CamilleMolas/gdpval
收藏Hugging Face2025-12-17 更新2025-12-20 收录
下载链接:
https://hf-mirror.com/datasets/CamilleMolas/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模型在现实世界中有经济价值的任务上的表现。数据集包含220个真实世界的知识任务,涵盖44个职业。每个任务包括一个文本提示和一组支持性参考文件。数据集可能包含敏感内容,如NSFW内容、政治内容等,这些内容的存在是为了反映不同职业中的真实主题。数据集中的第三方品牌和商标仅用于研究和评估目的。
GDPval dataset is designed to evaluate AI model performance on real-world economically valuable tasks. It includes 220 real-world knowledge tasks across 44 occupations. Each task consists of a text prompt and a set of supporting reference files. The dataset may contain sensitive content such as NSFW themes and political content, which are included to reflect real themes addressed in various occupations. Third-party brands and trademarks in the dataset are used solely for research and evaluation purposes.
提供机构:
CamilleMolas



