SEED-Bench

What is SEED-Bench?

SEED-Bench aims at the evaluation of generative comprehension in MLLMs, consisting of 19K multiple choice questions, which spans 12 evaluation dimensions…

Released

2023-07-30

Modality

multimodal

Evaluates

多模态, Multimodal, 理解, Understanding, 多模态模型, VLM, 图像理解, Image Understanding, 不支持, Unsupported

Openness

restricted

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

SEED-Bench paper, code and dataset

• Paper https://arxiv.org/abs/2307.16125
• Code https://github.com/AILab-CVC/SEED-Bench
• Dataset https://huggingface.co/datasets/AILab-CVC/SEED-Bench

Which sources cite SEED-Bench?

• SEED-Bench

Related 多模态, Multimodal, 理解, Understanding, 多模态模型, VLM, 图像理解, Image Understanding, 不支持, Unsupported benchmarks

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