OCRRouter

Granite Docling vs Florence-2

Pick Granite Docling to convert English PDFs with tables, code and equations into structured output inside a Docling pipeline. Pick Florence-2 for scene text and short labels where you need line boxes, or when the same model must also do captioning or detection. The main split is structure: Granite Docling outputs DocTags, Markdown, HTML and LaTeX, while Florence-2 returns only plain text and boxes.

Granite Doclingibm/granite-doclingFlorence-2microsoft/florence-2
TypeOpen sourceOpen source
Price1 credit / page1 credit / page
Per 1,000 pages$1.00$1.00
Typical speed1.5 s / page0.8 s / page
Best forSmall-model document conversionLightweight OCR with boxes
InputsPDF, imagesimages
LanguagesEnglish, experimental CJK and ArabicEnglish
Max pages per request500500
Tables✓ YesNo
HandwritingNoNo
Math✓ YesNo
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNoNo
MultilingualNoNo
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 Granite Docling if

  • It converts full pages to DocTags, Markdown, HTML or LaTeX with bounding boxes, so tables and equations keep their structure.
  • The model card reports table structure TEDS of 0.97 on FinTabNet, equation F1 of 0.968 and code recognition F1 of 0.988.
  • At 258M parameters and Apache-2.0, it is a low-cost fit for CPU or small GPU conversion inside Docling.

Choose Florence-2 if

  • OCR_WITH_REGION returns quadrilateral boxes for each text line, which suits scene text and short labels.
  • The same model also does captioning, detection and grounding, so one model can cover a pipeline that needs more than OCR.
  • It is MIT licensed and comes in 0.23B base and 0.77B large sizes, so it can run as lightweight edge OCR in English.

Key differences

Granite DoclingFlorence-2
Output formatsDocTags, Markdown, HTML, LaTeX, bounding boxesPlain text and bounding boxes only
LicenceApache-2.0MIT
Size258M parameters0.23B (base), 0.77B (large)
Tables and equationsTable structure TEDS 0.97 on FinTabNet, equation F1 0.968No table or LaTeX output
LanguagesEnglish primary; Japanese, Arabic and Chinese marked experimentalChinese output mostly wrong because the vocabulary lacks CJK characters
HandwritingNot publishedSpelling errors and missing spaces on cursive handwriting and French text in a Hugging Face blog test
Known failureRepetitive loops on page headings and invoices; may print only exclamation marks on GPUs without bfloat16 such as T4 unless run in float32Model card notes the continued-pretrained checkpoint used only 0.1B samples and might not be well trained

Sources

What each one is

Granite Docling

Compact IBM vision model that converts pages to DocTags for the Docling pipeline.

Granite Docling details

Florence-2

Small Microsoft vision model (0.23B and 0.77B) with OCR and OCR-with-regions tasks that return text with boxes.

Florence-2 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": "ibm/granite-docling","fallbacks": ["microsoft/florence-2"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Granite Docling alternativesFlorence-2 alternativesBest OCR models in 2026