OmniDocBench

Measures: End-to-end parsing of varied PDF pages (academic papers, textbooks, slides, financial reports, newspapers, handwritten notes; English and Chinese) into structured markdown. Overall = mean of (1 - text edit distance) x 100, table TEDS and formula CDM; text and reading-order edit distance are lower-is-better.

Maintainer: OpenDataLab
Introduced: 2024
Status: Active
Saturation: Saturated
Typical provenance: Mixed
In scoring set: No

Paper Official leaderboard

Leaderboard

Show independent results only

Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.

No results to show.