Public KG record
r-1
Recorded overview
A single-pass document parsing model that integrates OCR, layout, table structur
Extract text from images, scans, or PDFs while preserving layout, tables, and document structure.
Recorded details
- Benchmarks: hyperscaler products
- Benchmarks: large LLMs
- Capabilities: text extraction from digital text, scans, handwriting
- Capabilities: table structure recognition including merged cells and nested headers
- Capabilities: layout detection including columns, headers, footers, reading order
- Capabilities: Integrates OCR, layout, tables, formatting, and grounding into a single full page pass
- Capabilities: Detects figures and provides a short generated description
- Deployment: hosted Parse API V3
Evidence coverage
The KG currently records 13 known information dimensions and has 5 undocumented dimensions, linked to 1 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- Reducto — releases
- Azure Document Intelligence — competes with
- Parse API — based on
- Azure Document Intelligence — competes with
- Amazon Textract — competes with