Benchmark

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

PaperOfficial leaderboard

Leaderboard

Independent and third-party results only.

No independent or third-party results yet. Show all results