mlfoundations-dev/DCFT-open-thoughts-subset-v1-etash_1742823125_eval_0981
收藏Hugging Face2025-03-24 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/mlfoundations-dev/DCFT-open-thoughts-subset-v1-etash_1742823125_eval_0981
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含了不同数学和编程任务的评价结果，包括AIME24、AIME25、AMC23、MATH500、GPQADiamond和LiveCodeBench。每个任务都提供了多次运行的准确率、解决的问题数和总问题数。
This dataset includes evaluation results for various mathematics and programming tasks, including AIME24, AIME25, AMC23, MATH500, GPQADiamond, and LiveCodeBench. Each task provides accuracy, number of problems solved, and total number of problems across multiple runs.
提供机构：
mlfoundations-dev
