OCRRouter

Qianfan OCR vs Docling

Pick Qianfan OCR when you need to parse scans, handwriting and scene text in many languages, with tables, formulas and key information extraction, and you have a GPU. Pick Docling when you ingest born-digital PDFs and Office files into a RAG pipeline and want structured JSON with layout, and it must run on CPU. The main split is model versus library: Qianfan OCR is a 4B end-to-end model, while Docling is a Python library whose scan accuracy depends on the OCR engine you plug in.

Qianfan OCRbaidu/qianfan-ocrDoclingibm/docling
TypeOCR APIOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed2.0 s / page2.2 s / page
Best forChinese documentsStructured export for RAG
InputsPDF, imagesPDF, images, DOCX
LanguagesChinese, English and moreLatin scripts, CJK
Max pages per request200500
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
Math✓ Yes✓ Yes
Bounding boxesNo✓ Yes
ConfidenceNoNo
FormsNoNo
Multilingual✓ YesNo
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 Qianfan OCR if

  • It scores 93.12 on OmniDocBench v1.5, the top end-to-end result in Baidu's table, while Docling has no published benchmark.
  • It covers 192 languages, handwriting and scene text in a single model.
  • It outputs Markdown, JSON, HTML, LaTeX and bounding boxes, which suits tables, formulas and key information extraction.

Choose Docling if

  • It parses PDF, DOCX, PPTX, XLSX, HTML, EPUB, images, emails and XBRL through one API.
  • It runs on CPU on macOS, Linux and Windows (x86_64 and arm64), with GPU as an optional speedup.
  • Its lossless JSON export keeps layout, reading order and table structure, and it has LangChain and LlamaIndex integrations.

Key differences

Qianfan OCRDocling
What it is4B end-to-end document parsing model from Baidu's Qianfan team (Qwen3-4B language model)Python library from IBM Research that converts documents into a DoclingDocument and plugs in OCR engines and VLMs
LicenceApache-2.0, commercial use allowedMIT; individual models have their own licences
How you run itSelf-host weights from Hugging Face, or use the Baidu Qianfan platformSelf-hosted library, free; you pay for compute
HardwareBenchmarked on one NVIDIA A100 with vLLM; not suited to CPU-only deploymentCPU works; GPU speeds up model stages
Output formatsMarkdown, JSON, HTML, LaTeX, bounding boxesMarkdown, HTML, JSON, DocTags, plain text
BenchmarksOmniDocBench v1.5 93.12, olmOCR-Bench 79.8, OCRBench 880 (author-reported)Not published
Known failure1.024 pages per second on an A100 even with W8A8; thinking mode can emit up to 16,384 tokensVersion 2.143.1 drops words and numbers with full-page Tesseract OCR (issue #5254); neighbouring columns can merge on some layouts (issue #5132)

Sources

What each one is

Qianfan OCR

Baidu's OCR-tuned vision model. Strong on Chinese documents and tables.

Qianfan OCR details

Docling

IBM's open-source document converter with a structured document model.

Docling 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": "baidu/qianfan-ocr","fallbacks": ["ibm/docling"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Qianfan OCR alternativesDocling alternativesBest OCR models in 2026