OCRRouter

PaddleOCR-VL vs InternVL3.5

Pick PaddleOCR-VL for document parsing on a modest GPU: it is under 1B parameters and outputs Markdown and JSON for pages with text, tables, formulas and charts. Pick InternVL3.5 when you need document question answering or one model family at several sizes. The main split is a purpose-built parser against a general vision language model.

PaddleOCR-VLpaddle/paddleocr-vlInternVL3.5opengvlab/internvl
TypeOpen sourceVision model
Price6 credits / page2 credits / page
Per 1,000 pages$6.00$2.00
Typical speed1.3 s / page3.0 s / page
Best forCJK documentsSelf-hosted document understanding
InputsPDF, imagesimages
Languages109 languagesMultilingual
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ YesNo
Confidence✓ YesNo
FormsNoNo
Multilingual✓ Yes✓ Yes
On OCRRouterAvailableAvailable

Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.

Which to choose

Choose PaddleOCR-VL if

  • It recognizes text, tables, formulas and charts and outputs Markdown and JSON for full pages.
  • It supports 109 languages in one model, including Cyrillic, Arabic, Devanagari and Thai scripts.
  • At under 1B parameters it runs on much smaller GPUs than 7B document VLMs.

Choose InternVL3.5 if

  • It comes in nine sizes from 1B to 241B-A28B, so you can trade accuracy for cost.
  • It suits document question answering and self-hosted multimodal pipelines, not only text extraction.
  • Models up to 30B fit on a single A100, and the MoE variants 20B-A4B and 30B-A3B activate few parameters per token.

Key differences

PaddleOCR-VLInternVL3.5
LicenceApache-2.0Apache-2.0
Model size0.9B1B to 241B-A28B; the 8B variant is 8.5B
HardwareNVIDIA GPU recommended; CPU possible but slow; no minimum VRAM statedUp to 30B on a single A100; 38B needs two A100s; 241B-A28B needs eight A100s
Output formatsMarkdown and JSONPlain text, Markdown and JSON
Layout and coordinatesLayout analysis for full pages; the transformers path does element-level recognition onlyNo bounding boxes or layout output by default
Published OCR benchmarksOmniDocBench v1.6 overall 96.33 (version 1.6, authors); olmOCR-Bench overall 80.0 (independent)Not published as text; the model card shows OCR scores only as chart images
Known failureVersion 1.6 regresses Russian and Kazakh OCR on born-digital PDFs, hangs on blurry images, and decodes about 11x slower because use_cache ships as falseNot published

Sources

What each one is

PaddleOCR-VL

Open-source document model from Baidu. Excellent on Chinese, Japanese and Korean.

PaddleOCR-VL details

InternVL3.5

Shanghai AI Lab's open vision-language family (1B to 241B, August 2025), strong on OCR and document benchmarks.

InternVL3.5 details

Try both on your own file

Run the file once with each model and compare the output.

PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?

Use one, fall back to the other

{"model": "paddle/paddleocr-vl","fallbacks": ["opengvlab/internvl"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

PaddleOCR-VL alternativesInternVL3.5 alternativesBest OCR models in 2026