MLVU Benchmark

What is MLVU?

MLVU test MLLMs' understanding of multi-task long videos, encompassing diverse tasks based on various long videos.

Released

2024-06-06

Modality

multimodal

Evaluates

多模态, Multimodal, 理解, Understanding, 多模态模型, VLM, 视频理解, Video Understanding, 不支持, Unsupported

Openness

restricted

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

MLVU paper, code and dataset

• Paper https://arxiv.org/abs/2406.04264
• Code https://github.com/JUNJIE99/MLVU
• Dataset https://huggingface.co/datasets/MLVU/MVLU

Which sources cite MLVU?

• MLVU

Related 多模态, Multimodal, 理解, Understanding, 多模态模型, VLM, 视频理解, Video Understanding, 不支持, Unsupported benchmarks

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