olmOCR

license

Apache-2.0(OSI)

source

public(allenai/olmocr)

governance

Allen Institute for AI

core-gated

ungated

Fully OSI-licensed (Apache-2.0), full source public.

• https://github.com/allenai/olmocr/blob/main/LICENSE recorded 2026-08-13

  Apache License Version 2.0 text

• https://raw.githubusercontent.com/allenai/olmocr/main/README.md recorded 2026-08-13

  README documents the whole pipeline building and installing from the published repo; no paid tier, enterprise edition or license key appears anywhere in it, so nothing is withheld from the source

22,925 PyPI downloads in the trailing 30 days for olmocr, which bands at 10K-100K, level 2 on the software and model adoption scale.

• https://pypistats.org/api/packages/olmocr/recent recorded 2026-08-13

  22,925 downloads in the trailing 30 days for olmocr

Benchmark-anchored: olmOCR scores near the top of olmOCR-Bench, the benchmark the project publishes itself, ahead of Marker, MinerU and Mistral OCR but now behind Chandra OCR and Infinity-Parser; on the third-party OmniDocBench it sits mid-pack. Near-SOTA rather than SOTA, and a snapshot at that, because extraction leaderboards move.

• https://raw.githubusercontent.com/allenai/olmocr/main/README.md recorded 2026-08-13

  olmOCR-Bench table in the README - olmOCR v0.4.0 scores 82.4, ahead of Marker 1.10.1 76.1, MinerU 2.5.4 75.2 and Mistral OCR 72.0, but now behind Chandra OCR 0.1.0 83.1 and Infinity-Parser 7B 82.5. GPT-4o has been dropped from the table.

• https://raw.githubusercontent.com/opendatalab/OmniDocBench/main/README.md recorded 2026-08-13

  OmniDocBench leaderboard - olmOCR 85.74 overall, mid-pack behind MinerU-2.5 93.04, Gemini 3 Pro 92.91 and GPT-5.2 86.59, and level with Mistral OCR 85.66