# PDFluent vs Docling

Source: https://pdfluent.com/comparison/vs-docling/

Docling is an MIT-licensed document-conversion toolkit that started at IBM Research. PDFluent is a general-purpose PDF SDK with a preview structured-extraction layer for the same kind of pipeline.

IBM Research created Docling and donated it to the LF AI & Data Foundation on 29 April 2025. It is MIT licensed. PDFluent is a general-purpose PDF SDK (parsing, rendering, forms, signatures, PDF/A, redaction) that also ships a preview structured-extraction layer aimed at the same RAG and LLM use case. For Docling's own scope and supported formats, check its documentation.

[Install the SDK](https://pdfluent.com/docs/)

## Side-by-side

PDFluent

Rust

```
use pdfluent::{ExtractOptions, PdfDocument};

fn main() -> pdfluent::Result<()> {
    let doc = PdfDocument::open("report.pdf")?;
    // Structured extraction (Preview)
    let markdown = doc.extract_markdown(&ExtractOptions::default())?;
    println!("{}", markdown);
    Ok(())
}
```

Docling

Python

```
from docling.document_converter import DocumentConverter

source = "report.pdf"
converter = DocumentConverter()
result = converter.convert(source)
print(result.document.export_to_markdown())
```

## Feature comparison

| Feature | PDFluent | Docling |
| --- | --- | --- |
| License model | AGPL v3 or commercial | MIT |
| Core engine language | Rust | Python package on PyPI |
| Official Rust bindings | Yes | Not assessed here |
| Official Node.js bindings | Yes | Not assessed here |
| Official.NET bindings | Yes | Not assessed here |
| Official Java bindings | Yes | Not assessed here |
| WebAssembly (runs in the browser) | Yes | Not assessed here |
| PDF creation & editing | Editing, for example image placement and replacement, redaction and form filling | Not assessed here |
| Merge / split PDFs | Yes, in the PDFluent editor | Not assessed here |
| Digital signatures | PAdES B-B, B-T and B-LT | Not assessed here |
| AcroForms / XFA forms | Fills XFA forms (read fields, set values, save) and flattens them to a regular PDF; AcroForm calculate and format actions run | Not assessed here |
| PDF/A validation & conversion | Validation for PDF/A-1, A-2 and A-3; conversion is a Preview feature | Not assessed here |
| Redaction | Yes: removes the redacted content from the file instead of covering it | Not assessed here |
| Markdown / LLM-ready text extraction | Preview: extract_markdown() / extract_blocks() (1.1.0) | Measured in the same run, on the same pages [A62, 2026-10-17] |
| Table structure recognition | Table model on the balanced tier (Preview, opt-in) | Included in the 19 measures below, same run [A62, 2026-10-17] |
| Extraction quality, 19 measures | Balanced tier with the table model (Preview): average 0.721 against 0.672 for Docling 2.126.0 over 19 measures* [A62, 2026-10-17]. *Balanced tier with the table model (Preview), on our own held-out half of four public datasets, 17 October 2026. The table model was trained on the source datasets of two of them (PubTables-1M, FinTabNet), and most of those held-out pages are in their training split. On the 13 measures without that overlap the ranking is the same (0.650, 0.642, 0.610). Details on the benchmarks page. | Measured in the same run, on the same pages [A62, 2026-10-17] |
| Speed and memory, one c3-standard-8 (8 vCPU) | Fast tier: 19 ms per page and 43 MB peak memory on all 8 cores. Balanced tier with the table model: 885 ms per page on all cores, slower than Docling on one thread [C22, 2026-10-17] | 1,526 ms per page and 1,629 MB peak memory on all cores; 4,187 ms per page on one thread [C22, 2026-10-17] |
| Non-PDF input formats (DOCX, PPTX, XLSX, HTML) | DOCX, PPTX, XLSX and HTML to Markdown (Preview) [A31-A34, 2026-10-04] | Read DOCX, PPTX, XLSX and HTML in our Office comparison [A31-A34, 2026-10-04]; check Docling's documentation for the full list of inputs |
| Vision-language-model pipeline option | No vision-language-model option in the extraction tiers described here | Not assessed here; check Docling's documentation |
| Local, offline execution | Yes: runs on your machine; optional features and model installs use the network | Not assessed here |
| Published, self-service pricing | Yes, prices published (as of 7 September 2026) | MIT licence; check Docling's documentation for any paid offering |

## Pros and cons

### PDFluent

- Yes A general-purpose PDF SDK, not just an extraction tool: one engine for editing, signing, forms, PDF/A validation, redaction and extraction
- Yes Balanced tier with the table model (Preview): average 0.721 against 0.672 for Docling 2.126.0 across 19 extraction measures* [A62, 2026-10-17]. *Balanced tier with the table model (Preview), on our own held-out half of four public datasets, 17 October 2026. The table model was trained on the source datasets of two of them (PubTables-1M, FinTabNet), and most of those held-out pages are in their training split. On the 13 measures without that overlap the ranking is the same (0.650, 0.642, 0.610). Details on the benchmarks page.
- Yes Fast tier: less time per page and less memory than Docling 2.126.0 on the same 8-vCPU machine [C22, 2026-10-17]
- Yes Six official language bindings including Rust, Node.js,.NET, Java, and WebAssembly
- Yes AGPL-3.0 for free use, with a commercial licence as the alternative if you do not want to publish your own source
- No image or audio input. DOCX, PPTX, XLSX and HTML input is Preview.
- No vision-language-model option in the extraction tiers described here
- No GPU route; on one thread the balanced tier is slower than Docling [C22, 2026-10-17]

### Docling

- Yes Read DOCX, PPTX, XLSX and HTML in our Office comparison [A31-A34, 2026-10-04]; check its documentation for further formats
- Yes MIT licensed
- Yes Widely used: 70,054 GitHub stars when read on 3 November 2026, against 40 for the PDFluent SDK repository; stars measure attention, not quality
- Distributed as a Python package on PyPI; we have not assessed other language bindings
- More time per page and more memory than PDFluent's fast tier on the same machine [C22, 2026-10-17]

## When to use each

### Choose PDFluent

Choose PDFluent if you need a single engine that both works on PDFs (edit, sign, fill forms, redact, validate PDF/A) and extracts structured, LLM-ready text from them, with bindings beyond Python, and the fast tier's speed and memory on the axes we've measured.

### Choose Docling

Choose Docling if you want an MIT-licensed tool, if you need input formats or a vision-language-model pipeline that PDFluent does not provide (check Docling's documentation for both), or if you run on a GPU, which PDFluent has no route for.

Values move with their headings.

## Bottom line

Docling and PDFluent overlap on one axis: turning a PDF into clean text for an AI pipeline. On that axis we measured both tools, plus pymupdf4llm 1.28.2, in one run on the same pages. PDFluent's balanced tier with the table model averaged 0.721 across 19 measures, against 0.672 for Docling 2.126.0 and 0.693 for pymupdf4llm 1.28.2* [A62, 2026-10-17]. *Balanced tier with the table model (Preview), on our own held-out half of four public datasets, 17 October 2026. The table model was trained on the source datasets of two of them (PubTables-1M, FinTabNet), and most of those held-out pages are in their training split. On the 13 measures without that overlap the ranking is the same (0.650, 0.642, 0.610). Details on the benchmarks page. Speed is a separate question with a tier attached. On one 8-vCPU c3-standard-8, PDFluent's fast tier took 19 ms per page against Docling's 1,526 ms on all cores [C22, 2026-10-17]. PDFluent also edits, signs and redacts PDFs and fills forms; for what Docling covers beyond extraction, read its documentation.

## Frequently asked questions

Is PDFluent faster than Docling?

It depends on the tier. On one GCP c3-standard-8 (8 vCPU, no GPU), on all cores, PDFluent's fast tier took 19 ms per page and peaked at 43 MB of memory; Docling 2.126.0 took 1,526 ms per page and peaked at 1,629 MB [C22, 2026-10-17]. The balanced tier with the table model runs two models: 885 ms per page on all cores, less than Docling, but on one thread it is slower than Docling: 7,053 against 4,187 ms per page [C22, 2026-10-17]. On an NVIDIA L4 GPU, Docling takes 592 ms per page; PDFluent has no GPU route [C22, 2026-10-17]. Quality is a separate measurement on the held-out half, covered on the benchmarks page.

Can Docling create or edit PDFs?

We did not assess that; check Docling's documentation for its scope. We measured Docling as a document-to-Markdown extractor. PDFluent edits PDFs, signs them (PAdES B-B, B-T and B-LT), redacts them and fills forms natively.

Does Docling support formats PDFluent doesn't?

Check Docling's documentation for its full list of inputs. In our Office comparison Docling 2.132.0 read DOCX, PPTX, XLSX and HTML. PDFluent's Preview extraction reads PDF plus DOCX, PPTX, XLSX and HTML, measured as at least as good as Docling on specific measures only [A31-A34, 2026-10-04]. PDFluent does not accept standalone image or audio files as input.

Why would I use PDFluent's extraction instead of Docling?

If you already need a general PDF SDK for editing, signing, redacting or validating PDFs, and want structured extraction from the same engine instead of adding a second dependency, PDFluent gives you both.

SDK · Install

## Try it on your own files.

Free under the AGPLv3, or a commercial licence if you would rather not publish your own source.

[Install the SDK](https://pdfluent.com/docs/)[SDK pricing](https://pdfluent.com/sdk/pricing/)
