OpenBMB's 1.3B MiniCPM-OCR scores 93.68 on real-world document parsing
OpenBMB released MiniCPM-OCR 1.0, a 1.3B model that turns document photos, scans and PDFs into text, tables, formulas, charts and seals. It scores 93.68 on Real5-OmniDocBench, which tests real-world captures such as curved, skewed and recaptured pages. With DSpark decoding acceleration, its throughput is about 1.49× PaddleOCR-VL-1.6 and 3.62× MinerU2.5 Pro. It runs on vLLM, SGLang, llama.cpp and Ollama.