DeepSeek · model
DeepSeek-R1-0528-Qwen3-8B benchmark scores
As of 2026-11-19, DeepSeek-R1-0528-Qwen3-8B (DeepSeek) has measured scores on 5 benchmarks and estimated scores on 24 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 59.0% | estimated ± 6.2 pp, medium confidence |
| AA-HLE | 5.0% | estimated ± 5.7 pp, medium confidence |
| AIME26 | 76.9% | estimated ± 4.3 pp, medium confidence |
| Artificial Analysis Intelligence Index | 6.7% | estimated ± 7.4 pp, medium confidence |
| CritPt | 0.3% | estimated ± 4.0 pp, high confidence |
| GPQA Diamond | 61.4% | estimated ± 1.2 pp, high confidence |
| HLE | 5.2% | estimated ± 6.5 pp, low confidence |
| AA-Omniscience Accuracy | 19.1% | estimated ± 8.0 pp, medium confidence |
| SWE-bench Verified | 58.0% | estimated ± 9.3 pp, low confidence |
| MMLU-Pro | 76.8% | estimated ± 4.4 pp, high confidence |
| AIME 2024 | 86.0% | measured |
| BBH | 82.7% | estimated ± 4.5 pp, low confidence |
| GPQA | 61.1% | measured |
| MMLU | 87.7% | estimated ± 4.2 pp, high confidence |
| Vals GPQA Diamond | 59.1% | estimated ± 4.5 pp, high confidence |
| Vals MMLU-Pro | 74.6% | estimated ± 2.3 pp, high confidence |
| MATH-500 | 97.5% | estimated ± 1.2 pp, high confidence |
| MMMLU | 78.9% | estimated ± 1.7 pp, high confidence |
| AIME 2025 | 76.3% | measured |
| AA MMLU-Pro | 84.4% | estimated ± 1.2 pp, low confidence |
| HLE w/o tools | 11.6% | estimated ± 5.1 pp, low confidence |
| C-Eval | 85.9% | estimated ± 1.2 pp, high confidence |
| HMMT Feb 2025 | 61.5% | measured |
| HMMT Feb 2026 | 42.9% | estimated ± 11.0 pp, low confidence |
| HMMT Nov 2025 | 64.2% | estimated ± 1.5 pp, medium confidence |
| MMLU-Redux | 87.9% | estimated ± 1.7 pp, high confidence |
| SuperGPQA | 42.2% | estimated ± 8.5 pp, low confidence |
| SimpleQA | 14.6% | estimated ± 13.4 pp, low confidence |
| LiveCodeBench | 60.5% | measured |