Zhipu GLM-OCR Released: SOTA Performance, Handles Complex Documents
Zhipu AI has officially released and open-sourced the professional-grade OCR model GLM-OCR, achieving "small size, high precision" document parsing capabilities with only 0.9B parameters. The model topped the authoritative OmniDocBench V1.5 evaluation with a score of 94.6, achieving SOTA performance in tasks such as text recognition, formula recognition, table parsing, and information extraction. It is specifically optimized for challenging scenarios such as handwriting, complex tables, and code documents, supports batch processing of PDFs and images, and achieves a throughput of 1.86 pages per second.
Zhipu AI has officially released and open-sourced the professional-grade OCR model GLM-OCR, achieving "small size, high precision" document parsing capabilities with only 0.9B parameters. The model topped the authoritative OmniDocBench V1.5 evaluation with a score of 94.6, achieving SOTA performance in tasks such as text recognition, formula recognition, table parsing, and information extraction. It is specifically optimized for challenging scenarios such as handwriting, complex tables, and code documents, supports batch processing of PDFs and images, and achieves a throughput of 1.86 pages per second.
This page provides an editorial summary based on publicly available information. It is not a republished article. Use the source link below for the original report.