Video-MME Benchmark

What is Video-MME?

Video-MME is an evaluation benchmark of multi-modal LLMs in video analysis, including 900 videos in various duration with a total of 254 hours which spans 6…

Released

2024-03-31

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

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

Video-MME code

• Code https://github.com/BradyFU/Video-MME

Which sources cite Video-MME?

• Video-MME

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