CVSBench

What is CVSBench?

CVSBench evaluates cross-view spatial reasoning in vision-language models using satellite-street image pairs. It includes tasks for cross-view VQA, grounding…

Released

2026-06-21

Evaluates

General AI, Reasoning, Vision & 3D

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.22476

CVSBench paper and dataset

• Paper https://arxiv.org/abs/2606.22476
• Dataset https://huggingface.co/datasets/zlyzlyzly/CVSBench

Which sources cite CVSBench?

• CVSBench

Related General AI, Reasoning, Vision & 3D benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A-OKVQA
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveFly-Bench