Skip to main content
ModelScale

Multimodal & Grounded benchmark

olmOCR leaderboard

olmOCR-Bench. Every model the catalog carries a published olmOCR value for, ranked by that value.

CategoryMultimodal & Grounded
MeasureMean accuracy
TasksLayout-rich PDF understanding
DifficultyComplex document processing
Published byolmOCR-Bench

An end-to-end document understanding benchmark over long, layout-rich PDFs with tables, equations, headers, footnotes, and multi-column flows.

olmOCR ranking

1 model with a published olmOCR value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

Models ranked by their published olmOCR-Bench value
RankModelProviderMean accuracy
1INInterfaze BetaInterfaze85.7

Evidence key: Observed

Rows are ordered by the value olmOCR-Bench published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.

All leaderboards