Qwen
Qwen (also known as Tongyi Qianwen) is a family of large language models developed by Alibaba Cloud. It ranks as one of the top performing Chinese language models and has achieved significant benchmarks globally. The model family includes various versions optimized for different tasks, including Qwen-VL for vision-language tasks, Qwen-Audio for audio processing, and specialized versions like Qwen2-Math for mathematical reasoning.
Qwen2.5
Qwen2.5 is the latest generation of the Qwen (Tongyi Qianwen) model family, featuring advanced MoE architecture and superior performance in reasoning, mathematics, and coding tasks.
Qwen3
Qwen3 is the next-generation family of Qwen large language models featuring dense and Mixture-of-Experts variants, seamless reasoning "thinking" mode, 32K–131K token context windows, and state-of-the-art performance in multilingual chat, coding and mathematical reasoning tasks.