ModelBest and OpenBMB Release MiniCPM-OCR Models

Oct 31, 2026
The open source MiniCPM-OCR series includes a document parsing model and a separate model that checks OCR output for errors.

ModelBest and OpenBMB released the open source MiniCPM-OCR series, the companies announced in a press release. The release includes MiniCPM-OCR 1.0, a 1.3 billion parameter document parsing model, and MiniCPM-OCR Jev, a 2 billion parameter model for assessing OCR output.

MiniCPM-OCR 1.0 processes scanned, photographed, curved, tilted and screen captured documents without image correction. It supports Chinese and English text, mathematical formulas, complex tables and extraction of specified fields from documents such as invoices, identity documents and financial statements.

MiniCPM-OCR Jev compares source images with OCR output and assigns confidence scores to text, formulas and tables. It can flag missing characters, recognition errors and formatting problems, select among results from multiple OCR systems and send uncertain results for human review.

The models are available through GitHub, Hugging Face and ModelScope. Supported software includes vLLM, SGLang, llama.cpp and Ollama, with hardware support covering AMD, Arm, Intel, NVIDIA, Apple Mac and several Chinese chip platforms.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

Guide
23 AI meeting assistants for financial advisors

23 AI meeting assistants for financial advisors

What each one captures, what it keeps and which records it changes, from standalone apps to the AI built into advisor CRMs.

Industry analysis

2025 Global Business Services Agenda: Gen AI Takes Center Stage

The Hackett Group

This industry analysis by The Hackett Group explores the transformative impact of generative artificial intelligence (Gen AI) on global business services (GBS) in 2025. The study highlights the shift from exploration to acceleration of Gen AI initiatives, with 89% of executives advancing these projects to improve customer satisfaction, innovate products, and reduce costs. The report also discusses the challenges and strategies for successful Gen AI adoption, emphasizing the need for a technology-enabled operating model and the importance of reskilling the workforce.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.