Launched this week
Baseer
A vision-language model that outperforms GPT-5 on Arabic OCR
16 followers
A vision-language model that outperforms GPT-5 on Arabic OCR
16 followers
Baseer is a vision-language model built specifically for Arabic documents it outperforms GPT-5, Gemini 2.5 Pro, and Azure Document Intelligence on OCR benchmarks. Extracts text, tables (HTML), and equations (LaTeX) while preserving structure. API, on-prem, or web.
