mlfoundations-dev/AIME24_evalchemy_4shards_Qwen2.5-7B-Instruct
收藏Hugging Face2025-03-07 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/mlfoundations-dev/AIME24_evalchemy_4shards_Qwen2.5-7B-Instruct
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数据集，用于AIME24评估。数据集提供了5次运行的评估结果，包括准确度、解决的问题数量和总问题数量，平均准确度为9.33%。
This is a dataset containing precomputed model outputs for AIME24 evaluation. The dataset provides evaluation results of 5 runs, including accuracy, number of questions solved, and total number of questions, with an average accuracy of 9.33%.
提供机构：
mlfoundations-dev
