MinerU vs InternVL3.5
Pick MinerU to convert mixed PDF and Office files into Markdown, HTML, LaTeX or DOCX, especially Chinese and English papers, or when you only have a CPU. Pick InternVL3.5 when you want a general vision language model for document question answering under a plain Apache-2.0 licence. MinerU is a parsing tool with fixed output formats. InternVL3.5 is a model family you size to your GPUs.
MinerUopendatalab/mineru | InternVL3.5opengvlab/internvl | |
|---|---|---|
| Type | Open source | Vision model |
| Price | 2 credits / page | 2 credits / page |
| Per 1,000 pages | $2.00 | $2.00 |
| Typical speed | 2.0 s / page | 3.0 s / page |
| Best for | Academic PDFs | Self-hosted document understanding |
| Inputs | PDF, images | images |
| Languages | 80+ languages | Multilingual |
| Max pages per request | 500 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | ✓ Yes | No |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ Yes |
| 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
- It reads PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML in one tool, so a mixed corpus needs no extra converters.
- Its basic tier runs on CPU with about 2 GB RAM, so you can start batch conversion without a GPU.
- It renders to Markdown, HTML, LaTeX, DOCX, EPUB and JSON, and it has an independent olmOCR-Bench overall score of 75.2 (MinerU 2.5.4).
Choose InternVL3.5 if
- It uses the Apache-2.0 licence and is built on Apache-2.0 Qwen3, which avoids the custom licence and AGPL-tagged weights that come with MinerU.
- It comes in nine sizes from 1B to 241B, so you can trade accuracy for cost, and models up to 30B fit on a single A100.
- It suits document question answering and self-hosted multimodal pipelines, where you ask questions about a page instead of converting it.
Key differences
| MinerU | InternVL3.5 | |
|---|---|---|
| What it is | Document parsing toolkit with CLI, API and WebUI; VLM tier uses a 1.2B model | General vision language model family, 1B to 241B-A28B parameters |
| Licence | MinerU Open Source License (Apache-2.0 based with extra conditions); VLM weights tagged AGPL-3.0 | Apache-2.0 |
| Hardware | Basic tier: CPU, 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAM | Up to 30B on one A100; 38B needs two A100s; 241B-A28B needs eight A100s |
| Output formats | Markdown, HTML, LaTeX, DOCX, EPUB, JSON | Plain text, Markdown, JSON; no bounding boxes or layout output by default |
| Input files | PDF, images, DOCX, PPTX, XLSX, EPUB, OFD, HTML | Not published |
| Benchmarks | olmOCR-Bench overall 75.2 (MinerU 2.5.4); ParseBench mean 45.9 (MinerU2.5) | Not published as text; the model card shows OCR scores only as chart images |
| Known failure modes | Repeated content with 300 KB figure blocks; merged header rows dropped in tables such as bank statements; full-width Chinese punctuation converted to half-width | No word coordinates; larger sizes cannot run CPU-only |
Sources
- MinerU GitHub README
- olmOCR-Bench table
- Issue #5554 table header rows
- Issue #5765 punctuation
- Hugging Face model card (8B)
- InternVL GitHub
What each one is
MinerU
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
MinerU detailsInternVL3.5
Shanghai AI Lab's open vision-language family (1B to 241B, August 2025), strong on OCR and document benchmarks.
InternVL3.5 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": ["opengvlab/internvl"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
MinerU alternativesInternVL3.5 alternativesBest OCR models in 2026