MMKE-Bench

What is MMKE-Bench?

MMKE-Bench is a benchmark designed to evaluate the ability of LMMs to edit visual knowledge in real-world scenarios. It includes 2,940 pieces of knowledge and…

Released

2025-02-27

Evaluates

其他, Other, 多模态模型, VLM, 跨模态推理, Cross-modal Reasoning, 不支持, Unsupported

Openness

restricted

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

MMKE-Bench paper, code and dataset

• Paper https://arxiv.org/abs/2502.19870
• Code https://github.com/MMKE-Bench-ICLR/MMKE-Bench
• Dataset https://huggingface.co/datasets/kailinjiang/MMKE-Bench-dataset

Which sources cite MMKE-Bench?

• MMKE-Bench

Related 其他, Other, 多模态模型, VLM, 跨模态推理, Cross-modal Reasoning, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• Ada-LEval
• AECBench
• AFQMC
• AgentBoard