Alibaba has unveiled Qwen3, a new family of open-source large language models that the company describes as a significant milestone in the journey toward artificial general intelligence and artificial superintelligence . The flagship model, Qwen3-235B-A22B, has demonstrated superior performance in several benchmarks, surpassing models from OpenAI and DeepSeek.
The Qwen3 series comprises six dense models and two Mixture-of-Experts models, ranging from 0.6 billion to 235 billion parameters. Notably, the Qwen3-235B-A22B model, with 22 billion active parameters, has achieved leading scores in various evaluations. On the Codeforces platform, it attained an Elo rating of 2056, outperforming DeepSeek-R1 and Google’s Gemini 2.5 Pro. In the AIME’24 and AIME’25 math benchmarks, it scored 85.7 and 81.4, respectively, indicating strong mathematical reasoning capabilities.
A distinctive feature of Qwen3 is its hybrid reasoning capability, allowing dynamic switching between “thinking” and “non-thinking” modes. The “thinking” mode is designed for complex, multi-step tasks such as mathematics, coding, and logical deduction, while the “non-thinking” mode facilitates fast, general-purpose responses. This dual-mode operation aims to optimize performance across a broad range of applications.
The models have been trained on 36 trillion tokens across 119 languages and dialects, enhancing their multilingual capabilities. This extensive training dataset contributes to Qwen3’s proficiency in handling diverse linguistic contexts, making it a versatile tool for global applications.
In terms of deployment efficiency, Qwen3-235B-A22B offers significant advantages. Despite its large parameter count, the model activates only 22 billion parameters during inference, reducing computational requirements and associated costs. This efficiency is particularly beneficial for developers seeking high-performance models without prohibitive resource demands.
The Qwen3 series is available under the Apache 2.0 license, promoting accessibility and collaboration within the AI research community. Developers can access the models through platforms such as Hugging Face and GitHub, facilitating integration into various applications, including mobile devices, smart glasses, autonomous vehicles, and robotics.
Alibaba’s release of Qwen3 represents a strategic move to position itself as a leader in the AI domain, challenging established players like OpenAI and Google. The company’s focus on hybrid reasoning and multilingual support reflects a commitment to advancing AI capabilities in a manner that is both innovative and inclusive.
