Verified record · from the answer index

lucataco/glm-ocr

modeltested · static-verifiedscore 79/100signed passport ✓published 176d ago · verified 2026-10-248,300 uses

Compact 0.9B multimodal OCR model from Z.ai. State-of-the-art on OmniDocBench V1.5 (94.62, #1 overall). Four modes: text recognition, formula (LaTeX), table parsing, and JSON-schema information extraction. Fits on a single T4.

Declared tools (1)

lucataco/glm-ocr

model:replicate:lucataco/glm-ocr