---
title: "Discussion on \"Gemini 1.5 Pro can see, hear & read yet it still sucks at OCR\" | Hashnode"
description: "Discussion on \"Gemini 1.5 Pro can see, hear & read yet it still sucks at OCR\". TL,DR: I tested all major models with vision and neither of them can understand where the text on the screen appears. Here are my notes."
url: "https://hashnode.com/posts/gemini-15-pro-can-see-hear-read-yet-it-still-sucks-at-ocr/661cfd6d4801119c842b7069"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Gemini 1.5 Pro can see, hear & read yet it still sucks at OCR](https://lukasnotes.dk/gemini-15-pro-can-see-hear-read-yet-it-still-sucks-at-ocr?utm_source=hashnode&utm_medium=feed)

TL,DR: I tested all major models with vision and neither of them can understand where the text on the screen appears. Here are my notes.

Apr 15, 2024 · 7 min read · lukasnotes.dk  
Read the article

-   [#ai](https://hashnode.com/tag/ai)
-   [#challenge](https://hashnode.com/tag/challenge)
-   [#gemini](https://hashnode.com/tag/gemini)
-   [#ocr](https://hashnode.com/tag/ocr)
-   [#vision](https://hashnode.com/tag/vision)

## Written by

[Lukas](https://hashnode.com/@flexchar)

@flexchar · Copenhagen, DK

  
[View profile](https://hashnode.com/@flexchar)

A developer you can trust.

I've discovered coding back in 2013 and three years later I spent all my summer building my first Laravel app which is still in production by the non-profit I've built for. Now I'm struggling to find the balance between enjoying the power of "I can build this myself" and not chocking myself to death trying to build everything myself. As it is common for developers to be less articulate, I decided to leverage writing about my endeavours, to keep me up.

## Responses

Markdown supported · ⌘↵ to post

No responses yet.