Gpt2 Large
开源来自 OpenAI · 发布于 2022-03-02
5.6
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 6 benchmarks with 5.6% average. Top scores: IFEval (20.5%), MUSR (5.7%), BBH (HuggingFace) (3.3%).
基准测试分数
| 基准测试 | 类别 | 分数 | Bar |
|---|---|---|---|
| IFEval | language | 20.5 | |
| MUSR | reasoning | 5.7 | |
| BBH (HuggingFace) | general | 3.3 | |
| MMLU-PRO | knowledge | 1.6 | |
| GPQA | knowledge | 1.2 | |
| MATH Level 5 | math | 1.2 |