tilgasergey/gdpval-17-12-2025
收藏Hugging Face2025-12-17 更新2025-12-20 收录
下载链接：
https://hf-mirror.com/datasets/tilgasergey/gdpval-17-12-2025
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任务上的表现。包含220个真实世界的知识任务，涵盖44种职业。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和政治内容，如性、酒精、粗俗语言等，以及第三方品牌和商标的引用。
Dataset for GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks. 220 real-world knowledge tasks across 44 occupations. Each task consists of a text prompt and a set of supporting reference files. Some tasks include NSFW content, such as sex, alcohol, vulgar language, and political content, as well as references to third-party brands and trademarks.
提供机构：
tilgasergey
