Evidence · first-party tested · observation #49
Scanned multi-column papers require the parser to recover both hierarchy and reading flow.
An image-only scanned research paper created from an OCR-bearing original by converting pages to images and rebuilding the PDF without searchable text. It contains text, multi-column layouts, figures, charts, tables, captions, and references, and is designed to stress OCR and reconstruction quality.
Multi-level segment comparison table with year-over-year changes.
Parsed rendering of the segment comparison table.
The observation
Scanned multi-column papers require the parser to recover both hierarchy and reading flow.
Criterion: text-between-columns handling · Scenario: Scanned multi-column research paper (group: scanned-research-paper)
Query this
get_evidence({
tool: "llamaparse",
scenario: "scanned-research-paper"
})MCP · admin.futuresmart.ai/api/mcp
Free with attribution.
Free with attribution.
Same input, other tools
LlamaParse ✗ FailedLlamaParse ✓ WorkedLlamaParse ✓ WorkedLlamaParse ✓ WorkedLlamaParse ✓ WorkedLlamaParse ✓ WorkedLlamaParse ✓ WorkedAudio Studio ✗ FailedAudio Studio ◐ MixedAudio Studio ✓ WorkedAudio Studio ✓ WorkedAudio Studio ✓ WorkedAudio Studio ✓ WorkedAudio Studio ✓ WorkedAudio Studio ✓ Worked
Real outputs, no retouching · every cell queryable via API & MCP · aidemos.com