Charts are exposed through both page-wise markdown files and the extracted visual assets, keeping the visual content linked to its original document location.
What was measured
Visual Content Retention
Retains charts, figures, diagrams, and images in the output and places them in the correct reading position.
decisive for this rankingtransformation
For complex PDFs, figures, charts, and images are part of the document content, so preserving them in the right place is part of the core job. (3 of 3 judges)
What was given, what came back
Test input: Scanned Research Paper · pdf · group: scanned-research-paper
Input — what we sent
45e3533a31c246b29e0ec6aaa98438e4.pdf
Scanned Research Paper
An image-only scanned research paper used to stress OCR and layout recovery in a multi-column academic document with figures, charts, tables, captions, and references.
Why this input is hard
- · OCR on scanned pages
- · Multi-column reading order
- · Figure and chart handling
- · Table reconstruction from scans
- · Caption association
- · Reference extraction
- · Overall document structure retention
Output — unretouched
Also checked on this input — same tool, 7 other criteria
Complex Document Handling✓ WorkedThe tool processes a scanned multi-column research paper end-to-end and returns OCR text, tables, and embedded chart assets in page-wise markdown output.Markdown Quality✓ WorkedThe export is packaged as usable markdown files in a ZIP, with both overall and page-wise outputs available for inspection.Reading Order & Structure✗ FailedThe opening page loses the distinction between the document title and the abstract, flattening the semantic organization of the first page.Reading Order & Structure✓ WorkedSection hierarchy and reading flow are preserved in the scanned paper, keeping headings and supporting paragraphs correctly connected despite the multi-column layout.Table Preservation✗ FailedBroken column boundaries and disrupted value alignment make the reconstructed table significantly less faithful to the source.Table Preservation✓ WorkedThe multicolumn table is reconstructed without losing its overall layout logic, so the table structure remains readable in the parsed output.Text & OCR Completeness◐ MixedThe report says the parser recovers much of the underlying text from the scanned paper, but it does not present a measured completeness rate and the first-page hierarchy is still lossy.
Provenance
- Observation
- 0f3a42b1-0d18-4374-bbeb-cd6776d7b79e
- Evidence run
- 6e3160de-fe46-4b45-b071-72560b5c5d0e
- Study
- Convert a Complex PDF into Clean Markdown with an API
- Research task
- 86b9h7t37
- Tested at
- not recorded
- Source
- first-party
- Evidence state
- verified
- Proof shown
- input + output shown
- Cost / latency
- not captured
- Repeat run
- not captured
- Tester
- not captured
The last three rows are honest blanks, not placeholders — our capture has no field for them yet.
Query this
get_evidence({
tool: "mistral-ai",
scenario: "scanned-research-paper"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 6 other tools
measured on Visual Content Retention
Adobe API✓ WorkedKeeps chart artwork embedded in the extracted page, placing the residual basal-area figure in situ beneath the extracted table text.Extend AI◐ MixedExtracts chart values into a captioned figure block, but the report says the mortality chart's trend visualization is not fully retained.Landing AI✗ FailedConverts a scanned bar chart into a textual transcription of legend items and approximate values instead of retaining the chart visually in the output.LlamaParse◐ MixedConverts a bar chart into a structured table, preserving the legend/value mapping but not keeping the chart as a visual chart.Nutrient.io⚠ StruggledExtracts the Figure 3 chart's values, but the chart structure and layout are not preserved, so the visualization is flattened into text-like output.Reducto✓ WorkedSegments a shield logo out of a single full-page raster scan and also retains Figure 1 as an image with an accurate synthesized caption; the returned logo crop is a tight 77x81px cut with legible shield text.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com