olmOCR-Bench
An end-to-end document understanding benchmark over long, layout-rich PDFs with tables, equations, headers, footnotes, and multi-column flows.
1 models
Higher is better.
About this benchmark
- Metric
- Mean accuracy
- Tasks
- Layout-rich PDF understanding
- Authors
- Allen Institute for AI (2025)
- Source
- olmOCR-Bench ↗
Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.