mlfoundations-dev/OpenThinker-7B_eval_03-10-25_06-55-57_0981
收藏Hugging Face2025-03-10 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/mlfoundations-dev/OpenThinker-7B_eval_03-10-25_06-55-57_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-7B模型在不同数学和编程任务上预计算出的评估结果的数据集。它提供了LiveCodeBench、AIME24、AIME25、AMC23、GPQADiamond和MATH500等多个任务的准确度指标，包括平均准确度、每次运行解决的问题数和总问题数。
This dataset contains precomputed model outputs for evaluating the performance of the OpenThinker-7B model on various mathematical and coding tasks. It provides accuracy metrics for tasks such as LiveCodeBench, AIME24, AIME25, AMC23, GPQADiamond, and MATH500, including average accuracy, number of questions solved per run, and total number of questions.
提供机构：
mlfoundations-dev
