GLM-OCR Explained: 0.9B Model That Beats Gemini 3 Pro at OCR
Last updated: April 2026 GLM-OCR is a 0.9-billion-parameter multimodal OCR model by Zhipu AI that scored 94.62 on OmniDocBench V1.5 — the highest of any model, open or closed. It outperforms Gemini 3 Pro (90.33), GPT-5.2 (85.4), and Qwen3-VL-235B (89.15) on document parsing despite being 260× smaller than the largest competitor. The model combines a … Read more