Alibaba (Qwen) · model
Qwen3.5-27B benchmark scores
As of 2026-10-07, Qwen3.5-27B (Alibaba (Qwen)) has measured scores on 25 benchmarks and estimated scores on 79 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 85.8% | measured |
| AA-HLE | 23.9% | measured |
| AA-SciCode | 44.7% | estimated ± 3.9 pp, high confidence |
| Artificial Analysis Intelligence Index | 22.9% | measured |
| CritPt | 0.9% | measured |
| GDPval-AA | 23.2% | estimated ± 8.4 pp, medium confidence |
| GPQA Diamond | 85.5% | estimated ± 0.4 pp, high confidence |
| HLE | 29.1% | estimated ± 7.8 pp, medium confidence |
| IFBench | 74.2% | estimated ± 6.9 pp, medium confidence |
| AA-LCR | 77.7% | measured |
| LiveCodeBench v6 | 85.0% | estimated ± 8.1 pp, low confidence |
| AA-Omniscience Accuracy | 20.7% | measured |
| SciCode | 44.9% | estimated ± 3.8 pp, high confidence |
| BrowseComp | 61.0% | measured |
| HLE w/ tools | 33.8% | estimated ± 4.6 pp, high confidence |
| IFEval | 95.0% | measured |
| LongBench v2 | 60.6% | measured |
| VITA-Bench | 34.5% | estimated ± 9.9 pp, low confidence |
| τ²-bench results | 93.9% | measured |
| AA Coding Index | 45.4% | estimated ± 5.1 pp, medium confidence |
| AA-MMMU-Pro | 75.0% | measured |
| APEX-Agents-AA | 10.5% | estimated ± 4.6 pp, high confidence |
| BioMysteryBench (human-difficult) | 27.7% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 77.2% | estimated ± 8.1 pp, low confidence |
| SWE-bench Verified | 72.4% | measured |
| AutomationBench | 17.3% | estimated ± 10.3 pp, low confidence |
| BFCL v4 | 69.4% | estimated ± 9.8 pp, low confidence |
| CyberGym | 64.8% | estimated ± 4.6 pp, medium confidence |
| JobBench | 32.8% | estimated ± 9.0 pp, medium confidence |
| SWE-bench Pro | 47.6% | estimated ± 3.2 pp, high confidence |
| τ³-bench results | 87.1% | estimated ± 8.9 pp, medium confidence |
| WideResearch | 68.2% | estimated ± 4.6 pp, high confidence |
| AA Agentic Index | 10.6% | estimated ± 6.4 pp, medium confidence |
| MMLU-Pro | 86.1% | measured |
| GPQA | 85.5% | measured |
| AA-IFBench | 75.6% | measured |
| Gert Labs | 39.4% | measured |
| AA-AnalystAgent | 9.0% | estimated ± 12.5 pp, low confidence |
| AA EnterpriseOps-Gym | 44.6% | estimated ± 3.6 pp, medium confidence |
| AA Harvey LAB | 85.7% | estimated ± 9.8 pp, low confidence |
| ApprenticeBench | 0.0% | estimated ± 3.1 pp, low confidence |
| ARC-AGI-1 | 65.8% | estimated ± 5.4 pp, medium confidence |
| ARC-AGI-2 | 23.9% | estimated ± 11.6 pp, low confidence |
| FrontierCode 1.1 Main | 6.2% | estimated ± 2.7 pp, low confidence |
| OfficeQA Pro | 50.3% | estimated ± 7.2 pp, low confidence |
| OSWorld-Verified | 56.2% | measured |
| Vals GPQA Diamond | 79.5% | estimated ± 4.8 pp, high confidence |
| Vals LiveCodeBench | 72.0% | estimated ± 9.9 pp, low confidence |
| Vals MMLU-Pro | 82.5% | estimated ± 1.2 pp, high confidence |
| Vals SWE-bench | 65.9% | estimated ± 6.8 pp, medium confidence |
| Terminal-Bench 2.1 (Vals AI) | 36.2% | estimated ± 6.3 pp, medium confidence |
| AA AutomationBench | 2.6% | estimated ± 5.7 pp, low confidence |
| GDP.pdf | 9.3% | estimated ± 6.6 pp, low confidence |
| AA ITBench | 46.2% | estimated ± 3.6 pp, medium confidence |
| AA Tau3 Banking | 17.6% | estimated ± 10.2 pp, low confidence |
| HLE w/o tools | 21.7% | estimated ± 4.9 pp, high confidence |
| OSWorld 2.0 | 0.0% | estimated ± 3.6 pp, medium confidence |
| SWE Multilingual | 70.5% | estimated ± 2.6 pp, low confidence |
| Toolathlon-Verified | 45.7% | estimated ± 7.7 pp, medium confidence |
| Vibe Code Bench | 1.0% | estimated ± 8.1 pp, medium confidence |
| CharXiv | 81.2% | estimated ± 3.3 pp, high confidence |
| CharXiv w/o tools | 83.7% | estimated ± 1.7 pp, low confidence |
| ExploitGym | 0.0% | estimated ± 6.1 pp, low confidence |
| C-Eval | 90.7% | estimated ± 0.7 pp, medium confidence |
| Claw-Eval | 55.0% | estimated ± 6.8 pp, low confidence |
| MathVision | 86.0% | measured |
| MCP Atlas | 60.6% | estimated ± 10.0 pp, low confidence |
| MCP-Tasks | 67.0% | estimated ± 8.2 pp, low confidence |
| MMLU-ProX | 82.2% | measured |
| MMLU-Redux | 93.6% | estimated ± 0.7 pp, high confidence |
| MMMU-Pro | 77.8% | estimated ± 2.2 pp, high confidence |
| NL2Repo | 32.2% | estimated ± 6.1 pp, medium confidence |
| NOVA-63 | 56.3% | estimated ± 1.3 pp, low confidence |
| ScreenSpot Pro | 67.1% | estimated ± 4.5 pp, medium confidence |
| SuperGPQA | 65.6% | measured |
| Terminal-Bench 2.0 | 41.6% | measured |
| Toolathlon | 31.8% | estimated ± 3.5 pp, high confidence |
| V* | 93.7% | measured |
| VideoMMMU | 85.6% | estimated ± 1.9 pp, low confidence |
| ERQA | 63.2% | estimated ± 2.4 pp, low confidence |
| HealthBench Hard | 0.0% | estimated ± 5.1 pp, low confidence |
| MedXpertQA (MM) | 72.1% | estimated ± 6.5 pp, low confidence |
| MMLU-Pro (Arcee) | 80.5% | estimated ± 4.0 pp, medium confidence |
| ResearchClawBench | 14.8% | estimated ± 2.2 pp, medium confidence |
| SWE-Rebench | 58.9% | measured |
| ARC-AGI-3 | 0.0% | estimated ± 2.1 pp, medium confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (raw) | 32.5% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 41.5% | estimated ± 4.8 pp, low confidence |
| HealthBench Professional (raw) | 44.2% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 70.8% | estimated ± 1.8 pp, low confidence |
| MMMU | 82.3% | measured |
| LiveCodeBench | 81.6% | estimated ± 10.2 pp, low confidence |
| BabyVision | 45.8% | estimated ± 4.3 pp, low confidence |
| MMVU | 73.3% | measured |
| ZeroBench | 13.3% | estimated ± 4.7 pp, low confidence |
| MMLU | 86.6% | estimated ± 1.1 pp, medium confidence |
| MMMU-Pro w/ Python | 78.7% | estimated ± 1.6 pp, high confidence |
| RefCOCO (avg) | 92.2% | estimated ± 1.8 pp, medium confidence |
| MathVision w/ Python | 92.8% | estimated ± 0.5 pp, low confidence |
| RealWorldQA | 1.2% | estimated ± 0.8 pp, low confidence |
| OmniDocBench 1.5 | 87.6% | estimated ± 6.4 pp, low confidence |