RealityBench tests VLMs on documenting physical work
Across 26 models, documentation is strong for in-frame text but weak for measurements and small spatial relations.
1 stories, newest first · one card per story
Across 26 models, documentation is strong for in-frame text but weak for measurements and small spatial relations.
Today 1.6K readers · 2.5K views · 780 reads · all time 189K views