opendataloader-bench
1. About the Project
PDF documents are everywhere, but LLMs can't read them directly. Extracting structured content — headings, tables, reading order — from PDFs is essential for RAG pipelines and document processing workflows.
This benchmark evaluates document structure and layout analysis engines to help you choose the right tool.
What we measure:
- Reading Order — Is the text extracted in the correct sequence?
- Table Fidelity — Are tables accurately reconstructed?
- Heading Hierarchy — Is the document structure preserved? The evaluation pipeline is modular—add new engines, corpora, or metrics with minimal effort.