Datalab releases OmniParseBench, an open OCR benchmark with 16,288 pass/fail tests
Overview
Datalab releases OmniParseBench, an open OCR benchmark that scores document parsers with 16,288 yes/no tests on 2,937 pages across 92 languages, according to MarkTechPost.
The dataset and code are public. OmniParseBench is an evaluation harness, not a model, and scoring runs offline without API keys. The harness installs with uv pip install omni-parse-bench and requires Python 3.11 or later.
On the launch leaderboard, Gemini 3.8 Flash scores 92.9 and Datalab's own parser scores 92.7, placing second.
Written by AI from the articles below · updated Oct 14, 9:01 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- MarkTechPostNewsDatalab releases OmniParseBench, an open OCR benchmark with 16,288 pass/fail tests
AIDatalab releases OmniParseBench, an open OCR benchmark that scores document parsers with 16,288 yes/no tests on 2,937 pages across 92 languages. The dataset and code are public, and the harness installs with uv pip install omni-parse-bench, needs Python 3.11+, and scores outputs offline without API keys. Gemini 3.8 Flash leads the launch leaderboard at 92.9, with Datalab accurate second at 92.7.
Heat trend
Not enough continuous observations to show a trend yet.