MMLongBench-Doc

What is MMLongBench-Doc?

MMLongBench-Doc is a long-context multi-modal benchmark comprising 1,062 expert-annotated questions. Benchmark Radar tracks MMLongBench-Doc, cited by 1 source…

Released

2024-07-01

Evaluates

长文本, Long-Context, NeurIPS 2024, 多模态模型, VLM, 长上下文, Long Context, OCR与文档理解, OCR and Document Understanding, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/MMLongBench-Doc

MMLongBench-Doc paper, code and dataset

• Paper https://arxiv.org/abs/2407.01523
• Code https://github.com/mayubo2333/MMLongBench-Doc
• Dataset https://huggingface.co/datasets/yubo2333/MMLongBench-Doc

Which sources cite MMLongBench-Doc?

• MMLongBench-Doc

Related 长文本, Long-Context, NeurIPS 2024, 多模态模型, VLM, 长上下文, Long Context, OCR与文档理解, OCR and Document Understanding, 不支持, Unsupported benchmarks

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