Other · model
QwQ-32B benchmark scores
As of 2026-10-29, QwQ-32B (Other) has measured scores on 14 benchmarks and estimated scores on 24 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 59.3% | measured |
| AA-HLE | 7.4% | measured |
| AIME26 | 71.0% | estimated ± 4.6 pp, medium confidence |
| CritPt | 0.0% | estimated ± 0.8 pp, low confidence |
| GPQA Diamond | 65.9% | estimated ± 1.2 pp, high confidence |
| HLE | 18.6% | estimated ± 2.3 pp, low confidence |
| IFBench | 54.1% | estimated ± 6.6 pp, low confidence |
| AA-LCR | 26.7% | measured |
| IFEval | 83.9% | measured |
| LongBench v2 | 52.1% | estimated ± 5.8 pp, low confidence |
| BioMysteryBench (human-difficult) | 12.8% | estimated ± 8.1 pp, low confidence |
| MMLU-Pro | 80.4% | estimated ± 1.1 pp, high confidence |
| AA-IFBench | 38.8% | measured |
| AIME 2024 | 79.5% | measured |
| Artificial Analysis Intelligence Index | 9.5% | measured |
| GPQA | 65.6% | measured |
| MMLU | 85.4% | estimated ± 2.7 pp, high confidence |
| AA-Omniscience Accuracy | 21.3% | estimated ± 7.2 pp, medium confidence |
| MATH-500 | 98.0% | measured |
| MMMLU | 80.9% | measured |
| AA MMLU-Pro | 84.2% | estimated ± 1.0 pp, low confidence |
| AIME 2025 | 69.5% | measured |
| ARC-AGI-1 | 62.8% | estimated ± 8.1 pp, low confidence |
| ARC-AGI-2 | 30.7% | estimated ± 14.6 pp, low confidence |
| Vals GPQA Diamond | 81.3% | estimated ± 5.3 pp, low confidence |
| Vals MMLU-Pro | 83.9% | estimated ± 2.1 pp, medium confidence |
| HLE w/o tools | 29.0% | estimated ± 4.6 pp, medium confidence |
| ARC-AGI-3 | 1.4% | estimated ± 7.7 pp, low confidence |
| C-Eval | 88.4% | measured |
| HMMT Feb 2025 | 45.2% | estimated ± 3.1 pp, medium confidence |
| INCLUDE | 69.7% | measured |
| MMLU-Redux | 90.0% | measured |
| SuperGPQA | 62.4% | estimated ± 2.0 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.3 pp, medium confidence |
| HealthBench Professional (raw) | 50.3% | estimated ± 8.6 pp, low confidence |
| SimpleQA | 18.1% | estimated ± 7.8 pp, medium confidence |
| MRCRv2 | 22.8% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 55.3% | estimated ± 2.6 pp, low confidence |