MinerU vs GOT-OCR 2.0
Pick MinerU when you need to convert mixed PDFs and Office files into Markdown, HTML, LaTeX, DOCX or JSON, including on CPU-only machines. Pick GOT-OCR 2.0 when you need a small 580M model for formulas, sheet music, chemical structures or box-guided region OCR. The main split is scope: MinerU is a document parsing toolkit with several tiers, while GOT-OCR 2.0 is a single OCR model.
MinerUopendatalab/mineru | GOT-OCR 2.0stepfun/got-ocr-2 | |
|---|---|---|
| Type | Open source | Open source |
| Price | 2 credits / page | 1 credit / page |
| Per 1,000 pages | $2.00 | $1.00 |
| Typical speed | 2.0 s / page | 1.5 s / page |
| Best for | Academic PDFs | Formatted text, formulas and charts |
| Inputs | PDF, images | images |
| Languages | 80+ languages | Chinese, English |
| Max pages per request | 500 | 100 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | No |
| On OCRRouter | Available | Available |
Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.
Which to choose
Choose MinerU if
- Its basic ONNX tier runs on CPU with 2 GB RAM, so you can start batch conversion without a GPU.
- It accepts PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML in one tool, which suits mixed RAG corpora.
- It has a published independent score: 75.2 on olmOCR-Bench overall (MinerU 2.5.4), and the VLM tier reaches 2.12 pages per second on one A100 with vLLM.
Choose GOT-OCR 2.0 if
- It reads formulas, sheet music, chemical structures (SMILES), charts and geometry, and outputs LaTeX, TikZ, SMILES and kern.
- Region OCR can be guided by box coordinates or color, so you can read one part of a page.
- It is a 580M model that is merged into Hugging Face Transformers with batched inference, plus multi-page OCR and dynamic resolution.
Key differences
| MinerU | GOT-OCR 2.0 | |
|---|---|---|
| What it is | Document parsing toolkit with CLI, API and WebUI, from basic CPU tier to VLM tiers | Single 580M end-to-end OCR model for text, formulas, tables, charts and sheet music |
| Licence | MinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0 | Code Apache-2.0; training data CC BY-NC 4.0 |
| Hardware | Basic tier: CPU, 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAM | CUDA 11.8 and PyTorch 2.0.1 per the README; CPU users are pointed to a llama.cpp port |
| Input and output | Inputs: PDF, images, Office files, EPUB, OFD, HTML. Outputs: Markdown, HTML, LaTeX, DOCX, EPUB, JSON | Outputs: plain text, Markdown, LaTeX, TikZ, SMILES, kern |
| Benchmarks | olmOCR-Bench overall 75.2 (MinerU 2.5.4); ParseBench mean 45.9 (MinerU2.5) | Not published |
| Known failure: output | VLM pipeline can repeat content and produce 300 KB figure blocks (issue #5728) | Output can start looping characters midway (issue #226); returns wrong text on images with no text (issue #235) |
| Known failure: tables and formats | VLM tiers drop merged header rows in tables such as bank statement account lines (issue #5554); full-width Chinese punctuation becomes half-width with no switch (issue #5765) | Format mode gives much worse results than plain OCR mode (issue #317) |
Sources
- MinerU GitHub README
- olmOCR-Bench table
- Issue #5554 table header rows
- GOT-OCR2.0 GitHub
- GOT-OCR 2.0 paper
- GitHub issue index
What each one is
MinerU
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
MinerU detailsGOT-OCR 2.0
Unified OCR model that reads plain text, tables, formulas, sheet music and charts.
GOT-OCR 2.0 detailsTry both on your own file
Run the file once with each model and compare the output.
Use one, fall back to the other
{"model": "opendatalab/mineru","fallbacks": ["stepfun/got-ocr-2"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
MinerU alternativesGOT-OCR 2.0 alternativesBest OCR models in 2026