Dataset Hub

MME‑RealWorld is a benchmark dataset for multimodal large language models (MLLMs), containing 13,366 high‑resolution images and 29,429 manually annotated question‑answer pairs covering 43 tasks across five real‑world scenarios. It aims to address the limitations of existing benchmarks for practical applications, offering large scale, high quality, and challenging tasks. A Chinese version (MME‑RealWorld‑CN) with 5,917 QA pairs is also provided.

The MMAD dataset is a comprehensive benchmark dataset for multimodal large language models in the field of industrial anomaly detection, containing questions, images, and descriptive text. All questions are presented in multiple‑choice format and have been manually verified. Images come from multiple sources and retain ground‑truth mask format to facilitate future evaluation of segmentation performance of multimodal large language models. The descriptive text is mostly of good quality but has not been manually verified, so use with caution. MMAD aims to evaluate the performance of current multimodal large language models in industrial quality inspection and identify key challenges in industrial anomaly detection.