Preserves the document title, disclaimer, and section headings in a readable hierarchy for the Sumitomo Heavy Industries financial report.
What was measured
Reading Order & Structure
Maintains headings, sections, column order, document hierarchy, and overall flow.
decisive for this rankingtransformation
Clean Markdown requires the original reading order, headings, sections, and hierarchy to be maintained correctly. (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
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, 4 other criteria
Complex Document Handling✓ WorkedProcesses an 18-page table-heavy report end-to-end and reaches SUCCESS in the Results view without manual correction.Markdown Quality◐ MixedRenders the table of contents as sequential text with page numbers instead of a nested TOC structure, so the markdown is usable but flattened.Table Preservation✓ WorkedPreserves a multi-level segment-results table with grouped headers and year-over-year columns, keeping the hierarchy legible in the extracted output.Table Preservation◐ MixedKeeps the numeric values in a dense hierarchical table but makes grouped-header semantics less explicit, so parent-child column roles become less clear.
Provenance
- Observation
- 06f3e900-c9d1-4767-bae7-efa3ac0e9779
- 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: "llamaparse",
scenario: "financial-report-table-heavy"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 8 other tools
measured on Reading Order & Structure
Adobe API✗ FailedCollapses a nested table-of-contents page into a flat list, so the indentation-based section hierarchy is no longer represented.Extend AI✓ WorkedKeeps section hierarchy and narrative flow intact in the table-heavy quarterly financial report, preserving headings and explanatory notes instead of collapsing them into one text block.Landing AI✓ WorkedKeeps the operating-performance section hierarchy intact, with the main section heading, subsection heading, and narrative paragraphs remaining in the correct flow.Mistral AI✓ WorkedDocument hierarchy and reading flow are preserved across the financial report, with headings staying connected to their explanatory text in the reconstructed output.Nutrient.io✓ WorkedThe tool preserves a long narrative operating-performance section with headings and paragraph flow in a quarterly financial report page.Reducto✗ 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.Tensorlake✓ WorkedKeeps section ordering and narrative flow in an 18-page table-heavy financial report, preserving the operating-performance section before the tabular disclosures.Upstage AI✓ WorkedPreserves section hierarchy in the Mechatronics/Industrial Machinery prose, keeping subsection headings and their paragraphs in the same structural order as the source.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com