Keeps the syntax clean: no <signature>, <empty>, <b>, <i>, or <u> tags appear anywhere in the output, and the table-of-contents extract renders as a valid pipe table.
What was measured
Markdown Quality
Produces clean, well-structured, usable markdown rather than a flat text dump.
decisive for this rankingtransformation
The ranking is specifically about producing clean Markdown, so the quality and usability of the Markdown output directly measures success. (3 of 3 judges)
What was given, what came back
Test input: Financial Report - Table Heavy · pdf · group: financial-report-table-heavy
Input — what we sent
Financial Report - Table Heavy
A table-heavy corporate financial report used to test extraction of dense, hierarchical financial statements with grouped columns, multi-row headers, segment-reporting tables, and narrative disclosures.
Why this input is hard
- · Multi-page financial statement extraction
- · Hierarchical table reconstruction
- · Grouped columns and multi-row headers
- · Reading order in a report with mixed narrative and tables
- · Document structure retention
- · Markdown usability
Output — unretouched
Also checked on this input — same tool, 8 other criteria
Advanced Features✗ FailedThe confidence field is nearly useless here: the only low-confidence flag is a false alarm on the correct page-18 section header, while the genuinely broken Business Results table stays high-confidence throughout.Advanced Features✓ WorkedSchema-driven extract.run fully recovers the broken Business Results table, separating the 2024 value and percent-change fields that parse.run had merged together.Complex Document Handling◐ MixedProcesses the 18-page report in 9.7 seconds with no truncation; the 9-column segment table at page 17 is flawless even though the first table on page 2 is broken.Reading Order & Structure✗ FailedProvides zero markdown heading markup across all 18 pages; the Roman-numeral sections and numbered subsections are flattened into plain text despite the source’s visible section hierarchy.Table Preservation✓ WorkedPreserves the balance-sheet hierarchy and values, including Assets > Current assets > Cash and deposits, and also reconstructs the later 9-column segment table with all values correct.Table Preservation✗ FailedBreaks a 5-column business-results table by duplicating the 2025 header and merging the 2024 value and percent change into one cell; the Net sales row ends up with 254,811 and 2.6 smashed together.Text & OCR Completeness✓ WorkedConverts all 18 pages with no omitted text; a dense financial-condition paragraph preserves multiple JPY-billion values exactly, including JPY1,252.7 billion, JPY623.6 billion, JPY27.2 billion, JPY10.8 billion, JPY5.0 billion, and JPY9.7 billion.Visual Content Retention✓ WorkedRetains the recurring page-header logo consistently across all 17 pages that carry it; the returned crops on pages 2 and 18 are the same mark and wordmark, with only a 1px width difference (453x36 vs 452x36) consistent with rounding.
Provenance
- Observation
- aa04c457-96be-40c1-87a5-5813f3f86c31
- 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: "reducto",
scenario: "financial-report-table-heavy"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 4 other tools
measured on Markdown Quality
LlamaParse◐ MixedRenders the table of contents as sequential text with page numbers instead of a nested TOC structure, so the markdown is usable but flattened.Mistral AI✓ WorkedThe output is organized as a downloadable ZIP containing a consolidated markdown document plus individual page-level files for localized inspection.PDF.ai✗ FailedMarkdown export failed on an 18-page table-heavy financial report; the report records "Output MD: Output failed."Tensorlake✓ WorkedReturns the extraction as structured markdown in the Document Markdown workflow, making the output usable rather than a raw text dump.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com