Alibaba (Qwen) · model
Qwen3 Max benchmark scores
As of 2026-10-07, Qwen3 Max (Alibaba (Qwen)) has measured scores on 10 benchmarks and estimated scores on 53 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 76.4% | measured |
| AA-HLE | 11.9% | measured |
| AA-SciCode | 46.2% | estimated ± 3.8 pp, high confidence |
| Artificial Analysis Intelligence Index | 15.6% | measured |
| CritPt | 0.0% | measured |
| GDPval-AA | 18.7% | estimated ± 8.8 pp, medium confidence |
| GPQA Diamond | 75.6% | estimated ± 2.2 pp, high confidence |
| HLE | 19.0% | estimated ± 9.5 pp, medium confidence |
| IFBench | 56.3% | estimated ± 6.9 pp, medium confidence |
| AA-LCR | 50.0% | measured |
| AA-Omniscience Accuracy | 24.4% | measured |
| BrowseComp | 59.8% | estimated ± 5.7 pp, medium confidence |
| IFEval | 90.0% | estimated ± 1.3 pp, high confidence |
| LongBench v2 | 0.0% | estimated ± 5.9 pp, low confidence |
| τ²-bench results | 74.3% | measured |
| AA Coding Index | 40.5% | estimated ± 6.8 pp, medium confidence |
| APEX-Agents-AA | 1.6% | estimated ± 11.4 pp, low confidence |
| BioMysteryBench (human-difficult) | 30.8% | estimated ± 5.9 pp, low confidence |
| SWE-bench Verified | 72.3% | estimated ± 4.4 pp, high confidence |
| BFCL v4 | 52.9% | estimated ± 9.8 pp, low confidence |
| CyberGym | 36.9% | estimated ± 10.0 pp, low confidence |
| τ³-bench results | 68.9% | estimated ± 8.9 pp, medium confidence |
| WideResearch | 66.0% | estimated ± 5.9 pp, low confidence |
| AA Agentic Index | 12.6% | estimated ± 6.4 pp, medium confidence |
| MMLU-Pro | 85.5% | estimated ± 3.5 pp, high confidence |
| GPQA | 79.7% | estimated ± 3.2 pp, high confidence |
| AA-IFBench | 44.1% | measured |
| Gert Labs | 43.7% | measured |
| AA EnterpriseOps-Gym | 15.9% | estimated ± 3.6 pp, low confidence |
| ApprenticeBench | 0.0% | estimated ± 3.1 pp, low confidence |
| ARC-AGI-1 | 21.3% | estimated ± 5.4 pp, low confidence |
| ARC-AGI-2 | 6.4% | estimated ± 14.2 pp, low confidence |
| FrontierCode 1.1 Main | 1.3% | estimated ± 4.3 pp, low confidence |
| OSWorld-Verified | 56.1% | estimated ± 5.9 pp, medium confidence |
| Vals GPQA Diamond | 67.0% | estimated ± 7.4 pp, medium confidence |
| Vals MMLU-Pro | 83.9% | estimated ± 2.2 pp, high confidence |
| Vals SWE-bench | 64.1% | estimated ± 6.3 pp, medium confidence |
| AA ITBench | 65.4% | estimated ± 3.6 pp, low confidence |
| HLE w/o tools | 9.7% | estimated ± 5.7 pp, medium confidence |
| OSWorld 2.0 | 0.0% | estimated ± 4.5 pp, low confidence |
| PostTrainBench v1.1 | 19.9% | estimated ± 10.5 pp, low confidence |
| Vibe Code Bench | 3.5% | measured |
| C-Eval | 88.9% | estimated ± 1.0 pp, low confidence |
| Claw-Eval | 57.1% | estimated ± 6.8 pp, low confidence |
| MCP Atlas | 43.5% | estimated ± 14.8 pp, low confidence |
| MCP-Tasks | 79.5% | estimated ± 8.2 pp, low confidence |
| MMLU-Redux | 94.4% | estimated ± 1.1 pp, medium confidence |
| SuperGPQA | 69.4% | estimated ± 7.5 pp, medium confidence |
| Toolathlon | 37.5% | estimated ± 7.2 pp, medium confidence |
| HealthBench Hard | 2.0% | estimated ± 7.7 pp, low confidence |
| MMLU-Pro (Arcee) | 77.1% | estimated ± 4.0 pp, low confidence |
| React Native Evals | 30.4% | estimated ± 3.0 pp, low confidence |
| ResearchClawBench | 14.9% | estimated ± 2.2 pp, medium confidence |
| SWE-Rebench | 0.0% | estimated ± 6.5 pp, low confidence |
| ARC-AGI-3 | 1.7% | estimated ± 3.4 pp, medium confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (raw) | 17.6% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 57.7% | estimated ± 4.8 pp, low confidence |
| HealthBench Professional (raw) | 30.7% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 58.2% | estimated ± 1.8 pp, low confidence |
| MMLU | 88.6% | estimated ± 1.1 pp, medium confidence |