Does Baidu release open-weight models?

Yes. Its Unlimited OCR document parsing models are published on Hugging Face and ModelScope under the MIT licence, with code on GitHub.

Baidu news

Internet and AI company1 story

Baidu is a Beijing-based internet and AI company, best known for China's largest search engine.

Baidu's long, wave-shaped glass headquarters building in Beijing behind a lawn and trees. — Baidu open-sources Unlimited OCR 2, a 3.3B model that parses documents hundreds of pages long

Open Source AI27 Oct 2026, 09:00 UTC

Baidu released Unlimited OCR 2 under MIT on 27 October 2026. It scores 77.1 on Baidu's new hundred-page MarathonDocBench, where rivals score under 34.

Summary

Baidu released Unlimited OCR 2 on 27 October 2026, an open-weight document parsing model of about 3.3 billion parameters under the MIT licence. A new attention method keeps memory and decoding speed nearly flat as documents grow, so the model can parse documents hundreds of pages long in one pass. On Baidu's new MarathonDocBench it scores 77.1, against 33.7 for the best model Baidu compared it with.

About Baidu

Baidu is a Beijing-based internet and AI company, best known for China's largest search engine. It develops the ERNIE model family, runs the Baidu AI Cloud and the PaddlePaddle deep learning framework, and publishes open-weight models such as the Unlimited OCR document parsing series on Hugging Face and GitHub.

Reviewed 28 Oct 2026

Facts at a glance

Type: Public internet, cloud and AI company
Headquarters: Beijing, China
Open models: Unlimited OCR and Unlimited OCR 2 on Hugging Face under the MIT licence source
Frameworks: PaddlePaddle deep learning framework

Questions people ask

Does Baidu release open-weight models?: Yes. Its Unlimited OCR document parsing models are published on Hugging Face and ModelScope under the MIT licence, with code on GitHub.
Where is Baidu based?: Beijing, China.

Baidu news

Every story about Baidu

Baidu open-sources Unlimited OCR 2, a 3.3B model that parses documents hundreds of pages long