mlfoundations-dev/QwQ-32B_1743609565_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/QwQ-32B_1743609565_eval_0981
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含了在不同数学竞赛数据集上的模型评估结果，具体包括AIME24、AIME25、AMC23、MATH500、GPQADiamond和LiveCodeBench。每个数据集的评估结果包括准确度、解决的问题数量和总问题数量，部分数据集还提供了多次运行的准确度详情。
This dataset contains model evaluation results on various mathematics competition datasets, including AIME24, AIME25, AMC23, MATH500, GPQADiamond, and LiveCodeBench. Each datasets evaluation results include accuracy, number of questions solved, and total number of questions, with detailed accuracy information for multiple runs provided for some datasets.
提供机构：
mlfoundations-dev
