Skip to content

Zhipu AI · OCR

GLM OCR

Zhipu AI 🇨🇳OCRGLM familyOpen weights. The weights are publicly available in a Hugging Face repo.
From Neosantara's listing:
GLM-OCR model by Z.ai, specialized in high-accuracy text extraction, table recognition (HTML), and formula recognition (LaTeX). Note: Does not support visual grounding output.
Max context
131K
Listings
6
Providers
6

Evidence and sources

🤗 zai-org/GLM-OCRReleased 2 Feb 2026Maker HQ: CN (source)
Sources: Neosantara Inference data, Together AI data, AI/ML API data, llminfo researchPrimary data from Neosantara Inference from Together AI: name from AI/ML API: primary mode from llminfo research: release date
Tags from its sources:open-sourcevisionocrmultilinguallightweight

Advantages and trade-offs

Compared with 10 representative OCR models

Advantages

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.

Input & output

as stated by the model's providers
Text
Images
Text

Listings

 Zhipu AI (Open Platform)glm-ocrSource: Zhipu BigModel Open Platform Pricing32K—
 Z.aiGLM-OCRSource: Z.AI PricingNot published by the provider$0.03$0.03—
 Eurouterzhipu/glm-ocrSource: EURouter data8K—
 Neosantaraglm-ocrSource: Neosantara Inference dataNot published by the provider——

2 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

OCR

OCR ArenaSource: OCR Arena data · Nov 2026

Math

Vision

Other

Data credits: Hugging Face official benchmark leaderboards; licence varies by benchmark · OmniDocBench (OpenDataLab), Apache-2.0 (licence)

Also known as: zai-org/glm-ocr, zhipu/glm-ocr

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works