Skip to content

Benchmark Results

ToolNIDTEDSMHSOverallSpeed
EdgeParse0.8850.5590.5540.7810.007 s/doc
Docling (IBM)0.8670.5400.4380.7450.584 s/doc
OpenDataLoader0.8610.3230.4360.7230.014 s/doc
PyMuPDF4LLM0.8520.3230.4070.7100.327 s/doc
LiteParse0.8150.0000.0010.5640.160 s/doc
MarkItDown0.8070.1930.0010.5640.123 s/doc
  • Latest published snapshot: updated 2026-03-28 on Apple M4 Max across 200 documents
  • EdgeParse is the fastest — 0.007 s/doc per document, 83× faster than Docling
  • Highest overall score — 0.781 across the current six-engine comparison
  • Best structure metrics — leading NID (0.885), TEDS (0.559), and MHS (0.554)
  • Best text metrics — also leads paragraph boundaries, text quality, and table-detection F1 in the full benchmark report
  • No ML stack required — the top score comes from a pure Rust CPU pipeline
ComparisonFactor
EdgeParse vs Docling83.4× faster
EdgeParse vs PyMuPDF4LLM46.7× faster
EdgeParse vs OpenDataLoader2.0× faster
EdgeParse vs MarkItDown17.6× faster
  • Hardware: Apple M4 Max
  • Corpus: 200 diverse PDF documents
  • Mode: Single-threaded
  • Categories: Academic papers, financial reports, invoices, government forms, books, manuals
  • Try Live Demo — parse any PDF in your browser with WebAssembly, no install needed
  • Enterprise — production-grade deployment with priority support by Elitizon