Reconstructs the 2011–2015 financial summary table with rows and columns intact, but misses a small number of currency symbols in the extracted values.
What was measured
Table Preservation
Preserves complex table structures, including rows, columns, multi-row headers, and merged-cell relationships in markdown.
decisive for this rankingtransformation
Accurate Markdown conversion of complex PDFs depends on keeping table structure intact, not flattening it into plain text. (3 of 3 judges)
What was given, what came back
Test input: Hybrid Earnings Report · pdf · group: hybrid-earnings-report
Input — what we sent
Hybrid Earnings Report
A long, real-world hybrid annual report used to benchmark end-to-end PDF-to-markdown conversion. It combines native text, financial tables, charts/graphics, and scanned signature/stamp regions, stressing preservation of document structure, reading order, and embedded visual content across a multi-section report.
Why this input is hard
- · Native digital text extraction
- · Complex financial table preservation
- · Chart and graphic retention
- · Image-based signatures and stamps
- · Reading order across a long multi-section report
- · Markdown quality and consistency
Output — unretouched
Also checked on this input — same tool, 4 other criteria
Advanced Features✓ WorkedSeparately extracts chart content into textual summaries and value tables, including a waterfall chart and bar charts with year/value pairs and growth statistics.Complex Document Handling◐ MixedHandles an 84-page hybrid report end to end, but quality degrades on signatures and multicolumn pages rather than staying uniform across the document.Reading Order & Structure✗ FailedBreaks the two-column reading order on the annual-report page, so headings and body text no longer follow the source navigation cleanly.Visual Content Retention✗ FailedDoes not retain handwritten signature content as visual output on the signatures page, leaving only partial surrounding legal text and no clearly identifiable signatures.
Provenance
- Observation
- eadd62f1-5229-47c5-9d69-024cbf87e51b
- 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: "upstage-ai",
scenario: "hybrid-earnings-report"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 8 other tools
measured on Table Preservation
Adobe API◐ MixedRetains the 2-column 'Other Noncurrent Assets' table but formats the currency symbols awkwardly around the values, showing a presentation-level mismatch even though the row data remains present.Extend AI✓ WorkedPreserves a 5-year financial summary table with row labels and year columns aligned, keeping the annual financial grid intact in markdown.Landing AI✓ WorkedReconstructs a five-year financial results table with the 2015–2011 columns and aligned row/value relationships intact in markdown-style rows.LlamaParse✓ WorkedPreserves aligned rows, columns, and value associations in a standard multi-year financial summary table.Mistral AI✓ WorkedThe financial table is reconstructed into a usable structured layout without losing the relationships between headers, rows, and corresponding values.Nutrient.io✗ FailedBreaks a 5-year financial summary table, misaligning rows, columns, and values instead of reconstructing the original structure cleanly.Reducto✓ WorkedPreserves a genuinely row-paired 52-row state table as a clean grid, keeping the 1,792 stores total and 239,539 retail-square-footage total intact.Tensorlake✓ WorkedKeeps a 5-year financial summary table structured, retaining the row/column relationships across sales, expenses, EBIT, and per-share rows instead of flattening the table.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com