ModelBest releases and open-sources MiniCPM-OCR series: 1.3B parsing model and 2B discrimination model
Original title:走向高效可信的文档智能|MiniCPM家族首个OCR系列模型发布并开源
AI summary
ModelBest released and open-sourced the MiniCPM-OCR series. MiniCPM-OCR 1.0 (1.3B) achieved SOTA scores of 93.68 on Real5-OmniDocBench and 54.7 on OCRBench v2, reaching 1.217 pages per second after DSpark acceleration, a 55% improvement in end-to-end efficiency.
Key Takeaways
- ModelBest released and open-sourced the MiniCPM-OCR series.
- MiniCPM-OCR 1.
- 3B) achieved SOTA scores of 93.
- 68 on Real5-OmniDocBench and 54.
- 7 on OCRBench v2,reaching 1.
Quick Facts
- Published
- Updated
- Source
- 公众号:面壁智能(MiniCPM)
- Category
- Model Releases
- AI score
- 66
原文给出双 SOTA 得分、吞吐实测与免检比例数据,并首次引入独立的解析结果判别模型,可用于评估文档解析落地方案。
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: ModelBest releases and open-sources MiniCPM-OCR series: 1.3B parsing model and 2B discrimination model. October 28, 2026. https://new.nat6.net/en/news/zd8g1y3609zl72lnwis70owqt/