PDF→Markdown Evaluation
9 PDFs · 900 questions · Multiple parsers (Mathpix / TextIn / Reducto / Marker / Internal)
Datasets (9)
23-0323_ego_stx4500_stx4500-fc_stringtrimmer_manual_en
PDF
100 Qs
FEIER
PDF
100 Qs
Hanwha_Integration_Guide
PDF
100 Qs
SSA1200_EGO_SNOW-SHOVEL-ATTACHMENT_22-0519_EXPLOSION-DIAGRAM_VERSION-A
PDF
100 Qs
TP-MVD8MV2-rotated
PDF
100 Qs
ego_accessory_compatibility_matrix
PDF
100 Qs
feier_start_100_manual
PDF
100 Qs
ihealth_bg5
PDF
100 Qs
zt4200s_ego_zero-turn-riding-mower_version-a
PDF
100 Qs
How this works
- Convert each PDF with multiple parsers → store Markdown under
docs/md/<parser>/<doc_id>/ - 100 PDF-specific questions per doc →
questions/<doc_id>/questions.jsonl(mirrored to site) - Run RAG pipelines → write answers to
runs/<parser>/<doc_id>/answers.jsonl - Use an LLM evaluator (or exact-match) against the original PDF to score