← Any document → text: all libraries · Reader board

Kreuzberg vs Unstructured: which one reads more real-world documents?

Kreuzberg 4.10.4 and Unstructured 0.27.36 on the same 477 odd real-world files from Apache Tika test documents (bug reports, fuzzers, broken exporters). Measured, not opinion; re-tested by itself on every new PyPI release. Updated 06 November 2026.

Kreuzberg got text from more files: 374 vs 370 of 477. Kreuzberg broke (error, hang or crash) on 6 files that Unstructured read; Unstructured broke on 2 files that Kreuzberg read.

By file type: files read with text

Files only Kreuzberg reads (18)

Files only Unstructured reads (14)

Don't want to run it yourself? I also run PDF & Document to Markdown as a pay-per-use API on Apify (it uses pdfplumber and pypdfium2 for PDFs, markitdown for Office files). Disclosure: that tool is mine; the rankings above come only from the measurements.

What this does not tell you

This compares not breaking: whether each library gets any text out of each file. It does not rank text quality (reading order, tables, headings), and speed is one GitHub-hosted runner, default settings, no OCR switched on. If you need structure for RAG, also look at the output on your own files.

How this is measured

• Each library runs a short recipe from its own docs (board/targets.py): open the file, get all text. Installed with the extras the docs recommend for reading (pypdf[full]: AES decryption, Brotli), nothing else. One worker process per CPU; per file 60 s / 120 s / 180 s / 300 s / 600 s at most (the any-document table allows longer: some tools load models), killed above the memory limit.
• Fails where another reads: the library raised an error, hung or crashed on a file from which another library in the same table got text. Files that every library fails on (encrypted, truncated, fuzzed) are not counted against anyone.
• Empty where another reads: no error, but no text. This is often the recipe, not the library: for example python-docx's paragraphs+tables recipe skips headers, text boxes and nested tables. Check the file list.
• Any document → text: a file type the tool's docs don't list, or that the tool itself rejects as unsupported, counts as "not supported", not as a failure (lists in board/libs.json). Returning a file's raw RTF source counts as empty, for every tool. Each tool runs with default settings: no OCR switched on by hand.
• OCR: each image comes with the human-written ground-truth text published with its dataset. Words found is the share of its words that appear anywhere in the engine's output (reading order doesn't matter); an image that fails or comes back empty counts as 0. The ground truth of receipts and document pages covers only their annotated text, so a character error rate would punish engines for reading more than was annotated; it is in the raw results but not ranked. English models, CPU, default settings.
• Speech: each clip comes with its dataset's reference transcript. Both texts go through Whisper's English text normalizer (case, punctuation, "twenty" = "20"); word error rate is all substituted, missing and extra words over all reference words, the usual corpus-level WER. A clip that fails or comes back empty counts all its words as errors. The three Whisper implementations use the same base.en model; each other engine its documented default model. English, CPU, default decoding settings.
• Language detection: each text's language is known from Tatoeba. An answer counts as correct if the library's code matches after mapping variants to ISO 639-1 (zh-cn → zh, nb → no, iw → he). Close languages count as different: Croatian detected as Bosnian or Serbian, or Norwegian as Danish, is wrong. One call per text with default settings and all languages enabled.
• PDF → Markdown: pages from AI2's olmOCR-bench (ODC-BY), scored with its own checks (vendored, Apache-2.0): a sentence must be present, a page header or footer absent, two passages in the right order, a table cell next to the right neighbour. Checks passed is all passed checks over all checks; a page that fails or comes back empty passes none. Math pages are left out (their checks need a browser to render formulas). Default settings: whatever OCR a tool does on its own, it does.
• Text quality (order, tables, layout) is not ranked in the other tables; they are about not breaking. The raw results have every output's size and hash.
• Same files for every version: the test collections are pinned to one commit. GitHub-hosted runner, so times are comparable within one table, roughly.