LADBench

What is LADBench?

LADBench evaluates large vision-language models on detecting logical anomalies in synthetic images across four domains: Residential, Urban, Collaborative, and…

Released

2026-06-16

Evaluates

General AI, Vision & 3D, cs.CV

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.17433

LADBench paper and dataset

• Paper https://arxiv.org/abs/2606.17433
• Dataset https://huggingface.co/datasets/SahasraK/LADBench

Which sources cite LADBench?

• LADBench

Related General AI, Vision & 3D, cs.CV benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 360CityArena
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveSciBench