MJ-Bench

What is MJ-Bench?

MJ-Bench incorporates a comprehensive preference dataset to evaluate multimodal judges in providing feedback for image generation models across four key…

Released

2024-07-05

Modality

multimodal

Evaluates

多模态, Multimodal, 多模态模型, VLM, 视觉生成, Visual Generation, 不支持, Unsupported

Openness

open

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

MJ-Bench paper, code and dataset

• Paper https://arxiv.org/abs/2407.04842
• Code https://github.com/MJ-Bench/MJ-Bench
• Dataset https://huggingface.co/datasets/MJ-Bench/MJ-Bench

Which sources cite MJ-Bench?

• MJ-Bench

Related 多模态, Multimodal, 多模态模型, VLM, 视觉生成, Visual Generation, 不支持, Unsupported benchmarks

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