Tool in benchmark · Version 1

Mistral AI in Converting a complex PDF into clean Markdown with a hosted API

Scenario-level performance from current published Results.

9 scenarios with published Results · 12 scenarios in the benchmark

How Mistral AI performed

Open a capability to explore its scenarios. Each row reports the test set in its published Result; counts are not combined into an overall score.

Equations & Mathematical Notation1 scenario · 1 with published Results

Scenario	Published outcomes	Test coverage	Result
A document containing mathematical equationsRound 1 · Graded 5 Oct 2026 · Published 8 Oct 2026	1 Pass0 Fail0 Not gradable 1 of 1 test case passed What happened Mistral AI kept the mathematical equations as LaTeX math in the Markdown for this PDF. The returned Markdown preserved all six display equations as math blocks with tags, kept inline symbols inside math delimiters, and carried through the page-break text and running heads. The page-by-page comparison sheets matched the source pages shown there.	1/1 assessed1/1 gradablePublished test set	View Result →

Figures & Charts2 scenarios · 1 with published Results

Scenario	Published outcomes	Test coverage	Result
A document with figures and captionsRound 1 · Graded 28 Sept 2026 · Published 6 Oct 2026	1 Pass0 Fail0 Not gradable 1 of 1 test case passed What happened Mistral AI preserved the figure at its source-page position and kept the caption directly below it. The Markdown places `![img-0.jpeg](assets/img-0.jpeg)` between the two surrounding paragraphs, with the Figure 1 caption immediately beneath it.	1/1 assessed1/1 gradablePublished test set	View Result →
A document with a data chart	No published result

Heading & Section Structure2 scenarios · 1 with published Results

Scenario	Published outcomes	Test coverage	Result
Footnotes at the bottom of the pageRound 1 · Graded 28 Sept 2026 · Published 6 Oct 2026	1 Pass0 Fail0 Not gradable 1 of 1 test case passed What happened Mistral AI keeps footnotes out of the body flow and links each marker to its note. The Markdown output places 13 footnotes after the page bodies in source order, and the 26 marker occurrences each appear once inline and once at their notes, so the association is preserved.	1/1 assessed1/1 gradablePublished test set	View Result →
A document with styled headings and subheadings	No published result

Reading Order & Layout1 scenario · 1 with published Results

Scenario	Published outcomes	Test coverage	Result
A page laid out in multiple columnsRound 1 · Graded 28 Sept 2026 · Published 6 Oct 2026	1 Pass0 Fail0 Not gradable 1 of 1 test case passed What happened Mistral AI read the two-column page down each column in turn rather than across the page. On the three pages, the left and right columns stayed in order without interleaving.	1/1 assessed1/1 gradablePublished test set	View Result →

Scanned Document OCR2 scenarios · 2 with published Results

Scenario	Published outcomes	Test coverage	Result
A cleanly scanned documentRound 1 · Graded 5 Oct 2026 · Published 6 Oct 2026	1 Pass0 Fail0 Not gradable 1 of 1 test case passed What happened Mistral AI passed the clean-scan OCR check. The image-only PDF had no text layer, and the returned Markdown reproduced the page’s text, numbers, dates, and closing lines. The signature was left as an image reference. One table header is shifted into the header row, but no content is lost.	1/1 assessed1/1 gradablePublished test set	View Result →
A document mixing digital and scanned pagesRound 1 · Graded 5 Oct 2026 · Published 6 Oct 2026	1 Pass0 Fail0 Not gradable 1 of 1 test case passed What happened Mistral AI processed the mixed PDF and included the scanned page in the Markdown output instead of skipping it. The scanned page appears in document order as tables and prose: the worksheet header, checks and readings, calibration note, time on site, and received by details are all present. The signature stays as an image reference.	1/1 assessed1/1 gradablePublished test set	View Result →

Table Extraction2 scenarios · 2 with published Results

Scenario	Published outcomes	Test coverage	Result
A simple, clearly formatted tableRound 1 · Graded 28 Sept 2026 · Published 6 Oct 2026	1 Pass0 Fail0 Not gradable 1 of 1 test case passed What happened Mistral AI preserved a simple, clearly formatted table: the returned Markdown kept the four headers in order, retained eight data rows, and matched all 32 data cells against the source. The table stayed a single pipe table, and the comma inside "Metals suite, eleven elements" did not split the cell.	1/1 assessed1/1 gradablePublished test set	View Result →
A table that continues across a page break	Different test setPublished Result available, but not included in this comparison.		View Result →

Text Fidelity1 scenario · 1 with published Results

Scenario	Published outcomes	Test coverage	Result
An ordinary digital text documentRound 1 · Graded 28 Sept 2026 · Published 6 Oct 2026	0 Pass1 Fail0 Not gradable 1 of 1 test case failed What happened Mistral AI did not keep an ordinary digital text document complete and unchanged. In the graded output for briefing_note.pdf, running headers and page numbers were spliced into body text at the cited line ranges, including 33-38, 56-64, 110-118, and 138-146.	1/1 assessed1/1 gradablePublished test set	View Result →

Code Extraction1 scenario · 0 with published Results

Scenario	Published outcomes	Test coverage	Result
A document containing a code block	No published result

Published evidence and test coverage answer different questions.

Publication availability

A published Result is public evidence for this tool on one scenario. “No published result” does not say whether testing has taken place.

Test coverage

Assessed includes Pass, Fail and Not gradable. Gradable includes Pass and Fail. Both use the pinned test count in that published Result.

Scenario scope

The 12 scenarios describe this benchmark’s scope. They are not an assumed applicability or test-coverage denominator for Mistral AI.