Document hierarchy and reading flow are preserved across the financial report, with headings staying connected to their explanatory text in the reconstructed output.
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✓ WorkedThe tool processes an 18-page table-heavy financial report end-to-end and returns both page-level and consolidated markdown outputs.Markdown Quality✓ WorkedThe output is organized as a downloadable ZIP containing a consolidated markdown document plus individual page-level files for localized inspection.Table Preservation✓ WorkedThe multilevel segment table is preserved with its hierarchical headers intact, maintaining the relationships between the grouped columns and their values.Table Preservation✗ FailedDistinct header levels are collapsed into a single cell in the multilevel table, weakening the parent-child relationships that define the column semantics.
Provenance
- Observation
- 1b28b2b5-cfd9-48db-82e9-11ad35d536f4
- 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: "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✗ FailedFlattens major headings on the report title/abstract page, reducing structural clarity in the opening pages.LlamaParse✓ WorkedPreserves the document title, disclaimer, and section headings in a readable hierarchy for the Sumitomo Heavy Industries financial report.Nutrient.io⚠ StruggledDoes not consistently preserve paragraph boundaries, so narrative flow fragments across sections instead of staying in the source order.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✗ FailedFlattens the Summary of Operating Performance page so the section heading is no longer visually or structurally distinguished from the running text.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com