Radar ·
MiniCPM-OCR 1.0 and Jev: open OCR model and output verifier
Post presents MiniCPM-OCR 1.0, a 1.3B document reading model, and Jev, a 2B model that scores which OCR output regions may need human review. Benchmark figures are the author's.
The post describes MiniCPM-OCR 1.0, a 1.3B model for reading documents, and MiniCPM-OCR Jev, a 2B model that scores which regions of OCR output may need human review. The benchmark figures are cited by the author and have not been verified here. The stated relevance is for engineers building OCR pipelines who want to flag likely errors before text reaches RAG systems or agents.
To consult the original, open the post through its Radar reference, check the publication date and compare the benchmark figures with the sources the author cites. If you use AI to study this material, do not paste real documents containing CPF, CNPJ, e-mail addresses, phone numbers or person names into it; use anonymized excerpts.
Original source: MiniCPM-OCR 1.0 e Jev: modelo OCR aberto e verificador de saída