DeepSeek · model
DeepSeek R1 Distill Qwen 14B benchmark scores
As of 2026-11-19, DeepSeek R1 Distill Qwen 14B (DeepSeek) has measured scores on 4 benchmarks and estimated scores on 21 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 57.0% | estimated ± 6.2 pp, medium confidence |
| AA-HLE | 4.3% | estimated ± 5.7 pp, medium confidence |
| Artificial Analysis Intelligence Index | 6.2% | estimated ± 7.4 pp, medium confidence |
| CritPt | 0.3% | estimated ± 4.0 pp, high confidence |
| GPQA Diamond | 59.4% | estimated ± 1.2 pp, high confidence |
| HLE | 4.6% | estimated ± 6.5 pp, low confidence |
| AA-Omniscience Accuracy | 19.1% | estimated ± 8.0 pp, medium confidence |
| SWE-bench Verified | 54.4% | estimated ± 9.3 pp, low confidence |
| MMLU-Pro | 75.7% | estimated ± 4.4 pp, high confidence |
| AIME 2024 | 69.7% | measured |
| BBH | 82.7% | estimated ± 4.5 pp, low confidence |
| GPQA | 59.1% | measured |
| MMLU | 87.5% | estimated ± 4.2 pp, high confidence |
| Vals GPQA Diamond | 57.1% | estimated ± 4.5 pp, high confidence |
| Vals MMLU-Pro | 73.5% | estimated ± 2.3 pp, high confidence |
| MATH-500 | 93.9% | measured |
| MMMLU | 77.8% | estimated ± 1.7 pp, high confidence |
| AIME 2025 | 56.1% | estimated ± 3.5 pp, high confidence |
| AA MMLU-Pro | 84.2% | estimated ± 1.2 pp, low confidence |
| HLE w/o tools | 11.6% | estimated ± 5.1 pp, low confidence |
| C-Eval | 85.2% | estimated ± 1.2 pp, high confidence |
| MMLU-Redux | 87.2% | estimated ± 1.7 pp, high confidence |
| SuperGPQA | 41.1% | estimated ± 8.5 pp, low confidence |
| SimpleQA | 14.6% | estimated ± 13.4 pp, low confidence |
| LiveCodeBench | 53.1% | measured |