Hacker News new | ask | show | jobs
by loaf_api 180 days ago
I've just finished processing thousands of documents using the Gemini Pro 3 vision model and it outperformed every OCR and image model I've tested by a long shot, perfect markdown with latex for the math every time.
2 comments
lysecret 179 days ago
3 flash is also insanely good even slightly outperforms 3 pro for me.
link
pacman1337 180 days ago
what prompt are you using?
link