LangNavBench

What is LangNavBench?

LangNavBench is a benchmark for evaluating natural language understanding in semantic navigation, built upon the manually verified LangNav open-set dataset.

Released

2025-07-09

Evaluates

理解, Understanding, 物理智能, Embodied AI, 语言理解, Comprehension, 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/LangNavBench

LangNavBench paper and code

• Paper https://arxiv.org/abs/2507.07299
• Code https://github.com/3dlg-hcvc/langmonmap

Which sources cite LangNavBench?

• LangNavBench

Related 理解, Understanding, 物理智能, Embodied AI, 语言理解, Comprehension, 空间理解, Spatial Understanding, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• Ada-LEval
• AECBench
• AFQMC
• AgentBoard