Introducing GLM-OCR: SOTA performance, optimized for complex document understanding.
With only 0.9B parameters, GLM-OCR delivers state-of-the-art results across major document understanding benchmarks, including formula recognition, table recognition, and information extraction.
Weights: https://t.co/vqIBgBCXYi
Try it: https://t.co/Ld7H8Pasls
API:
Optimized for real-world scenarios: It handles complex tables, code-heavy docs, official seals, and other challenging elements where traditional OCR fails.
The model integrates the CogViT visual encoder pre-trained on large-scale image–text data, a lightweight cross-modal connector with efficient token downsampling, and a GLM-0.5B language decoder. Combined with a two-stage pipeline of layout analysis and parallel recognition based on PP-DocLayout-V3, GLM-OCR delivers robust and high-quality OCR performance across diverse document layouts.
GLM-OCR achieves a throughput of 1.86 pages/second for PDF documents and 0.67 images/second for images, significantly outperforming comparable models.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
Why it matters
Document parsing at this quality normally means a large vision model. A 0.9B model with open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition →, seals and table handling, and 1.86 PDF pages per second changes what fits in a local ingestion pipeline.
