience Accuracy | 26.4% | measured |
| SciCode | 48.7% | estimated ± 2.9 pp, medium confidence |
| Terminal-Bench 2.1 | 68.7% | estimated ± 6.7 pp, medium confidence |
| BrowseComp | 69.8% | estimated ± 4.3 pp, high confidence |
| HLE w/ tools | 45.6% | estimated ± 5.3 pp, low confidence |
| IFEval | 94.3% | measured |
| LongBench v2 | 62.0% | measured |
| VITA-Bench | 44.3% | measured |
| τ²-bench results | 97.7% | measured |
| AA Coding Index | 54.5% | measured |
| AA-MMMU-Pro | 78.0% | measured |
| APEX-Agents | 17.6% | estimated ± 9.4 pp, low confidence |
| APEX-Agents-AA | 17.9% | estimated ± 5.5 pp, medium confidence |
| BioMysteryBench (human-difficult) | 30.5% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 81.1% | estimated ± 7.3 pp, low confidence |
| SWE-bench Verified | 78.8% | measured |
| AutomationBench | 48.6% | estimated ± 9.1 pp, low confidence |
| BFCL v4 | 73.3% | estimated ± 2.7 pp, high confidence |
| CyberGym | 51.7% | estimated ± 6.0 pp, low confidence |
| JobBench | 18.5% | estimated ± 5.1 pp, low confidence |
| SkillsBench | 46.7% | estimated ± 4.9 pp, medium confidence |
| SWE-bench Pro | 56.6% | measured |
| τ³-bench results | 70.7% | measured |
| WideResearch | 74.3% | measured |
| AA Agentic Index | 18.7% | estimated ± 3.1 pp, high confidence |
| MMLU-Pro | 88.5% | measured |
| AA-IFBench | 75.2% | measured |
| BBH | 100.0% | estimated ± 2.8 pp, medium confidence |
| FailureSensorIQ | 65.9% | estimated ± 1.7 pp, high confidence |
| GPQA | 90.4% | measured |
| MMLU | 90.5% | estimated ± 0.9 pp, high confidence |
| Vals GPQA Diamond | 87.4% | measured |
| Vals LiveCodeBench | 86.0% | measured |
| Vals MMLU-Pro | 87.7% | measured |
| MATH-500 | 97.7% | estimated ± 3.1 pp, medium confidence |
| MMMLU | 87.6% | estimated ± 0.7 pp, medium confidence |
| MMMU | 86.0% | measured |
| Chess Puzzles | 16.0% | measured |
| AIME 2025 | 96.6% | estimated ± 1.8 pp, medium confidence |
| AA MMLU-Pro | 85.3% | estimated ± 0.7 pp, high confidence |
| Gert Labs | 31.4% | measured |
| AA Tau3 Banking | 39.6% | estimated ± 2.0 pp, low confidence |
| AA Terminal-Bench 2.1 | 79.9% | estimated ± 2.5 pp, medium confidence |
| ApprenticeBench | 3.4% | estimated ± 10.4 pp, low confidence |
| ARC-AGI-1 | 82.5% | estimated ± 6.5 pp, medium confidence |
| ARC-AGI-2 | 55.7% | estimated ± 10.9 pp, low confidence |
| CursorBench 3.1 | 47.9% | estimated ± 4.8 pp, low confidence |
| CursorBench 3.2 | 53.1% | estimated ± 3.6 pp, high confidence |
| EBR-bench | 0.0% | estimated ± 10.4 pp, low confidence |
| Terminal-Bench 3.0 | 2.8% | estimated ± 6.9 pp, low confidence |
| FrontierCode 1.1 Main | 25.4% | estimated ± 4.2 pp, low confidence |
| FrontierMath v2 (Tier 4) | 7.3% | estimated ± 4.0 pp, high confidence |
| FrontierMath v2 (Tiers 1-3) | 38.2% | measured |
| FrontierSWE v2 | 9.7% | estimated ± 8.3 pp, medium confidence |
| Furniture Assembly | 32.9% | estimated ± 9.3 pp, medium confidence |
| MaxxBench | 47.2% | estimated ± 8.8 pp, medium confidence |
| MazeBench | 0.0% | estimated ± 2.7 pp, high confidence |
| Mystery Game Puzzles | 12.0% | measured |
| NYT Connections | 60.3% | measured |
| OfficeQA Pro | 50.5% | estimated ± 6.8 pp, medium confidence |
| OSWorld-Verified | 68.6% | estimated ± 3.8 pp, medium confidence |
| ParseBench-1 | 53.6% | estimated ± 5.2 pp, low confidence |
| Terminal-Bench 4.1 | 2.2% | estimated ± 9.2 pp, low confidence |
| Terminal-Bench Hard | 43.9% | measured |
| Vals SWE-bench | 73.4% | measured |
| Terminal-Bench 2.1 (Vals AI) | 53.2% | measured |
| VulcanBench v3 | 84.3% | estimated ± 5.6 pp, low confidence |
| CWE-Bench-AA | 41.1% | estimated ± 8.1 pp, medium confidence |
| AA Cyber Index | 23.2% | estimated ± 12.4 pp, low confidence |
| DeepsecBench-AA | 9.7% | estimated ± 8.2 pp, low confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 54.0% | estimated ± 4.3 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 31.0% | estimated ± 0.8 pp, low confidence |
| AA ITBench | 30.3% | estimated ± 4.4 pp, medium confidence |
| Bug Hunt Bench | 9.6% | estimated ± 7.2 pp, low confidence |
| Chartography (tools) | 82.1% | estimated ± 4.1 pp, low confidence |
| CursorBench 4.0 | 33.0% | estimated ± 3.3 pp, medium confidence |
| CWE-bench v1 | 40.1% | estimated ± 5.7 pp, medium confidence |
| DeepSWE | 56.3% | estimated ± 7.2 pp, low confidence |
| DRACO | 72.1% | estimated ± 2.0 pp, medium confidence |
| FrontierCode 2.0 | 20.2% | estimated ± 6.7 pp, low confidence |
| FrontierPhysics | 2.5% | estimated ± 5.0 pp, low confidence |
| HLE w/o tools | 41.1% | estimated ± 4.9 pp, high confidence |
| OSWorld 2.0 | 6.0% | estimated ± 6.9 pp, low confidence |
| OSWorld 2.1 | 14.5% | estimated ± 3.6 pp, medium confidence |
| OSWorld 2.1 Offline | 41.4% | estimated ± 10.1 pp, low confidence |
| PostTrainBench v1.1 | 18.4% | estimated ± 3.7 pp, medium confidence |
| SpireClimb | 5.8% | estimated ± 7.2 pp, low confidence |
| StealthMark | 34.7% | estimated ± 9.2 pp, medium confidence |
| SWE Multilingual | 73.8% | measured |
| Toolathlon-Verified | 64.2% | estimated ± 3.0 pp, high confidence |
| VulcanBench Frontier v4 | 77.7% | estimated ± 8.3 pp, low confidence |
| AA AutomationBench | 44.0% | estimated ± 9.9 pp, low confidence |
| GDP.pdf | 13.9% | estimated ± 4.2 pp, medium confidence |
| AA Terminal-Bench 4.0 | 0.0% | estimated ± 13.7 pp, low confidence |
| ARC-AGI-3 | 1.2% | estimated ± 8.6 pp, low confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| CWE-bench | 34.3% | estimated ± 6.2 pp, low confidence |
| MKA | 32.9% | estimated ± 4.6 pp, medium confidence |
| SkillsBench official leaderboard (BenchFlow) | 47.8% | estimated ± 6.1 pp, medium confidence |
| BinaryAudit | 35.8% | estimated ± 12.1 pp, low confidence |
| CompileBench | 66.7% | estimated ± 10.0 pp, low confidence |
| OTelBench | 14.2% | estimated ± 4.1 pp, low confidence |
| Vibe Code Bench | 25.6% | measured |
| FACTS Multimodal | 34.7% | estimated ± 4.0 pp, medium confidence |
| Hermes Bench | 55.3% | estimated ± 2.9 pp, high confidence |
| Hermes Index | 21.3% | estimated ± 5.7 pp, low confidence |
| ParseBench-2 | 70.3% | estimated ± 5.0 pp, medium confidence |
| CharXiv | 81.5% | measured |
| CharXiv w/o tools | 82.9% | estimated ± 1.2 pp, high confidence |
| ExploitBench | 23.8% | estimated ± 7.2 pp, low confidence |
| ExploitGym | 0.0% | estimated ± 8.3 pp, low confidence |
| AI2D_TEST | 93.4% | estimated ± 0.9 pp, medium confidence |
| C-Eval | 93.3% | measured |
| Claw-Eval | 58.8% | measured |
| CountBench | 97.3% | estimated ± 1.3 pp, medium confidence |
| DeepPlanning | 41.5% | measured |
| DynaMath | 86.1% | estimated ± 0.8 pp, medium confidence |
| ERQA | 68.1% | estimated ± 3.1 pp, high confidence |
| HMMT Feb 2025 | 96.7% | measured |
| HMMT Feb 2026 | 87.8% | measured |
| HMMT Nov 2025 | 94.6% | measured |
| INCLUDE | 84.7% | estimated ± 1.4 pp, low confidence |
| MathVision | 88.0% | measured |
| MAXIFE | 83.5% | estimated ± 2.2 pp, medium confidence |
| MCP Atlas | 48.2% | measured |
| MCP-Tasks | 74.1% | measured |
| MLVU (M-Avg) | 86.5% | estimated ± 1.5 pp, high confidence |
| MMAnswerBench | 83.8% | measured |
| MMLU-ProX | 84.7% | measured |
| MMLU-Redux | 94.5% | measured |
| MMMU-Pro | 78.8% | measured |
| NL2Repo | 37.9% | measured |
| NOVA-63 | 57.9% | measured |
| OmniDocBench 1.5 | 89.9% | estimated ± 2.2 pp, high confidence |
| PolyMath | 73.8% | estimated ± 11.4 pp, low confidence |
| PostTrainBench v1 | 19.0% | estimated ± 3.1 pp, medium confidence |
| QwenClawBench | 57.2% | measured |
| RealWorldQA | 83.0% | estimated ± 1.4 pp, medium confidence |
| ScreenSpot Pro | 68.2% | measured |
| SimpleVQA | 65.1% | estimated ± 7.1 pp, medium confidence |
| SuperGPQA | 71.6% | measured |
| Terminal-Bench 2.0 | 61.6% | measured |
| Toolathlon | 39.8% | measured |
| V* | 96.9% | measured |
| Video-MME (w/o subtitle) | 85.5% | estimated ± 1.2 pp, high confidence |
| Video-MME (with subtitle) | 87.6% | estimated ± 1.9 pp, high confidence |
| VideoMMMU | 84.0% | measured |
| We-Math | 87.5% | estimated ± 2.1 pp, medium confidence |
| AA LiveCodeBench | 88.1% | estimated ± 2.6 pp, high confidence |
| HealthBench Hard | 4.2% | estimated ± 5.1 pp, low confidence |
| LiveCodeBench Pro | 81.0% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (MM) | 72.0% | estimated ± 2.4 pp, high confidence |
| MMLU-Pro (Arcee) | 88.0% | estimated ± 4.0 pp, medium confidence |
| React Native Evals | 79.1% | estimated ± 2.7 pp, medium confidence |
| ResearchClawBench | 18.0% | measured |
| SWE-Rebench | 61.7% | estimated ± 3.6 pp, medium confidence |
| PostTrainBench | 15.8% | estimated ± 3.7 pp, medium confidence |
| DAYJOB | 1.3% | estimated ± 3.2 pp, high confidence |
| DAYJOB Healthcare | 0.7% | estimated ± 4.2 pp, high confidence |
| Finance Agent v2 | 55.1% | estimated ± 2.4 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| FrontierCode 1.1 Extended | 54.8% | estimated ± 3.0 pp, low confidence |
| HealthBench (raw) | 36.6% | estimated ± 6.0 pp, low confidence |
| HealthBench (length-adjusted) | 48.9% | estimated ± 3.4 pp, low confidence |
| HealthBench Professional | 51.9% | estimated ± 4.2 pp, low confidence |
| HealthBench Professional (raw) | 47.9% | estimated ± 4.5 pp, medium confidence |
| HLE-Verified | 15.4% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 81.8% | estimated ± 1.8 pp, low confidence |
| ScarfBench | 25.0% | estimated ± 9.1 pp, low confidence |
| BlenderWorld (text-only) | 70.0% | estimated ± 2.8 pp, medium confidence |
| Cookie-Bench | 76.9% | estimated ± 1.3 pp, medium confidence |
| STEMBench | 2.4% | estimated ± 0.2 pp, medium confidence |
| SimpleQA | 26.9% | estimated ± 4.3 pp, medium confidence |
| LiveCodeBench | 78.6% | estimated ± 14.6 pp, low confidence |
| Agents' Last Exam | 29.7% | estimated ± 9.7 pp, low confidence |
| BabyVision w/ Python | 88.8% | estimated ± 3.8 pp, low confidence |
| OpenHarmony Bench v1.0 | 43.2% | estimated ± 2.7 pp, medium confidence |
| SEC-Bench Pro | 37.1% | estimated ± 9.3 pp, medium confidence |
| IMOAnswerBench | 82.0% | estimated ± 5.6 pp, medium confidence |
| BabyVision | 53.9% | estimated ± 3.7 pp, high confidence |
| MMVU | 77.7% | estimated ± 2.7 pp, medium confidence |
| PerceptionBench | 55.0% | estimated ± 3.6 pp, medium confidence |
| ZeroBench | 15.7% | estimated ± 3.6 pp, medium confidence |
| MRCRv2 | 85.5% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 61.3% | estimated ± 2.6 pp, low confidence |
| OCRBench V2 | 70.4% | estimated ± 2.1 pp, medium confidence |
| BioBasicsBench | 22.8% | estimated ± 2.2 pp, low confidence |
| LifeVal | 8.9% | estimated ± 5.0 pp, low confidence |
| MMMU-Pro w/ Python | 80.9% | estimated ± 2.0 pp, high confidence |
| ExploitBench Internal Port | 0.0% | estimated ± 1.4 pp, low confidence |
| MathVision w/ Python | 94.0% | estimated ± 0.5 pp, low confidence |
| PinchBench | 94.5% | estimated ± 5.5 pp, low confidence |