olmOCR-Bench.

7,010 unit tests across 1,402 PDF documents. Tests parsing of tables, math, multi-column layouts, old scans, and more.

Best published scores.

56 results indexed across 9 metrics. Shaded row marks current SOTA; ties broken by submission date.

Primary

pass-rate · higher is better

All metrics

arxiv, base, headers-footers, long-tiny-text, multi-column, old-scans, old-scans-math, pass-rate, tables

4 steps
of state of the art.

Each row below marks a model that broke the previous record on pass-rate. Intermediate submissions are kept in the leaderboard above; only SOTA-setting entries are re-listed here.

Higher scores win. Each subsequent entry improved upon the previous best.

1. Jun 5, 2025MonkeyOCR-pro-3B75.80
2. Dec 16, 2025Chandra v0.1.0datalab-to83.10
3. Jan 20, 2026LightOnOCR-2-1BLightOn83.20
4. Mar 19, 2026dots.mocrRedNote83.90

Neighbouring benchmarks.

Other Document Parsing datasets on Codesota.

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

• 01A public checkpoint or API endpoint
• 02A reproduction script with frozen commit + seed
• 03Declared evaluation environment (Python, deps)
• 04One row per metric declared by this dataset
• 05A contact so we can follow up on discrepancies