A single place to compare open OCR models for agent-ready documents
now has a page that gathers OCR models and test results in one place. OCR turns text inside PDFs or scanned pages into digital text that software can read. The page lists major OCR , strong , and links to their papers and code.
Baidu recently released Unlimited OCR, a 3-billion-parameter model based on DeepSeek OCR that uses a new method called R-SWA. Mistral also released OCR 4, which is available through an API. Turning messy company PDFs into clean Markdown can make them easier for AI agents to read, search, and use.
This can support -augmented generation for internal knowledge chatbots or customer support systems.
Key points
- now lists OCR and leading models on one page.
- Baidu released Unlimited OCR, a 3-billion-parameter model based on DeepSeek OCR.
- Mistral released OCR 4 as an API-based option.
- OCR can turn PDFs and scans into text that AI agents can use more easily.
- Clean document text can support -augmented generation and chatbot use cases.