Alibaba (Qwen) · model
Qwen3.7 Plus benchmark scores
As of 2026-10-07, Qwen3.7 Plus (Alibaba (Qwen)) has measured scores on 54 benchmarks and estimated scores on 78 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 90.0% | measured |
| AA-HLE | 35.6% | measured |
| AA-SciCode | 46.1% | measured |
| AIME26 | 96.4% | estimated ± 1.3 pp, high confidence |
| Artificial Analysis Intelligence Index | 25.2% | measured |
| CritPt | 9.1% | measured |
| GDPval-AA | 13.5% | measured |
| GPQA Diamond | 90.3% | measured |
| HLE | 34.7% | measured |
| IFBench | 79.1% | measured |
| AA-LCR | 73.0% | measured |
| LiveCodeBench v6 | 87.8% | estimated ± 2.1 pp, high confidence |
| AA-Omniscience Accuracy | 22.5% | measured |
| SciCode | 51.3% | measured |
| Terminal-Bench 2.1 | 67.8% | estimated ± 6.9 pp, medium confidence |
| BrowseComp | 82.8% | estimated ± 2.2 pp, medium confidence |
| HLE w/ tools | 38.5% | estimated ± 6.1 pp, low confidence |
| IFEval | 94.6% | measured |
| LongBench v2 | 61.5% | estimated ± 5.9 pp, medium confidence |
| VITA-Bench | 45.6% | measured |
| τ²-bench results | 93.0% | measured |
| AA Coding Index | 55.9% | measured |
| AA-MMMU-Pro | 80.5% | measured |
| APEX-Agents | 28.4% | estimated ± 0.6 pp, medium confidence |
| APEX-Agents-AA | 22.4% | measured |
| BioMysteryBench (human-difficult) | 29.3% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 84.1% | estimated ± 4.5 pp, high confidence |
| SWE-bench Verified | 77.7% | measured |
| AutomationBench | 28.4% | estimated ± 9.7 pp, low confidence |
| BFCL v4 | 72.9% | measured |
| CyberGym | 60.7% | estimated ± 5.3 pp, low confidence |
| JobBench | 19.9% | estimated ± 4.9 pp, low confidence |
| SWE-bench Pro | 57.6% | measured |
| τ³-bench results | 70.7% | estimated ± 1.4 pp, low confidence |
| WideResearch | 61.5% | estimated ± 9.1 pp, low confidence |
| AA Agentic Index | 19.7% | measured |
| MMLU-Pro | 88.5% | measured |
| FrontierMath v2 (Tiers 1-3) | 39.0% | estimated ± 8.4 pp, low confidence |
| GPQA | 90.3% | measured |
| AA-IFBench | 78.0% | measured |
| Gert Labs | 47.5% | estimated ± 3.7 pp, low confidence |
| AA-AnalystAgent | 9.2% | estimated ± 5.5 pp, low confidence |
| AA EnterpriseOps-Gym | 43.0% | estimated ± 3.6 pp, medium confidence |
| AA Harvey LAB | 80.8% | estimated ± 1.2 pp, low confidence |
| ApprenticeBench | 0.0% | estimated ± 5.0 pp, low confidence |
| ARC-AGI-1 | 89.6% | estimated ± 2.7 pp, high confidence |
| ARC-AGI-2 | 57.0% | estimated ± 10.1 pp, low confidence |
| CursorBench 3.1 | 34.4% | estimated ± 3.4 pp, low confidence |
| CursorBench 3.2 | 54.7% | estimated ± 3.6 pp, high confidence |
| Terminal-Bench 3.0 | 2.7% | estimated ± 6.9 pp, low confidence |
| FrontierCode 1.1 Main | 17.7% | estimated ± 2.7 pp, low confidence |
| FrontierSWE v2 | 10.9% | estimated ± 9.0 pp, medium confidence |
| OfficeQA Pro | 60.4% | estimated ± 7.2 pp, medium confidence |
| OSWorld-Verified | 73.3% | measured |
| Vals GPQA Diamond | 89.6% | estimated ± 2.0 pp, high confidence |
| Vals LiveCodeBench | 86.6% | estimated ± 0.8 pp, medium confidence |
| Vals MMLU-Pro | 87.0% | estimated ± 1.2 pp, high confidence |
| Vals SWE-bench | 75.4% | estimated ± 5.3 pp, low confidence |
| Terminal-Bench 2.1 (Vals AI) | 52.8% | measured |
| AA AutomationBench | 3.8% | estimated ± 7.0 pp, low confidence |
| GDP.pdf | 7.1% | estimated ± 4.9 pp, medium confidence |
| AA ITBench | 41.3% | estimated ± 3.6 pp, low confidence |
| AA Tau3 Banking | 22.0% | estimated ± 5.8 pp, low confidence |
| AA Terminal-Bench 2.1 | 64.9% | estimated ± 4.4 pp, high confidence |
| AA Terminal-Bench 4.0 | 5.6% | estimated ± 14.0 pp, low confidence |
| CursorBench 4.0 | 19.7% | estimated ± 1.6 pp, medium confidence |
| CWE-bench v1 | 21.3% | estimated ± 6.9 pp, low confidence |
| DeepSWE | 24.3% | estimated ± 6.4 pp, low confidence |
| HLE w/o tools | 33.2% | estimated ± 2.9 pp, high confidence |
| OSWorld 2.0 | 2.8% | measured |
| PostTrainBench v1.1 | 24.2% | estimated ± 4.7 pp, medium confidence |
| SWE Multilingual | 75.8% | measured |
| Toolathlon-Verified | 42.5% | estimated ± 1.0 pp, low confidence |
| Vibe Code Bench | 19.7% | estimated ± 8.1 pp, medium confidence |
| CharXiv | 85.9% | measured |
| CharXiv w/o tools | 83.7% | estimated ± 1.7 pp, medium confidence |
| ExploitGym | 0.6% | estimated ± 6.9 pp, low confidence |
| C-Eval | 93.1% | estimated ± 0.7 pp, medium confidence |
| Claw-Eval | 62.7% | measured |
| DeepPlanning | 62.3% | measured |
| HMMT Feb 2025 | 98.4% | estimated ± 1.8 pp, low confidence |
| HMMT Feb 2026 | 92.9% | measured |
| MathVision | 90.3% | measured |
| MCP Atlas | 73.2% | measured |
| MCP-Tasks | 77.0% | estimated ± 0.6 pp, low confidence |
| MMAnswerBench | 86.6% | estimated ± 2.8 pp, low confidence |
| MMLU-ProX | 85.4% | measured |
| MMLU-Redux | 94.5% | measured |
| MMMU-Pro | 79.0% | measured |
| NL2Repo | 41.1% | measured |
| NOVA-63 | 58.8% | measured |
| QwenClawBench | 61.8% | measured |
| ScreenSpot Pro | 79.0% | measured |
| SuperGPQA | 71.4% | measured |
| Terminal-Bench 2.0 | 70.3% | measured |
| Toolathlon | 27.0% | estimated ± 6.3 pp, low confidence |
| V* | 97.0% | estimated ± 5.1 pp, low confidence |
| VideoMMMU | 85.4% | measured |
| ERQA | 69.8% | measured |
| HealthBench Hard | 3.5% | estimated ± 5.1 pp, low confidence |
| LiveCodeBench Pro | 81.8% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (MM) | 71.0% | measured |
| MedXpertQA (Text) | 54.7% | estimated ± 4.5 pp, medium confidence |
| MMLU-Pro (Arcee) | 87.0% | estimated ± 3.4 pp, low confidence |
| React Native Evals | 78.1% | estimated ± 3.5 pp, high confidence |
| ResearchClawBench | 17.1% | estimated ± 1.3 pp, high confidence |
| SWE-Rebench | 61.0% | estimated ± 3.6 pp, medium confidence |
| ARC-AGI-3 | 0.0% | estimated ± 2.1 pp, medium confidence |
| BioMysteryBench (human-solvable) | 82.7% | estimated ± 0.6 pp, low confidence |
| DRACO | 67.1% | estimated ± 3.0 pp, low confidence |
| FrontierCode 1.1 Extended | 55.2% | estimated ± 3.0 pp, low confidence |
| HealthBench (raw) | 44.9% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 50.7% | estimated ± 4.8 pp, low confidence |
| HealthBench Professional (raw) | 55.5% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 18.0% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 77.1% | estimated ± 1.8 pp, low confidence |
| MMMU | 87.7% | estimated ± 0.9 pp, medium confidence |
| LiveCodeBench | 89.6% | measured |
| OpenHarmony Bench | 51.0% | estimated ± 2.4 pp, high confidence |
| IMOAnswerBench | 86.0% | measured |
| BabyVision | 63.5% | estimated ± 4.3 pp, medium confidence |
| MMVU | 77.9% | estimated ± 2.9 pp, medium confidence |
| SimpleVQA | 81.7% | measured |
| ZeroBench | 17.2% | estimated ± 4.7 pp, low confidence |
| MMMLU | 89.0% | measured |
| MMLU | 87.7% | estimated ± 1.1 pp, medium confidence |
| MMMU-Pro w/ Python | 80.3% | estimated ± 0.6 pp, high confidence |
| MathVision w/ Python | 95.3% | estimated ± 0.5 pp, medium confidence |
| RealWorldQA | 86.9% | measured |
| Video-MME (with subtitle) | 88.0% | measured |
| OmniDocBench 1.5 | 91.4% | measured |