MVBench

What is MVBench?

MVBench can test MLLMs' temporal understanding in the dynamic video tasks. It covers 20 challenging video tasks that cannot be effectively solved with a single…

Released

2023-11-28

Modality

multimodal

Evaluates

多模态, Multimodal, 理解, Understanding, 多模态模型, VLM, 视频理解, Video Understanding, 开源收录, Open-Source, 不支持, Unsupported

Openness

open

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

MVBench paper, code and dataset

• Paper https://arxiv.org/abs/2311.17005
• Code https://github.com/OpenGVLab/Ask-Anything
• Dataset https://huggingface.co/datasets/OpenGVLab/MVBench

Which sources cite MVBench?

• MVBench

Related 多模态, Multimodal, 理解, Understanding, 多模态模型, VLM, 视频理解, Video Understanding, 开源收录, Open-Source, 不支持, Unsupported benchmarks

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