ProBench

What is ProBench?

ProBench is a benchmark that contains open-ended multimodal queries that require intensive expert-level knowledge to solve.

Released

2025-03-10

Modality

multimodal

Evaluates

多模态, Multimodal, 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/ProBench

ProBench paper, code and dataset

• Paper https://arxiv.org/abs/2503.06885
• Code https://github.com/Yan98/ProBench_eval
• Dataset https://huggingface.co/datasets/HelloKKMe/ProBench

Which sources cite ProBench?

• ProBench

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

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