On-demand local services giant Meituan has become the latest Chinese Big Tech company to release an open-source large language model (LLM) to market, more than two years after it acquired mainland AI start-up Light Year for US$281 million.
Advertisement
Beijing-based Meituan, the long-standing leader of China’s food delivery market, on Monday released and open-sourced its own LLM, called LongCat-Flash-Chat, via artificial intelligence developer platforms Hugging Face and GitHub, as well as the model’s official website.
According to the model’s technical report, LongCat-Flash-Chat features 560 billion total parameters – the variables used to define and manipulate the input and output of models – and the so-called Mixture-of-Experts (MoE) architecture. MoE architecture divides the model into separate sub-networks, or “experts”, that specialise in a subset of the input data to jointly perform a task.
In technical benchmark comparisons cited in the report, LongCat-Flash-Chat was shown to be on par with the performance of DeepSeek’s V3.1, Alibaba Cloud’s Qwen3 family and Moonshot AI’s Kimi K2, as well as US models like Anthropic’s Claude Sonnet and Google’s Gemini 2.5 Flash. Alibaba Cloud is the AI and cloud computing unit of Alibaba Group Holding, owner of the South China Morning Post.
Meituan’s foray into open-source models reflects its efforts to establish a viable AI business since acquiring Light Year, which was established by a co-founder of the food delivery services giant.
Advertisement
It also showed how Chinese AI companies are continuing to narrow the gap with their US peers through the open-source approach, which makes the source code of AI models available for third-party developers to use, modify and distribute.