MiniCPM-OCR 1.0 and Jev: open-source OCR parsing and verification models
The pairing of a small parser with a separate verification model is the notable design choice: Jev is model-agnostic, so teams can keep their existing OCR engine and add quality checking without swapping stacks. Developers processing documents at volume can benchmark it against PaddleOCR-VL-1.6 or MinerU2.5 Pro using the released GitHub code, Hugging Face weights, and hosted API. The day-0 support across 12 chip vendors also eases deployment on non-NVIDIA hardware.
OpenBMB released the MiniCPM-OCR suite with two open-source models: MiniCPM-OCR 1.0, a 1B-scale OCR model scoring 93.68 on Real5-OmniDocBench and 54.7 on OCRBench v2, and MiniCPM-OCR Jev, a 2B verification model that scores 93.6 on JevOCRBench. Jev checks the accuracy of text, formulas, and tables from different OCR parsers and nearly matches Qwen3.5-397B-A17B (93.8) while outperforming JEV-35B-A3B (90.1). With the DSpark SDK, MiniCPM-OCR runs 1.49× faster than PaddleOCR-VL-1.6 and 3.62× faster than MinerU2.5 Pro, reaching up to 128 pages per minute. The models ship with quantized variants, fine-tuning support, and day-0 deployment on Arm, Houmo AI, Intel, NVIDIA plus 10 more chip vendors via FlagOS, and run on vLLM, SGLang, llama.cpp, and Ollama.
Your OCR says it’s done—but did it get everything right? 🤔 In high-stakes workflows, even a small error can be costly.
🚀 Meet the MiniCPM-OCR suite: an open-source solution to parse fast and guard the results.
Two new models: 🔹 MiniCPM-OCR 1.0 — SOTA OCR performance and speed at 1B scale. Compact, accurate, and fast. 🔹 MiniCPM-OCR Jev — A 2B decision model that helps assess parsing accuracy, with performance approaching that of Qwen3.5-397B-A17B on JevOCRBench.
⚡ What’s new? Small model, SOTA results: MiniCPM-OCR 1.0 scores 93.68 on Real5-OmniDocBench and 54.7 on OCRBench v2.
A sharp goalkeeper 🛡️: MiniCPM-OCR Jev is model-agnostic, checking text, formulas, and tables from different OCR parsers. It achieves 93.6 on JevOCRBench, outperforming JEV-35B-A3B (90.1) and approaching Qwen3.5-397B-A17B (93.8).
Up to 128 pages per minute 🤯: With DSpark, MiniCPM-OCR runs at 1.49× the speed of PaddleOCR-VL-1.6 and 3.62× that of MinerU2.5 Pro. The SDK’s concurrency optimizations further boost throughput to as much as 128 pages per minute.
Deploy where you work: Day-0 support for Arm, Houmo AI, Intel, and NVIDIA, plus 10 more chip vendors through FlagOS.
Ready for your stack: vLLM, SGLang, llama.cpp, and Ollama, with quantized models, fine-tuning support, and Agent Skills.
🔗 GitHub: https://t.co/2SlATAJk08 🤗 Hugging Face: MiniCPM-OCR 1.0：https://t.co/i347di4Fju MiniCPM-OCR Jev：https://t.co/ayVzhCJenh 👉 Try the Demo：https://t.co/QsFAJT3AFy Use the API：https://t.co/dP01jBS2j2
- rohanpaul_ai16:41原文
