Tencent announces Hunyuan OCR with 1 billion parameters
A briefing published on November 25, 2025, describes a document-understanding model offering parsing, visual question answering, and translation. It also mentions an interactive demo and access to the model.
On November 25, 2025, a briefing reported Tencent’s launch of Hunyuan OCR, described as an end-to-end document-understanding model with 1 billion parameters. According to the text, it offers document parsing, visual question answering, and translation. Engineers can evaluate it on these tasks; the post also mentions an interactive demo and a model page, but provides no test results or performance metrics.
To consult and verify the report, find Tencent’s original post and check its task descriptions, model page, and cited demo. Compare any results you observe with your team’s documents and evaluation criteria. If you use AI to study or test the material, avoid submitting confidential documents without authorization and check the data-handling rules of the tool you choose.