U4R/MME-Reasoning
收藏Hugging Face2025-06-13 更新2025-07-05 收录
下载链接：
https://hf-mirror.com/datasets/U4R/MME-Reasoning
下载链接
链接失效反馈官方服务：
资源简介：
MME-Reasoning是一个全面的基准，专门设计用于评估多模态大型语言模型（MLLMs）的推理能力。该数据集包括1188个精心挑选的问题，这些问题系统性地覆盖了归纳、演绎和假设三种逻辑推理类型，并涵盖了不同的难度等级。
MME-Reasoning is a comprehensive benchmark specifically designed to evaluate the reasoning capability of Multimodal Large Language Models (MLLMs). The dataset consists of 1,188 carefully curated questions that systematically cover inductive, deductive, and abductive types of logical reasoning, spanning a range of difficulty levels.
提供机构：
U4R
