ProJudge Benchmark

What is ProJudge?

ProJudge is a comprehensive, multi-modal, multi-discipline, and multi-difficulty benchmark specifically designed for evaluating abilities of MLLM-based process…

Released

2025-03-09

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/ProJudge

ProJudge paper, code and dataset

• Paper https://arxiv.org/abs/2503.06553
• Code https://github.com/jiaxin-ai/ProJudge
• Dataset https://huggingface.co/datasets/julyai/ProJudgeBench

Which sources cite ProJudge?

• ProJudge

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