Alibaba (Qwen) · model
Qwen3 235B-A22B benchmark scores
As of 2026-10-29, Qwen3 235B-A22B (Alibaba (Qwen)) has measured scores on 9 benchmarks and estimated scores on 16 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 60.8% | estimated ± 6.3 pp, medium confidence |
| AA-HLE | 5.4% | estimated ± 5.0 pp, high confidence |
| AIME26 | 29.7% | estimated ± 4.6 pp, low confidence |
| CritPt | 0.0% | estimated ± 0.8 pp, low confidence |
| GPQA Diamond | 63.2% | estimated ± 1.2 pp, high confidence |
| HLE | 13.4% | estimated ± 2.3 pp, low confidence |
| IFBench | 51.1% | estimated ± 9.2 pp, medium confidence |
| IFEval | 83.2% | measured |
| MMLU-Pro | 79.2% | estimated ± 1.1 pp, high confidence |
| AA-IFBench | 30.2% | estimated ± 8.8 pp, medium confidence |
| AIME 2024 | 40.1% | measured |
| Artificial Analysis Intelligence Index | 9.6% | estimated ± 3.8 pp, low confidence |
| GPQA | 62.9% | measured |
| MMLU | 87.7% | estimated ± 4.3 pp, high confidence |
| AA-Omniscience Accuracy | 21.6% | estimated ± 8.1 pp, medium confidence |
| MATH-500 | 91.2% | measured |
| MMMLU | 79.8% | measured |
| AA MMLU-Pro | 83.8% | estimated ± 1.0 pp, low confidence |
| AIME 2025 | 24.7% | measured |
| HLE w/o tools | 11.6% | estimated ± 5.2 pp, low confidence |
| C-Eval | 86.1% | measured |
| INCLUDE | 75.6% | measured |
| MMLU-Redux | 89.2% | measured |
| SuperGPQA | 58.3% | estimated ± 2.0 pp, low confidence |
| SimpleQA | 24.3% | estimated ± 14.6 pp, low confidence |