Evidence · first-party tested

Extracts the table of contents as sequential text: entries and page numbers survive, but the TOC relationships are not reconstructed as a structured table.

✗ Failed🧾 artifact-verifiedTested Jun 20, 2026Llamaparse →
Output — unretouched
Extracted table of contents from a quarterly financial report.
Extracted table of contents from a quarterly financial report.
The observation

Extracts the table of contents as sequential text: entries and page numbers survive, but the TOC relationships are not reconstructed as a structured table.

Criterion: Table Preservation · Scenario: Sumitomo Heavy Industries Consolidated Financial Report (group: financial-report)
Query this
get_evidence({
  tool: "llamaparse",
  scenario: "financial-report"
})
MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, other tools
Adobe PDF Extract API ✓ WorkedExtend AI ⚠ StruggledLanding AI ✓ WorkedMistral AI ✗ FailedNutrient.io ✗ FailedPDF Vector ⚠ StruggledTensorlake ✗ FailedUpstage AI ◐ Mixed
Real outputs, no retouching · every cell queryable via API & MCP · aidemos.com