minicpm-ocr 1.0.1

MiniCPM-OCR · Fast, accurate parsing for real-world documents.

MiniCPM-OCR 1.0     MiniCPM-OCR Jev  

_{Get Started  ·  Model Weights  ·  Online Demo (China)  ·  Online Demo (Global)  |  English  ·  中文}

MiniCPM-OCR is a family of models for efficient document parsing and text recognition. MiniCPM-OCR 1.0 parses Chinese and English documents and PDFs, balancing quality and efficiency across challenging inputs such as scans, photographs, curved pages, and recaptured documents. MiniCPM-OCR Jev evaluates OCR results at the region level, distinguishing problematic regions from reliable ones. It works with different parsing models to help users locate content that needs review.

MiniCPM-OCR 1.0

MiniCPM-OCR 1.0 (1.3B) is the first OCR-specific model in the MiniCPM-V/o family. It focuses on text-centric document understanding, covering text, tables, formulas, charts, seals, and structured information extraction. Its key features include:

• 🏆 SOTA document parsing: MiniCPM-OCR 1.0 achieves a SOTA score of 93.68 on Real5-OmniDocBench, a benchmark for real-world document parsing, and demonstrates leading parsing capabilities on OmniDocBench v1.6, Wild-OmniDocBench, and olmOCR-Bench. It supports Chinese and English documents and PDFs, handling both standard documents and challenging capture conditions, including scans, curved pages, photographs, skewed pages, and recaptured documents.
• ⚡ Efficient inference. With DSpark decoding acceleration (DSpark-BF16, DSpark-GGUF), MiniCPM-OCR 1.0 improves end-to-end processing efficiency by 55%. Its throughput is approximately 1.49× that of PaddleOCR-VL-1.6 and 3.62× that of MinerU2.5 Pro, reducing the time needed for large-scale document parsing.
• 🔍 General recognition and information extraction: MiniCPM-OCR 1.0 achieves a SOTA score of 54.7 on OCRBench v2, demonstrating strong general OCR capabilities. It also supports key information extraction (KIE), extracting relevant document content for downstream information management and automated processing.
• 🛠️ Easy deployment and development: MiniCPM-OCR 1.0 supports vLLM, SGLang, llama.cpp, and Ollama from day one, with multiple chip platforms and quantized versions available at release. It supports further fine-tuning and provides a pip SDK, a full-featured API, and established agent workflows for application integration and customization. Online demos are available for China and global users.

SOTA Performance, Higher Throughput

Among the open-source OCR models shown below, MiniCPM-OCR 1.0 achieves a parsing throughput of 1.2 pages/s and the highest equally weighted average score across four document parsing benchmarks: OmniDocBench v1.6, Real5-OmniDocBench, Wild-OmniDocBench, and olmOCR-Bench.

_{The average score weights OmniDocBench v1.6, Real5-OmniDocBench, Wild-OmniDocBench, and olmOCR-Bench equally. The horizontal axis shows throughput in pages per second on a logarithmic scale. See the reproduction guide for test settings and reproduction details, and the model guide throughput evaluation for each model's throughput.}

Benchmark Comparisons

See the OCR model guide for per-benchmark bar charts and throughput details.

Examples

Left to right: original document, detected layout, and rendered Markdown.

English Documents

Chinese Documents

MiniCPM-OCR Jev

MiniCPM-OCR Jev is an OCR quality decision model for text, formulas, and tables. Given an image and its corresponding OCR result, it returns a quality score from 0 to 1 to help select reliable results and locate content that needs review.

• 🛡️ Strong performance in a small model: With only 2B parameters, MiniCPM-OCR Jev achieves an AUROC (×100) of 93.6 on JevOCRBench, outperforming JEV-35B-A3B (90.1) and approaching Qwen3.5-397B-A17B (93.8).
• 🧩 Consistent generalization: Across parsing results from MiniCPM-OCR 1.0, GLM-OCR, PaddleOCR-VL-1.6, and Xiaomi-OCR-0, its AUROC (×100) ranges from 91.9 to 93.4.

Evaluation Results

The table below reports overall and per-category AUROC (×100) on JevOCRBench. Higher values indicate better discrimination between correct and incorrect parsing results.

Review-Free Accuracy

Accuracy at different review-free rates across three document types.

Decision Examples

Jev scores for text, formula, and table recognition.

See the model guide, use cases, cross-model evaluation, and decision examples.

Using MiniCPM-OCR

Choose how to integrate MiniCPM-OCR 1.0 and MiniCPM-OCR Jev:

Skill

Ask a coding agent to follow the MiniCPM-OCR 1.0 skill to set up the environment, download models, and parse your first document. Send the following instruction to the agent:

Read and execute https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/SKILL_en.md

If you have already cloned this repository, you can use ./docs/SKILL_en.md directly.

API

Use the API to access MiniCPM-OCR 1.0 recognition and MiniCPM-OCR Jev quality scoring.

MiniCPM-OCR 1.0 API example  ·  MiniCPM-OCR Jev API example (coming soon)

Local Deployment

Run the models on your own hardware: MiniCPM-OCR 1.0 parses PDFs and images into Markdown or JSON, while MiniCPM-OCR Jev scores the parsing results.

MiniCPM-OCR 1.0 deployment tutorial · MiniCPM-OCR Jev deployment tutorial

Fine-Tuning

Model Weights

Model	Description	Main Model Weights	DSpark Heads
MiniCPM‑OCR 1.0	Efficient document parsing and text recognition for Chinese and English documents and PDFs, balancing quality and speed across scans, photographs, curved pages, and recaptured documents.	🤗   BF16 🤗   GGUF 🤗   AWQ 🤗   GPTQ	🤗   BF16 🤗   GGUF
MiniCPM‑OCR Jev	An OCR quality decision model for text, formulas, and tables. Given an image and its OCR result, it returns a quality score from 0 to 1.	🤗   BF16 🤗   GGUF 🤗   AWQ 🤗   GPTQ

💡 FAQ and Troubleshooting

See the FAQ for common questions about installation, model downloads, GPU memory, input formats, and unexpected outputs.

📄 License

The entire project is released under the Apache License 2.0, including code, documentation, and model weights for MiniCPM-OCR 1.0 and MiniCPM-OCR Jev.