bench-temp/mmlu-pt-high-school-ablation-v2-notink-equal
收藏数据链接：
官方服务：
资源简介：
该数据集包含来自健康与生物科学、人文、语言和STEM四个领域的题目，每个题目包含任务原始文本、问题ID、正确回答的难度数量（整数）和难度分数（浮点数）等特征，用于评估不同学科问题的难度。
This dataset contains questions from four domains: health and biological sciences, humanities, languages, and STEM. Each question includes features such as task raw text, question ID, difficulty in terms of number of correct answers (integer), and difficulty score (float), used to evaluate the difficulty of questions across different subjects.
提供机构：
bench-temp
