Comparisons · 7 tools · Same 38 public documents · Open benchmark

Document to Markdown converters, compared

Seven converters, the same 38 public documents, the same 4-CPU machine. On AgentDocBench, anymd scores 96.4 and converts all 38 documents in 11.5 s. Every figure on this page is generated from the raw results in the anymd repository, including the categories where another tool wins. Start with the scoreboard, or open the head-to-head page for the tool you use today.

Install anymd free    See the full benchmark

npx -y @sylphx/anymd setup --client cursor,claude-code,codex

Scoreboard

AgentDocBench checks what an agent needs from a converter: the words verbatim, in reading order, with tables intact, fast, and in as few tokens as possible.

Tool Overall Converted Table cells F1 Time Output tokens Head to head
anymd 8.2.0 96.4 38/38 92.2 11.5 s 368,659 –
Docling 2.130.0 93.0 38/38 89.9 2,432.4 s 430,148 anymd vs Docling
Kreuzberg 4.10.4 81.7 38/38 38.4 16.0 s 455,689 anymd vs Kreuzberg
Unstructured 0.27.8 81.2 38/38 38.4 346.5 s 414,333 anymd vs Unstructured
MarkItDown 0.1.8 76.8 38/38 57.2 75.6 s 538,388 anymd vs MarkItDown
Marker 2.0.0 71.0 30/38 60.9 7,104.5 s 277,779 anymd vs Marker
pdftotext 24.02.0 42.2 23/38 0.0 0.90 s 201,448 anymd vs pdftotext

Scores are 0 to 100; higher is better. Overall is the mean of the 12 category scores, and a document a tool did not convert scores 0. Time and tokens cover the documents each tool converted, so the table below compares them on the same 19 documents.

Speed and tokens on the 19 documents every tool converted

Tool Time Output tokens Measured
anymd 4.58 s 146,660 2026-10-01
Docling 1,723.3 s 162,290 2026-09-25
Kreuzberg 7.94 s 139,422 2026-09-25
Unstructured 187.4 s 145,360 2026-09-25
MarkItDown 45.4 s 194,382 2026-09-25
Marker 5,256.3 s 181,132 2026-09-25
pdftotext 0.66 s 147,183 2026-09-25

Every tool ran on GitHub-hosted runners (Linux x86_64, 4 CPUs), timed as a fresh process per file.

Which converter fits

Markdownify MCP is an MCP server built on MarkItDown, not the standalone converter measured above. Compare the install steps, supported formats, and web tools before switching.

Docling is the closest to anymd on accuracy. Pick it for an in-process Python library with LangChain or LlamaIndex integrations, a lossless JSON document model, or vision-language models on a GPU. It scored higher on designed reports, scans and EPUB; on a CPU it was the slowest of the tools that converted every document.

Kreuzberg has a Rust core with bindings for Python, TypeScript, Go, Java and more, reads 91+ formats including email and archives, and adds chunking and embeddings. It scored highest on HTML and tied anymd on spreadsheets; tables are its weak spot.

Unstructured splits files into typed elements, with chunking and connectors for batch RAG ingestion in Python. Its text is close to anymd's; its tables are not.

MarkItDown is Microsoft's lightweight Python converter, good on Office files, spreadsheets, HTML and designed reports. With its default options it returns no text for scanned PDFs.

Marker uses vision-model OCR and an optional LLM, and is at its best on a GPU. Its OCR beat anymd on two of the three scans; on a 4-CPU runner it timed out on six documents.

pdftotext is Poppler's plain-text extractor: the quickest way to pull a born-digital PDF's text layer, often already installed. It reads PDFs only, with no OCR and no tables.

anymd is for agents that read PDFs, Office files, EPUB, HTML, scans and media through one MCP server on any CPU, with page anchors to cite and tables kept as Markdown. It is free and MIT licensed.

Cloud APIs and other libraries

Three popular tools are not in the local AgentDocBench run above—two are metered cloud APIs requiring API keys and uploads, and one is an AGPL-3.0 Python library not yet submitted to bench/—so we compare architecture, privacy, licensing and pricing head to head:

  • anymd vs LlamaParse: local MIT Rust binary with no API key or file uploads vs LlamaCloud's metered credit-per-page parsing API.
  • anymd vs Mistral OCR: instant native PDF and Office parsing offline vs Mistral AI's cloud vision OCR API billed per 1,000 pages.
  • anymd vs PyMuPDF4LLM: permissive MIT Rust CLI and MCP server across PDF, Office and media vs Artifex's AGPL-3.0 Python PDF library.

How the scores were measured

Every tool ran on GitHub-hosted Linux x86_64 runners with 4 CPUs, through its own CLI or Python API with default options unless its page says otherwise. Time is the wall time of a fresh process per file, start-up and model loading included. The scoring does not know which tool produced an output. GPUs, long-running servers and releases newer than the ones listed were not measured. The corpus, ground truth, scoring and raw results are public in bench/, and anyone can rerun them or submit a tool.

Check what your agent cites with anymd Pro

Converting a file with anymd is free. When an agent quotes a PDF or a video, anymd Pro takes you back to the source:

  • Cite-check compares up to 100 quotes per request with the page and area each one cites, and reports whether it matches, doesn't match, or needs more evidence. It uses the text and its position on the page, not an AI opinion.
  • Video timelines and frames show scenes, chapters and subtitle or transcript timings, and the frame behind a cited moment with its actual decoded timestamp and a SHA-256 hash of the image.

One-time US$29 purchase. No subscription. Sign in, pay securely, then run anymd login with the same account to activate Pro on your machine. After activation, Pro works offline.

See Anymd Pro

FAQ

Which document to Markdown converter is the most accurate? On AgentDocBench, anymd scores 96.4 overall across 38 documents in 12 categories, followed by Docling. The scoreboard lists every tool's score, time and output tokens, and each head-to-head page lists the categories and documents where the other tool scores higher.

Which converter is the fastest? pdftotext, on the PDFs it reads, because it copies the text layer and runs no OCR. Of the tools that converted all 38 documents, anymd is the fastest, at 11.5 seconds on a 4-CPU runner.

Does anymd need Python or a GPU? No. anymd is a native Rust binary that runs on any CPU. The npx install needs Node 18 or newer; Homebrew, Scoop and Docker install the same binary without Node.

Is the benchmark biased toward anymd? It lives in the anymd repository, so you can check it: the scoring does not know which tool produced an output, the corpus and ground truth are public, and the categories where anymd loses are published. Anyone can rerun it or add a tool.

Is anymd free? Yes. anymd is MIT licensed, including the CLI, the MCP server, OCR and transcripts. anymd Pro is an optional one-time purchase, US$29 or the local price in 16 currencies, that adds PDF cite-check and video timelines and frames.

Docling, Kreuzberg, Unstructured, MarkItDown, Marker and Poppler are projects of their respective owners; anymd is not affiliated with or endorsed by any of them. Benchmark figures come from the AgentDocBench results committed in the anymd repository.