DeepSeek R1 Distill Llama 8B
开源来自 DeepSeek · 发布于 2025-01-20
33.6
平均分
N/A
输入价格
N/A
输出价格
N/A
上下文窗口
text-generation
类型
Tested on 11 benchmarks with 33.6% average. Top scores: JSQuAD (80.2%), JNLI (69.4%), JCommonsenseQA (62.4%).
基准测试分数
| 基准测试 | 类别 | 分数 | Bar |
|---|---|---|---|
| JSQuAD | language | 80.2 | |
| JNLI | language | 69.4 | |
| JCommonsenseQA | language | 62.4 | |
| LLM-JP — Overall | language | 41.4 | |
| IFEval | language | 37.8 | |
| JMMLU | language | 37.8 | |
| MATH Level 5 | math | 22.0 | |
| MMLU-PRO | knowledge | 12.1 | |
| BBH (HuggingFace) | general | 5.3 | |
| GPQA | knowledge | 0.7 | |
| MUSR | reasoning | 0.5 |