OCRRouter

Tesseract vs InternVL3.5

Pick Tesseract for clean printed scans, offline PDF searchability and cheap CPU batch jobs in many languages. Pick InternVL3.5 for document question answering and Markdown or JSON output, when you have GPUs and want one model family in several sizes. The main split is a CPU-only OCR engine that returns lines and words versus a GPU-hosted vision language model.

Tesseracttesseract/tesseractInternVL3.5opengvlab/internvl
TypeOpen sourceVision model
PriceFree2 credits / page
Per 1,000 pages$0.00$2.00
Typical speed0.6 s / page3.0 s / page
Best forClean printed text, freeSelf-hosted document understanding
InputsPDF, imagesimages
Languages100+ languagesMultilingual
Max pages per request500500
TablesNo✓ Yes
HandwritingNoNo
MathNo✓ Yes
Bounding boxesNoNo
ConfidenceNoNo
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 Tesseract if

  • It runs on CPU only with no model server, so it fits small machines and offline use.
  • It recognizes more than 100 languages out of the box and can be trained for more.
  • It outputs plain text, hOCR, searchable PDF, TSV, ALTO and PAGE XML, and it is the engine behind OCRmyPDF.

Choose InternVL3.5 if

  • It comes in nine sizes from 1B to 241B, so you can trade accuracy for cost.
  • It is a vision language model, so it suits document question answering and returns Markdown or JSON.
  • 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

TesseractInternVL3.5
LicenceApache-2.0Apache-2.0, built on Apache-2.0 Qwen3
How you run itCLI or C++ library with an LSTM recognizer, locallySelf-hosted with Transformers, LMDeploy or vLLM
HardwareCPU only, no GPU neededUp to 30B on one A100, 38B on two A100s, 241B-A28B on eight A100s
PriceFree, self-hosted (you pay for compute)Free, self-hosted (you pay for compute)
Output formatsPlain text, hOCR, searchable PDF, TSV, ALTO, PAGEPlain text, Markdown, JSON
Layout and coordinatesLines and words only, no table structure, formula or reading-order outputNo bounding boxes or layout output by default
Input quality and handwritingNeeds binarization, deskew and about 300 DPI input; not built for handwriting; confuses digit 1 with lowercase l (issue #2753)Not published
OCR benchmark scoresNot publishedNot published as text; the model card shows OCR scores only as chart images

Sources

What each one is

Tesseract

The classic open-source OCR engine. Plain text from clean printed scans.

Tesseract 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": "tesseract/tesseract","fallbacks": ["opengvlab/internvl"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Tesseract alternativesInternVL3.5 alternativesBest OCR models in 2026