A new benchmark shows frontier image-editing models can sometimes follow instructions rendered inside an image and answer on the same canvas, with the best model, Nano Banana Pro, reaching 48.7% strict proxy accuracy versus 96.1% for humans.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Image-Space Rule Discovery
A new benchmark shows frontier image-editing models can sometimes follow instructions rendered inside an image and answer on the same canvas, with the best model, Nano Banana Pro, reaching 48.7% strict proxy accuracy versus 96.1% for humans.