SEED-Bench-2

What is SEED-Bench-2?

SEED-Bench-2 assesses both text and image generation of MLLMs. It spans 27 evaluation dimensions, featuring 24K multiple-choice questions with precise human…

Released

2023-11-28

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-2

SEED-Bench-2 paper, code and dataset

• Paper https://arxiv.org/abs/2311.17092
• Code https://github.com/AILab-CVC/SEED-Bench
• Dataset https://huggingface.co/datasets/AILab-CVC/SEED-Bench-2

Which sources cite SEED-Bench-2?

• SEED-Bench-2

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