MVPBench

What is MVPBench?

MVPBench, a curated benchmark designed to rigorously evaluate visual physical reasoning through the lens of visual CoT. Each example features interleaved…

Released

2025-06-02

Modality

multimodal

Evaluates

多模态, Multimodal, 推理, Reasoning, 理解, Understanding, 多模态模型, VLM, 逻辑推理, 图像理解, Image Understanding, 不支持, Unsupported

Openness

open

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

MVPBench paper, code and dataset

• Paper https://arxiv.org/pdf/2505.24182
• Code https://github.com/CSU-JPG/MVPBench
• Dataset https://huggingface.co/datasets/CSU-JPG/MVPBench

Which sources cite MVPBench?

• MVPBench

Related 多模态, Multimodal, 推理, Reasoning, 理解, Understanding, 多模态模型, VLM, 逻辑推理, 图像理解, Image Understanding, 不支持, Unsupported benchmarks

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