Compare / Docling

A Docling alternative with bindings beyond Python.

This Docling alternative page compares licence, benchmark scores and community. We read competitor facts between 2 and 16 November 2026.

Competitor facts read between 2 and 16 November 2026.

At a glance

PDFluent and Docling, row by row.

The benchmark's README lists docling at 0.882 overall against 0.9282 for PDFluent 1.4.0 quality auto. PDFluent is ahead on all 4 scores: overall, reading order, table structure and heading hierarchy. This is one benchmark and one run. The competitor figures come from its README.*

PDFluent and Docling compared, competitor facts read between 2 and 16 November 2026
DimensionPDFluentDocling
LicenceAGPL-3.0, or a commercial licenceMIT (Docling 2.150.0)
LanguagesRust, Python, Node.js, WebAssembly, Java and .NET, plus a command-line toolA Python package on PyPI
opendataloader-bench, overallPDFluent ahead0.9282 (PDFluent 1.4.0, quality auto)0.882
Reading orderPDFluent ahead0.94630.898
Table structure (TEDS)PDFluent ahead0.91400.887
Heading hierarchyPDFluent ahead0.87670.824
Docling-shaped outputextract_docling returns Docling JSON. Structured extraction ships as a Preview.Its own document format
Age and community (3 November 2026)Other tool aheadpdfluent-sdk: 40 GitHub stars, first PyPI release 2026-05-14docling: 70,054 GitHub stars, first PyPI release 2024-07-15, created at IBM Research

* Overall score 0.9282 (SDK 1.4.0, quality="auto", keep_furniture=True, layout, table and formula models installed) on all 200 documents, with the benchmark’s own harness and evaluator, measured 11 November 2026 on the final macOS arm64 release wheel. Competitor figures are taken from the benchmark’s public README as read on 3 November 2026 (highest overall there: 0.907, opendataloader [hybrid]), not re-run by us. The leaderboard engines ran on their own setups while PDFluent was measured on macOS arm64, and table structure depends on the platform. PDFluent is not on that leaderboard. Other engines have submissions open that are not yet on the leaderboard. One run, no confidence interval. The PDFluent row keeps page headers and footers because the benchmark’s ground truth counts them as content. PyMuPDF and MuPDF are trademarks of Artifex Software, Inc. PDFluent is an independent product of Innovation Trigger B.V. and is not affiliated with or endorsed by Artifex.

* GitHub stars and first PyPI release read on 3 November 2026. Stars measure attention, not quality, and a first release is not a founding date. IBM Research created Docling and donated it to the LF AI & Data Foundation on 29 April 2025.

Measured

Every engine, one scale.

opendataloader-bench, overall score0 to 1, one scale
  1. PDFluent 1.4.00.9282
  2. opendataloader [hybrid]0.907
  3. nutrient0.885
  4. docling0.882
  5. marker0.861
  6. unstructured [hi_res]0.841
  7. edgeparse0.837
  8. opendataloader0.831
  9. mineru0.831
  10. pymupdf4llm0.732
  11. unstructured0.686
  12. markitdown0.589
  13. liteparse0.576

PDFluent 1.4.0 with quality auto, page headers and footers kept. Other engines as published in the benchmark README on 2 November 2026. Footnote

The chart shows the 12 engines on the public opendataloader-bench leaderboard next to PDFluent 1.4.0 at quality auto. On the four scores of that benchmark PDFluent is ahead of Docling on 4 of 4. The table under the chart gives every engine on every score.

PDFluent and the 12 leaderboard engines on all four scores
EngineOverallReading orderTable structureHeadings
PDFluent 1.4.00.92820.94630.91400.8767
opendataloader [hybrid]0.9070.9340.9280.821
nutrient0.8850.9250.7080.819
docling0.8820.8980.8870.824
marker0.8610.8900.8080.796
unstructured [hi_res]0.8410.9040.5880.749
edgeparse0.8370.8940.7170.706
opendataloader0.8310.9020.4890.739
mineru0.8310.8570.8730.743
pymupdf4llm0.7320.8850.4010.412
unstructured0.6860.8820.0000.388
markitdown0.5890.8440.2730.000
liteparse0.5760.8660.0000.000
Migrate

Their call, next to ours.

Doclingdocling.py
1from docling.document_converter import DocumentConverter
2
3converter = DocumentConverter()
4result = converter.convert("report.pdf")
5print(result.document.export_to_markdown())
PDFluentpdfluent.py
1from pdfluent import Document
2
3# pip install pdfluent
4with Document("report.pdf") as doc:
5 markdown = doc.extract_markdown()
6 docling_json = doc.extract_docling()

extract_docling takes first_page, page_count and name, and returns Docling JSON. quality="balanced" adds tables once the models are installed. The Docling code is the example from its own documentation, read on 16 November 2026.

Price

What each costs, as of 16 November 2026.

Neither tool charges per page. Docling is MIT licensed. PDFluent is free under the AGPL-3.0, or a commercial licence costs EUR 999 per organisation per year excluding VAT as of 7 September 2026. The cost is the licence choice and your own compute.

List prices as of 16 November 2026
ProductPlanPrice
PDFluent SDKFree under the AGPL-3.0, or a commercial licenceEUR 0, or EUR 999 per organisation per year, excluding VAT (as of 7 September 2026)No per-page fee. You run it on your own hardware.
PDFluent hosted APIComing soon, not live yetPlanned: prepaid packs from USD 25 for 25,000 credits. 1 credit per page at fast, 3 at autoUSD 1.00 and USD 3.00 per 1,000 pages at the USD 25 pack. Planned terms as of 16 November 2026.
DoclingMIT licenceNo price list: a Python package you run yourselfYour cost is your own compute, as with the PDFluent SDK.

* List prices read on 16 November 2026 from each vendor’s own pricing page, and the arithmetic on them. The services name their tiers and strategies differently and have not been measured against each other, so a lower price is not a like for like saving. The PDFluent hosted API is coming soon and is not live; its prices are planned terms, checked again at launch. The SDK runs on your own hardware, which has its own cost. The SDK price is as of 7 September 2026.

SDK licence · Hosted API pricing, coming soon

Which one

Who each one suits.

Pick PDFluent when

PDFluent suits teams that work outside Python, with bindings for Rust, Node.js, WebAssembly, Java and .NET. The SDK runs inside your own process on your own machine. There is no cloud service, no licence server and no activation, and its default build has no HTTP client. Structured extraction returns Docling JSON, so Docling-shaped output stays available.

Pick Docling when

Docling is the better fit when you want an MIT-licensed tool from IBM Research. IBM Research created Docling and donated it to the Linux Foundation AI & Data Foundation on 29 April 2025. Docling also has the larger community: 70,054 GitHub stars on 3 November 2026, against 40 for pdfluent-sdk. Stars measure attention rather than quality.

Questions

Three questions.

Which licence do I need?+
Docling 2.150.0 is MIT licensed. PDFluent is free under the AGPL-3.0, or you can take a commercial licence if you do not want to publish your own source.
Can I keep Docling-shaped output?+
Yes, you can keep Docling-shaped output. Structured extraction ships as a Preview.
How hard is it to switch from Docling?+
You call one method, extract_docling, instead of the Docling converter. PDFluent ships bindings for Rust, Python, Node.js, WebAssembly, Java and .NET, plus a command-line tool.

Try it on a
document you know.

Install it, open one file you can judge, and read what comes back.

Other comparisons: LlamaParse alternative · Unstructured alternative