The Hunyuan OCR model has been open-sourced, with only 1B of parameters and state-of-the-art (SOTA) capabilities in several core areas.

Tencent's Hunyuan Open Source Lightweight OCR Model, HunyuanOCR, boasts only 1B parameters yet achieves state-of-the-art (SOTA) performance in several core capabilities. Based on Hunyuan's native multimodal architecture and employing an end-to-end design, the model achieved a score of 94.1 on the complex document parsing benchmark OmniDocBench, surpassing mainstream models such as Gemini 3 Pro.