Alibaba (Qwen) · model
Qwen3.5-27B benchmark scores
As of 2026-11-22, Qwen3.5-27B (Alibaba (Qwen)) has measured scores on 30 benchmarks and estimated scores on 125 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 85.8% | measured |
| AA-HLE | 23.9% | measured |
| AA-SciCode | 44.9% | estimated ± 3.8 pp, high confidence |
| Artificial Analysis Intelligence Index | 22.9% | measured |
| CritPt | 0.9% | measured |
| GDPval-AA | 22.9% | estimated ± 7.8 pp, medium confidence |
| GPQA Diamond | 85.6% | estimated ± 1.2 pp, high confidence |
| HLE | 22.1% | estimated ± 5.1 pp, medium confidence |
| IFBench | 73.8% | estimated ± 6.6 pp, medium confidence |
| AA-LCR | 77.7% | measured |
| LiveCodeBench v6 | 80.7% | measured |
| AA-Omniscience Accuracy | 20.7% | measured |
| SciCode | 44.1% | estimated ± 3.6 pp, high confidence |
| BrowseComp | 61.0% | measured |
| HLE w/ tools | 49.1% | estimated ± 5.5 pp, medium confidence |
| IFEval | 95.0% | measured |
| LongBench v2 | 60.6% | measured |
| VITA-Bench | 32.6% | estimated ± 6.7 pp, low confidence |
| τ²-bench results | 93.9% | measured |
| AA Coding Index | 44.9% | estimated ± 5.3 pp, medium confidence |
| AA-MMMU-Pro | 75.0% | measured |
| APEX-Agents-AA | 11.3% | estimated ± 4.4 pp, high confidence |
| BioMysteryBench (human-difficult) | 15.7% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 77.0% | estimated ± 6.8 pp, low confidence |
| SWE-bench Verified | 72.4% | measured |
| BFCL v4 | 68.4% | estimated ± 8.5 pp, low confidence |
| CyberGym | 71.3% | estimated ± 5.8 pp, low confidence |
| JobBench | 17.5% | estimated ± 10.7 pp, low confidence |
| SkillsBench | 33.8% | estimated ± 4.1 pp, low confidence |
| SWE-bench Pro | 50.1% | estimated ± 4.5 pp, high confidence |
| WideResearch | 73.3% | estimated ± 2.1 pp, low confidence |
| AA Agentic Index | 11.0% | estimated ± 8.0 pp, medium confidence |
| MMLU-Pro | 86.1% | measured |
| AA-IFBench | 75.6% | measured |
| BBH | 99.4% | estimated ± 2.8 pp, medium confidence |
| FailureSensorIQ | 65.0% | estimated ± 1.7 pp, high confidence |
| GPQA | 85.5% | measured |
| MMLU | 88.6% | estimated ± 0.9 pp, high confidence |
| Vals GPQA Diamond | 84.9% | estimated ± 3.2 pp, high confidence |
| Vals LiveCodeBench | 0.2% | estimated ± 3.4 pp, low confidence |
| Vals MMLU-Pro | 85.0% | estimated ± 2.3 pp, high confidence |
| MMMLU | 86.3% | estimated ± 0.7 pp, medium confidence |
| MMMU | 82.3% | measured |
| Chess Puzzles | 20.2% | estimated ± 12.3 pp, low confidence |
| AA MMLU-Pro | 84.2% | estimated ± 0.8 pp, medium confidence |
| Gert Labs | 28.9% | measured |
| AA Harvey LAB v1.0 | 85.7% | estimated ± 9.8 pp, low confidence |
| AA Tau3 Banking | 23.5% | estimated ± 3.6 pp, low confidence |
| ApprenticeBench | 3.2% | estimated ± 10.4 pp, low confidence |
| ARC-AGI-1 | 68.5% | estimated ± 6.7 pp, medium confidence |
| ARC-AGI-2 | 24.5% | estimated ± 10.9 pp, low confidence |
| FrontierCode 1.1 Main | 14.1% | estimated ± 4.2 pp, low confidence |
| MazeBench | 0.0% | estimated ± 2.7 pp, high confidence |
| Mystery Game Puzzles | 14.5% | estimated ± 14.6 pp, low confidence |
| NYT Connections | 47.9% | measured |
| OfficeQA Pro | 50.3% | estimated ± 6.8 pp, low confidence |
| OSWorld-Verified | 56.2% | measured |
| ParseBench-1 | 59.1% | estimated ± 6.2 pp, medium confidence |
| Terminal-Bench Hard | 41.5% | estimated ± 4.0 pp, medium confidence |
| Vals SWE-bench | 65.9% | estimated ± 6.6 pp, medium confidence |
| Terminal-Bench 2.1 (Vals AI) | 36.1% | estimated ± 6.4 pp, medium confidence |
| CWE-Bench-AA | 41.1% | estimated ± 6.4 pp, medium confidence |
| AA Cyber Index | 18.1% | estimated ± 12.4 pp, low confidence |
| DeepsecBench-AA | 8.8% | estimated ± 8.2 pp, low confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 52.8% | estimated ± 4.3 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 57.8% | estimated ± 1.1 pp, low confidence |
| AA ITBench | 35.5% | measured |
| Chartography (tools) | 80.3% | estimated ± 4.1 pp, low confidence |
| CWE-bench v1 | 38.6% | estimated ± 5.7 pp, medium confidence |
| DeepSWE | 33.5% | estimated ± 12.7 pp, low confidence |
| DRACO | 60.9% | estimated ± 2.9 pp, low confidence |
| HLE w/o tools | 34.2% | estimated ± 4.9 pp, high confidence |
| OSWorld 2.0 | 0.0% | estimated ± 3.6 pp, medium confidence |
| OSWorld 2.1 | 9.6% | estimated ± 3.6 pp, medium confidence |
| SpireClimb | 5.8% | estimated ± 7.2 pp, low confidence |
| StealthMark | 41.3% | estimated ± 10.7 pp, low confidence |
| SWE Multilingual | 69.9% | estimated ± 3.2 pp, low confidence |
| Toolathlon-Verified | 62.6% | estimated ± 3.0 pp, high confidence |
| AA AutomationBench | 42.7% | estimated ± 9.9 pp, low confidence |
| GDP.pdf | 13.1% | estimated ± 4.2 pp, medium confidence |
| ARC-AGI-3 | 1.3% | estimated ± 9.8 pp, medium confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| CWE-bench | 32.5% | estimated ± 6.2 pp, low confidence |
| MKA | 32.9% | estimated ± 4.6 pp, medium confidence |
| SkillsBench official leaderboard (BenchFlow) | 47.6% | 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 | 0.3% | estimated ± 8.4 pp, medium confidence |
| FACTS Multimodal | 28.2% | estimated ± 4.0 pp, medium confidence |
| Hermes Index | 19.8% | estimated ± 5.7 pp, low confidence |
| ParseBench-2 | 64.9% | estimated ± 5.0 pp, medium confidence |
| CharXiv | 79.5% | measured |
| CharXiv w/o tools | 79.3% | estimated ± 1.2 pp, high confidence |
| ExploitGym | 0.0% | estimated ± 8.3 pp, low confidence |
| AI2D_TEST | 93.4% | estimated ± 0.9 pp, medium confidence |
| C-Eval | 92.4% | estimated ± 1.0 pp, medium confidence |
| Claw-Eval | 54.1% | estimated ± 6.2 pp, low confidence |
| CountBench | 97.1% | estimated ± 1.3 pp, medium confidence |
| DynaMath | 85.5% | estimated ± 0.8 pp, medium confidence |
| ERQA | 63.3% | estimated ± 3.1 pp, high confidence |
| INCLUDE | 83.2% | estimated ± 1.4 pp, low confidence |
| MathVision | 86.0% | measured |
| MAXIFE | 74.8% | estimated ± 6.5 pp, low confidence |
| MCP Atlas | 66.9% | estimated ± 6.8 pp, medium confidence |
| MLVU (M-Avg) | 85.7% | estimated ± 1.5 pp, high confidence |
| MMLU-ProX | 82.2% | measured |
| MMLU-Redux | 93.8% | estimated ± 0.6 pp, high confidence |
| MMMU-Pro | 75.0% | measured |
| NL2Repo | 30.0% | estimated ± 3.4 pp, high confidence |
| NOVA-63 | 56.3% | estimated ± 1.3 pp, low confidence |
| OmniDocBench 1.5 | 89.4% | estimated ± 2.2 pp, high confidence |
| PolyMath | 42.5% | estimated ± 11.4 pp, low confidence |
| PostTrainBench v1 | 11.8% | estimated ± 5.5 pp, low confidence |
| RealWorldQA | 83.2% | estimated ± 1.5 pp, high confidence |
| ScreenSpot Pro | 70.7% | estimated ± 6.8 pp, medium confidence |
| SimpleVQA | 62.1% | estimated ± 7.1 pp, medium confidence |
| SuperGPQA | 65.6% | measured |
| Terminal-Bench 2.0 | 41.6% | measured |
| Toolathlon | 32.6% | estimated ± 4.2 pp, high confidence |
| V* | 93.7% | measured |
| Video-MME (w/o subtitle) | 82.3% | estimated ± 1.2 pp, high confidence |
| Video-MME (with subtitle) | 86.5% | estimated ± 1.9 pp, high confidence |
| VideoMMMU | 85.2% | estimated ± 1.5 pp, medium confidence |
| We-Math | 87.2% | estimated ± 2.1 pp, medium confidence |
| HealthBench Hard | 8.9% | estimated ± 8.6 pp, low confidence |
| MedXpertQA (MM) | 63.2% | estimated ± 2.4 pp, high confidence |
| MMLU-Pro (Arcee) | 80.5% | estimated ± 4.0 pp, medium confidence |
| React Native Evals | 76.2% | estimated ± 2.7 pp, medium confidence |
| ResearchClawBench | 13.9% | estimated ± 2.1 pp, low confidence |
| SWE-Rebench | 58.9% | measured |
| Finance Agent v2 | 55.1% | estimated ± 2.4 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (raw) | 32.3% | estimated ± 6.0 pp, low confidence |
| HealthBench (length-adjusted) | 47.5% | estimated ± 3.4 pp, low confidence |
| HealthBench Professional | 56.7% | estimated ± 4.2 pp, low confidence |
| HealthBench Professional (raw) | 43.9% | estimated ± 4.5 pp, medium confidence |
| HLE-Verified | 16.0% | estimated ± 7.1 pp, low confidence |
| STEMBench | 2.3% | estimated ± 0.2 pp, low confidence |
| SimpleQA | 19.1% | estimated ± 4.3 pp, medium confidence |
| LiveCodeBench | 74.6% | estimated ± 14.6 pp, low confidence |
| Agents' Last Exam | 29.6% | estimated ± 9.7 pp, low confidence |
| BabyVision w/ Python | 88.8% | estimated ± 3.8 pp, low confidence |
| BabyVision | 47.9% | estimated ± 3.7 pp, high confidence |
| MMVU | 73.3% | measured |
| PerceptionBench | 52.8% | estimated ± 3.6 pp, low confidence |
| ZeroBench | 15.7% | estimated ± 3.6 pp, low confidence |
| MRCRv2 | 85.4% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 61.3% | estimated ± 2.6 pp, low confidence |
| OCRBench V2 | 70.3% | estimated ± 3.3 pp, high confidence |
| BioBasicsBench | 33.9% | estimated ± 2.8 pp, low confidence |
| LifeVal | 39.3% | estimated ± 1.6 pp, low confidence |
| MMMU-Pro w/ Python | 78.2% | estimated ± 2.0 pp, high confidence |
| ExploitBench Internal Port | 0.4% | estimated ± 13.8 pp, low confidence |
| MathVision w/ Python | 92.8% | estimated ± 0.5 pp, low confidence |
| PinchBench | 88.9% | estimated ± 3.6 pp, medium confidence |