MMSI-Bench

What is MMSI-Bench?

MMSI-Bench is a novel Visual Question Answering (VQA) benchmark specifically designed to evaluate Multi-image Spatial Intelligence in multimodal large language…

Released

2025-05-30

Modality

multimodal

Evaluates

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

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

MMSI-Bench paper and code

• Paper https://arxiv.org/pdf/2505.23764
• Code https://github.com/OpenRobotLab/MMSI-Bench

Which sources cite MMSI-Bench?

• MMSI-Bench

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

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