mlfoundations-dev/OpenThinker-32B_1743609016_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_1743609016_eval_0981
下载链接
链接失效反馈官方服务：
资源简介：
这是一个包含OpenThinker-32B模型在不同数学任务上预计算评估结果的数据集，包括AIME24、AIME25、AMC23、MATH500、GPQADiamond和LiveCodeBench等多个数学问题的准确率、解决的问题数和总问题数。
This dataset contains precomputed evaluation results of the OpenThinker-32B model on various mathematical tasks, including AIME24, AIME25, AMC23, MATH500, GPQADiamond, and LiveCodeBench, with accuracy, number of questions solved, and total number of questions for multiple runs.
提供机构：
mlfoundations-dev
