{"slug": "mistral-s-new-ocr-model-beats-competitors-in-72-percent-of-blind-test-cases-says", "title": "Mistral's new OCR model beats competitors in 72 percent of blind test cases, company says", "summary": "Mistral AI released OCR 4, a new model that reads text from documents and identifies page elements like titles and tables. In a blind test with over 600 documents, independent reviewers preferred OCR 4's results 72 percent of the time over competing models. The model supports 170 languages and costs $4 per 1,000 pages.", "body_md": "# Mistral's new OCR model beats competitors in 72 percent of blind test cases, company says\n\n**Mistral AI has released OCR 4, a new model that reads text from documents like PDFs, Word files, and PowerPoint presentations.**\n\nUnlike earlier versions, OCR 4 doesn't just pull raw text. It also identifies where each element sits on the page and what role it plays - whether it's a title, a table, an equation, or a signature. This block classification helps break documents into meaningful sections automatically, useful for feeding them into search systems or letting AI agents process them. The model also outputs confidence scores, giving an estimate of how certain it is about each word or page it reads.\n\nOCR 4 supports 170 languages and works well even with less common ones, according to Mistral. In a blind test with over 600 documents, independent reviewers preferred OCR 4's results 72 percent of the time over competing models, the company says. The model is available through the [API](https://docs.mistral.ai/models/model-cards/ocr-4-0), [Mistral Studio](https://console.mistral.ai/), and [Microsoft Foundry](https://aka.ms/mistral-ocr4-tcblog). It costs $4 per 1,000 pages, or $2 in batch mode.\n\n```\nAI News Without the Hype – Curated by Humans\n\n\t\t\t\t\tSubscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive \"AI Radar\" frontier report six times a year, full archive access, and access to our comment section.\t\t\t\t\n\n\t\t\t\t\tSubscribe now\n```\n\n[Mistral](https://mistral.ai/news/ocr-4/)", "url": "https://wpnews.pro/news/mistral-s-new-ocr-model-beats-competitors-in-72-percent-of-blind-test-cases-says", "canonical_source": "https://the-decoder.com/mistrals-new-ocr-model-beats-competitors-in-72-percent-of-blind-test-cases-company-says/", "published_at": "2026-06-24 09:28:40+00:00", "updated_at": "2026-06-24 09:47:21.681730+00:00", "lang": "en", "topics": ["ai-products", "ai-tools", "machine-learning", "natural-language-processing", "ai-infrastructure"], "entities": ["Mistral AI", "OCR 4", "Microsoft Foundry", "Mistral Studio"], "alternates": {"html": "https://wpnews.pro/news/mistral-s-new-ocr-model-beats-competitors-in-72-percent-of-blind-test-cases-says", "markdown": "https://wpnews.pro/news/mistral-s-new-ocr-model-beats-competitors-in-72-percent-of-blind-test-cases-says.md", "text": "https://wpnews.pro/news/mistral-s-new-ocr-model-beats-competitors-in-72-percent-of-blind-test-cases-says.txt", "jsonld": "https://wpnews.pro/news/mistral-s-new-ocr-model-beats-competitors-in-72-percent-of-blind-test-cases-says.jsonld"}}