On May 6, LiveBench, an internationally renowned large model evaluation ranking platform, unveiled its latest rankings, with Alibaba's open-source next-generation Tongyi Qianwen model, Qwen3 (Qianwen 3), securing the top spot among global open-source models. In the critical domain of instruction following, Qianwen 3 outperformed leading closed-source models such as o3 High, o4-Mini High, and Gemini 2.5 pro, achieving global supremacy. Despite its modest number of parameters and low cost, Qianwen 3 has demonstrated exceptional performance, setting new benchmarks across multiple evaluations. It supports a wide range of languages and dialects and is freely available for use on various platforms worldwide. Qianwen 3's robust tool invocation capabilities and flexible API configurations cater to the diverse performance and cost requirements of AI applications across different scenarios.