Mistral AI OCR

The European Patent Office accelerates innovation with Mistral

The European Patent Office partnered with Mistral AI on a three-month proof of concept to automate patent document transcription. A 1B-parameter OCR model was fine-tuned on over 150,000 PDFs (50,000 unique patents) and built into a pipeline converting complex patent documents (with formulas, chemical structures, tables, and figures across multiple European languages) from Markdown to HTML to ST36-compliant XML, deployed on-premises. The system achieves 400,000 pages/day throughput with a character recognition error rate below 1%, cutting lead time from up to 5 days down to a few minutes.

European Patent OfficeMistral AI OCR