MMBench-Video

What is MMBench-Video?

MMBench-Video is a comprehensive video understanding evaluation benchmark that covers long videos, multiple shots, and evaluates the temporal understanding…

Released

2024-06-20

Modality

multimodal

Evaluates

多模态, Multimodal, 推理, Reasoning, 理解, Understanding, 多模态模型, VLM, 逻辑推理, 视频理解, Video Understanding, 官方自建, Official, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

MMBench-Video paper and code

• Paper https://arxiv.org/abs/2406.14515
• Code https://github.com/open-compass/VLMEvalKit

Which sources cite MMBench-Video?

• MMBench-Video

Related 多模态, Multimodal, 推理, Reasoning, 理解, Understanding, 多模态模型, VLM, 逻辑推理, 视频理解, Video Understanding, 官方自建, Official, 不支持, Unsupported benchmarks

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