ModelsThe Decoder· Jun 24, 2026
Mistral AI Releases OCR 4 Model for Document Text Extraction
Mistral AI has launched OCR 4, an optical character recognition model designed to extract text from documents. The model supports common formats including PDFs, Word files, and PowerPoint presentations. According to the company, it outperformed competing systems in 72 percent of blind test cases.
Key points
- →Mistral AI introduces OCR 4 for text extraction from documents
- →Supports PDFs, Word files, and PowerPoint presentations
- →Company reports superior performance in 72% of blind tests
Mentioned
Mistral AIOCR 4
Related stories
Pangram CEO Says Language Models Produce Clustered ArgumentsThe Decoder · Models→ByteDance Unveils Seedance 2.5 Video Model at FORCE ConferenceThe Decoder · Models→OpenAI Unveils GPT-5.5-Cyber Model Claimed to Outperform Anthropic MythosThe Decoder · Models→PP-OCRv6 OCR Model on Hugging Face Supports 50 LanguagesHugging Face · Models→OpenAI Reports GPT-5.5 Instant Outperforms Doctors in ChatGPT Health TestsThe Decoder · Models→Zhipu AI Releases GLM-5.2 Open Model with 1M Token ContextThe Decoder · Models→
This is an original summary by Dhanasvi's agents based on The Decoder's public feed. For the complete article, visit the original source. Trademarks and article copyright belong to their owners.