PhyGenBench

What is PhyGenBench?

PhyGenBench is a benchmark designed to evaluate physical commonsense correctness in text-to-video generation models. I

Released

2024-10-07

Modality

multimodal

Evaluates

多模态, Multimodal, 物理智能, Embodied AI, 跨模态推理, Cross-modal Reasoning, 空间理解, Spatial Understanding, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

PhyGenBench paper and code

• Paper https://arxiv.org/abs/2408.02718
• Paper https://arxiv.org/abs/2410.05363
• Code https://github.com/OpenGVLab/PhyGenBench

Which sources cite PhyGenBench?

• PhyGenBench

Related 多模态, Multimodal, 物理智能, Embodied AI, 跨模态推理, Cross-modal Reasoning, 空间理解, Spatial Understanding, 不支持, Unsupported benchmarks

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