Chandra OCR: An Open-Source Model Claiming SOTA Across 90+ Languages

A new 4-billion-parameter open-source OCR model reportedly hits 85.9% accuracy across handwriting, tables, and diagrams in over 90 languages.

A new open-source optical character recognition model called Chandra is drawing attention for its claimed state-of-the-art performance across a remarkably broad scope. As @akshay_pachaar highlighted, the 4-billion-parameter model reportedly achieves 85.9% accuracy and handles handwriting recognition, table extraction, and diagram captioning across more than 90 languages — all released under a fully open-source license.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia curae.

Unlock the full briefing

Get every story in today's briefing, the full archive, and the daily AI intelligence brief.

All stories today

Full archive

Daily brief