mlfoundations-dev/OpenThinker-32B_1743569343_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_1743569343_eval_0981
下载链接
链接失效反馈官方服务：
资源简介：
这是一个包含预计算模型输出的评估数据集，用于评估模型在不同任务（AIME24、AIME25、AMC23、MATH500、GPQADiamond、LiveCodeBench）上的表现。每个任务都有详细的准确率、解决的问题数量和总问题数量，以及多次运行的平均准确率和标准差。
This is an evaluation dataset containing precomputed model outputs, used to assess the performance of the model on different tasks (AIME24, AIME25, AMC23, MATH500, GPQADiamond, LiveCodeBench). Each task includes detailed accuracy, number of questions solved, and total number of questions, as well as average accuracy and standard deviation across multiple runs.
提供机构：
mlfoundations-dev
