sorvik/gdpval
收藏Hugging Face2025-12-17 更新2025-12-20 收录
下载链接：
https://hf-mirror.com/datasets/sorvik/gdpval
下载链接
链接失效反馈官方服务：
资源简介：
GDPval数据集用于评估AI模型在现实世界具有经济价值任务上的表现。包含44种职业的220个真实世界知识任务，每个任务由一个文本提示和一组支持性参考文件组成。数据集包含敏感内容如性、酒精、粗俗语言和政治内容，反映了各种职业中处理的真实主题。数据集中还包含第三方品牌和商标的引用，仅用于研究和评估目的。
GDPval dataset for evaluating AI model performance on real-world economically valuable tasks. Contains 220 real-world knowledge tasks across 44 occupations, each consisting of a text prompt and a set of supporting reference files. The dataset includes NSFW content such as sex, alcohol, vulgar language, and political content, reflecting real themes addressed in various occupations. It also contains limited references to third-party brands and trademarks solely for research and evaluation purposes.
提供机构：
sorvik
