OCRRouter

GOT-OCR 2.0 vs Florence-2

Pick GOT-OCR 2.0 for formulas, tables, sheet music, chemical structures and English or Chinese documents where you need Markdown or LaTeX out. Pick Florence-2 for English scene text and short labels where you need line boxes, or where one small model must also do captioning and detection. The main split is structured document output versus a tiny, MIT-licensed model that returns only text and boxes.

GOT-OCR 2.0stepfun/got-ocr-2Florence-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 forFormatted text, formulas and chartsLightweight OCR with boxes
Inputsimagesimages
LanguagesChinese, EnglishEnglish
Max pages per request100500
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 GOT-OCR 2.0 if

  • It outputs Markdown, LaTeX, TikZ, SMILES and kern, so formulas, tables, charts and sheet music come out as structured text.
  • It supports region OCR guided by box coordinates or color, plus multi-page OCR with dynamic resolution.
  • It targets English and Chinese documents, while Florence-2 gets Chinese output mostly wrong.

Choose Florence-2 if

  • It is much smaller at 0.23B (base) or 0.77B (large), against 580M for GOT-OCR 2.0, and it is MIT licensed.
  • OCR_WITH_REGION returns quadrilateral boxes per 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.

Key differences

GOT-OCR 2.0Florence-2
LicenceCode Apache-2.0; training data CC BY-NC 4.0MIT
Model size580M parameters0.23B (base), 0.77B (large)
Output formatsPlain text, Markdown, LaTeX, TikZ, SMILES, kernPlain text and bounding boxes only; no Markdown, tables or LaTeX
Chinese textListed as a good fit (English and Chinese documents)Output mostly wrong; vocabulary lacks CJK characters
HandwritingNot publishedA Hugging Face blog test found spelling errors and missing spaces on cursive handwriting
Hardware and setupCUDA 11.8 and PyTorch 2.0.1 per the README; CPU users are pointed to a llama.cpp portSelf-hosted via Transformers; described as suited to lightweight edge OCR in English
Known failureLoops characters midway through recognition (issue #226); outputs wrong text on blank images instead of an empty string (issue #235); format mode is much worse than plain mode (issue #317)Spelling errors and missing spaces on French text; model card warns the continued-pretrained checkpoint used only 0.1B samples

Sources

What each one is

GOT-OCR 2.0

Unified OCR model that reads plain text, tables, formulas, sheet music and charts.

GOT-OCR 2.0 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": "stepfun/got-ocr-2","fallbacks": ["microsoft/florence-2"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

GOT-OCR 2.0 alternativesFlorence-2 alternativesBest OCR models in 2026