Codesota · Models · olmOCR-7BAllen AI3 results · 2 benchmarks
Model card

olmOCR-7B.

Allen AIopen-source
§ 02 · Benchmarks

Every benchmark olmOCR-7B has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01OmniDocBenchComputer Vision · Document Parsingaccuracy81.8%#13/13source ↗
02olmOCR-BenchComputer Vision · Document Parsingaccuracy75.5%#16/18source ↗
03OmniDocBenchComputer Vision · Document Parsingcomposite81.8%#24/34source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where olmOCR-7B actually performs.

Computer Vision
2
benchmarks
avg rank #17.7
§ 04 · Papers

1 paper with results for olmOCR-7B.

  1. 2025-02-25· 2 results

    olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models

§ 05 · Related models

Other Allen AI models scored on Codesota.

olmOCR v0.4.0
9 results
olmOCR v0.3.0
2 results
§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
2
results
omnidocbench-leaderboard
1
result
0 of 3 rows marked verified.