sleeping-ai/Moscow-Mule
收藏Hugging Face2024-12-06 更新2024-12-14 收录
下载链接：
https://hf-mirror.com/datasets/sleeping-ai/Moscow-Mule
下载链接
链接失效反馈官方服务：
资源简介：
Moscow Mule是一个多选问答（MCQA）基准数据集，旨在解决过去评估中的问题，并确保模型在排行榜上得到公平评估。该数据集是ICML 2025的一部分，未来会有更新。
Introducing Moscow Mule a MCQA benchmark dataset aimed to address past issues and solve them. We want to minimise the debackles created by past evals and make sure every model is evaluated fairly on the leaderboards. It’s part of ICML 2025. Updates will be posted later.
提供机构：
sleeping-ai
