mlfoundations-dev/stratos_pdf_science_questions__unverified__v1_eval_03-18-25_22-14-26_0981
收藏Hugging Face2025-03-18 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/mlfoundations-dev/stratos_pdf_science_questions__unverified__v1_eval_03-18-25_22-14-26_0981
下载链接
链接失效反馈官方服务：
资源简介：
该数据集是关于预计算模型输出评估的，包含了不同测试集如AIME24、AIME25、AMC23、MATH500、GPQADiamond和LiveCodeBench的准确率、解题数量和总题量等信息。
This dataset is about precomputed model output evaluation, including accuracy, number of questions solved, and total number of questions for different test sets such as AIME24, AIME25, AMC23, MATH500, GPQADiamond, and LiveCodeBench.
提供机构：
mlfoundations-dev
