Benchmark Results
Results Summary
Section titled “Results Summary”| Tool | NID | TEDS | MHS | Overall | Speed |
|---|---|---|---|---|---|
| EdgeParse | 0.885 | 0.559 | 0.554 | 0.781 | 0.007 s/doc |
| Docling (IBM) | 0.867 | 0.540 | 0.438 | 0.745 | 0.584 s/doc |
| OpenDataLoader | 0.861 | 0.323 | 0.436 | 0.723 | 0.014 s/doc |
| PyMuPDF4LLM | 0.852 | 0.323 | 0.407 | 0.710 | 0.327 s/doc |
| LiteParse | 0.815 | 0.000 | 0.001 | 0.564 | 0.160 s/doc |
| MarkItDown | 0.807 | 0.193 | 0.001 | 0.564 | 0.123 s/doc |
Key Takeaways
Section titled “Key Takeaways”- 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
Speed Comparison
Section titled “Speed Comparison”| Comparison | Factor |
|---|---|
| EdgeParse vs Docling | 83.4× faster |
| EdgeParse vs PyMuPDF4LLM | 46.7× faster |
| EdgeParse vs OpenDataLoader | 2.0× faster |
| EdgeParse vs MarkItDown | 17.6× faster |
Test Environment
Section titled “Test Environment”- Hardware: Apple M4 Max
- Corpus: 200 diverse PDF documents
- Mode: Single-threaded
- Categories: Academic papers, financial reports, invoices, government forms, books, manuals
See It in Action
Section titled “See It in Action”- Try Live Demo — parse any PDF in your browser with WebAssembly, no install needed
- Enterprise — production-grade deployment with priority support by Elitizon