Alibaba (Qwen) · model
Qwen3.5-4B benchmark scores
As of 2026-10-29, Qwen3.5-4B (Alibaba (Qwen)) has measured scores on 7 benchmarks and estimated scores on 50 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 77.1% | measured |
| AA-HLE | 9.9% | measured |
| CritPt | 0.0% | measured |
| GDPval-AA | 25.3% | estimated ± 10.9 pp, low confidence |
| GPQA Diamond | 73.7% | estimated ± 2.5 pp, high confidence |
| HLE | 13.3% | estimated ± 9.7 pp, medium confidence |
| IFBench | 56.5% | estimated ± 6.6 pp, medium confidence |
| AA-LCR | 63.0% | measured |
| HLE w/ tools | 47.2% | estimated ± 5.5 pp, medium confidence |
| IFEval | 91.4% | estimated ± 2.8 pp, high confidence |
| LongBench v2 | 59.0% | estimated ± 5.8 pp, low confidence |
| τ²-bench results | 92.1% | measured |
| AA-MMMU-Pro | 65.4% | measured |
| BioMysteryBench (human-difficult) | 0.0% | estimated ± 6.8 pp, low confidence |
| BFCL v4 | 67.5% | estimated ± 8.5 pp, low confidence |
| AA Agentic Index | 23.7% | estimated ± 12.3 pp, low confidence |
| MMLU-Pro | 83.4% | estimated ± 6.9 pp, medium confidence |
| AA-IFBench | 52.0% | measured |
| Artificial Analysis Intelligence Index | 12.6% | estimated ± 5.8 pp, medium confidence |
| GPQA | 78.8% | estimated ± 6.1 pp, medium confidence |
| MMLU | 88.0% | estimated ± 8.3 pp, medium confidence |
| AA-Omniscience Accuracy | 22.7% | estimated ± 7.8 pp, medium confidence |
| MMMLU | 83.3% | estimated ± 0.7 pp, medium confidence |
| MMMU | 77.0% | estimated ± 2.7 pp, high confidence |
| AA MMLU-Pro | 85.9% | estimated ± 1.5 pp, medium confidence |
| ARC-AGI-1 | 74.7% | estimated ± 7.8 pp, low confidence |
| ARC-AGI-2 | 30.7% | estimated ± 14.6 pp, low confidence |
| OfficeQA Pro | 50.3% | estimated ± 6.8 pp, low confidence |
| ParseBench | 50.5% | estimated ± 5.5 pp, medium confidence |
| Vals GPQA Diamond | 68.1% | estimated ± 7.1 pp, medium confidence |
| Vals MMLU-Pro | 81.3% | estimated ± 2.3 pp, medium confidence |
| HLE w/o tools | 8.0% | estimated ± 5.4 pp, low confidence |
| ARC-AGI-3 | 1.4% | estimated ± 7.7 pp, low confidence |
| CharXiv | 74.2% | estimated ± 6.2 pp, low confidence |
| CharXiv w/o tools | 73.5% | estimated ± 2.6 pp, medium confidence |
| AI2D_TEST | 88.0% | estimated ± 2.0 pp, medium confidence |
| C-Eval | 90.8% | estimated ± 1.1 pp, low confidence |
| CountBench | 88.2% | estimated ± 2.9 pp, low confidence |
| DynaMath | 6.0% | estimated ± 3.0 pp, low confidence |
| ERQA | 38.0% | estimated ± 2.9 pp, medium confidence |
| MathVision | 69.4% | estimated ± 3.2 pp, medium confidence |
| MMLU-Redux | 90.3% | estimated ± 3.3 pp, high confidence |
| MMMU-Pro | 66.9% | estimated ± 1.6 pp, high confidence |
| RealWorldQA | 76.4% | estimated ± 2.7 pp, medium confidence |
| ScreenSpot Pro | 67.7% | estimated ± 11.2 pp, low confidence |
| V* | 0.5% | estimated ± 7.5 pp, low confidence |
| Video-MME (w/o subtitle) | 77.1% | estimated ± 1.7 pp, medium confidence |
| Video-MME (with subtitle) | 78.5% | estimated ± 3.7 pp, low confidence |
| HealthBench Hard | 0.0% | estimated ± 8.6 pp, low confidence |
| MedXpertQA (MM) | 19.5% | estimated ± 6.5 pp, low confidence |
| MMLU-Pro (Arcee) | 77.1% | estimated ± 4.0 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| STEMBench | 2.4% | estimated ± 0.2 pp, medium confidence |
| SimpleQA | 27.1% | estimated ± 7.8 pp, medium confidence |
| MRCRv2 | 35.2% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 60.5% | estimated ± 2.6 pp, low confidence |
| MMMU-Pro w/ Python | 69.6% | estimated ± 2.0 pp, high confidence |