Mistral debuts OCR 4, a model featuring structured document extraction with bounding boxes, block classification, and inline confidence scores, in 170 languages (Mistral AI Blog)

<a href="https://mistral.ai/news/ocr-4/"><img align="RIGHT" border="0" hspace="4" src="http://www.techmeme.com/260623/i37.jpg" vspace="4" /></a> <p><a href="https://www.techmeme.com/260623/p37#a260623p37" title="Techmeme permalink"><img height="12" src="http://www.techmeme.com/img/pml.png" style="border: none; padding: 0; margin: 0;" width="11" /></a> <a href="https://mistral.ai/">Mistral AI Blog</a>:<br /> <span style="font-size: 1.3em;"><b><a href="https://mistral.ai/news/ocr-4/">Mistral debuts OCR 4, a model featuring structured document extraction with bounding boxes, block classification, and inline confidence scores, in 170 languages</a></b></span>&nbsp; &mdash;&nbsp; Today, we're releasing Mistral OCR 4, featuring bounding boxes, block classification, and inline confidence scores alongside extracted text.</p>