mlfoundations-dev/OpenThinker-7B_eval_03-11-25_18-36-38_0981
收藏Hugging Face2025-03-11 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/mlfoundations-dev/OpenThinker-7B_eval_03-11-25_18-36-38_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模型在不同评估任务上的预计算输出的数据集，用于评估模型性能。数据集包括了LiveCodeBench、AIME24、AIME25、AMC23、GPQADiamond、MATH500六个任务的准确率数据，以及每次运行的详细结果。
This dataset contains precomputed outputs of the OpenThinker-7B model on various evaluation tasks, used for assessing the models performance. The dataset includes accuracy data for six tasks: LiveCodeBench, AIME24, AIME25, AMC23, GPQADiamond, and MATH500, as well as detailed results for each run.
提供机构：
mlfoundations-dev
