mlfoundations-dev/OpenThinker-32B_1743604989_eval_0981
收藏Hugging Face2025-04-02 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/mlfoundations-dev/OpenThinker-32B_1743604989_eval_0981
下载链接
链接失效反馈官方服务：
资源简介：
该数据集是OpenThinker-32B模型在不同数学任务上的评估结果，包括AIME24、AIME25、AMC23、MATH500、GPQADiamond和LiveCodeBench。每个任务都有详细的准确度、问题解决数和总问题数的记录，部分任务有多组运行数据。
This dataset contains evaluation results of the OpenThinker-32B model on various math tasks, including AIME24, AIME25, AMC23, MATH500, GPQADiamond, and LiveCodeBench. Each task has detailed records of accuracy, number of questions solved, and total number of questions, with some tasks having multiple runs of data.
提供机构：
mlfoundations-dev
