MMIU Benchmark

What is MMIU?

MMIU test MLLMs' multi-image understanding capabilities, encompassesing 7 types of multi-image relationships, 52 tasks, 77K images, and 11K meticulously…

Released

2024-08-05

Modality

multimodal

Evaluates

多模态, Multimodal, 理解, Understanding, 多模态模型, VLM, 图像理解, Image Understanding, 不支持, Unsupported

Openness

restricted

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/MMIU

MMIU paper, code and dataset

• Paper https://arxiv.org/abs/2408.02718
• Code https://github.com/OpenGVLab/MMIU
• Dataset https://huggingface.co/datasets/FanqingM/MMIU-Benchmark

Which sources cite MMIU?

• MMIU

Related 多模态, Multimodal, 理解, Understanding, 多模态模型, VLM, 图像理解, Image Understanding, 不支持, Unsupported benchmarks

• 3DCodeBench
• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• ActiveFly-Bench
• Ada-LEval
• AECBench