欢迎来到Qwen

Qwen3

Qwen是阿里巴巴集团Qwen团队研发的大语言模型和大型多模态模型系列。无论是语言模型还是多模态模型，均在大规模多语言和多模态数据上进行预训练，并通过高质量数据进行后期微调以贴近人类偏好。Qwen具备自然语言理解、文本生成、视觉理解、音频理解、工具使用、角色扮演、作为AI Agent进行互动等多种能力。

Qwen3-2507

With input from the community and insights from further research, Instruct-only and Thinking-only models are coming back! The results are Qwen3-2507:

Qwen3-Instruct-2507 has the following features:

  • Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage.

  • Substantial gains in long-tail knowledge coverage across multiple languages.

  • Markedly better alignment with user preferences in subjective and open-ended tasks, enabling more helpful responses and higher-quality text generation.

  • Enhanced capabilities in 256K long-context understanding, extensible to 1M.

Qwen3-Thinking-2507 has the following features:

  • Significantly improved performance on reasoning tasks, including logical reasoning, mathematics, science, coding, and academic benchmarks that typically require human expertise — achieving state-of-the-art results among open-source thinking models.

  • Markedly better general capabilities, such as instruction following, tool usage, text generation, and alignment with human preferences.

  • Enhanced 256K long-context understanding capabilities, extensible to 1M.

Qwen3

Qwen3, aka Qwen3-2504, has the following features:

  • 全尺寸稠密与混合专家模型：0.6B, 1.7B, 4B, 8B, 14B, 32B and 30B-A3B, 235B-A22B

  • 支持在**思考模式**（用于复杂逻辑推理、数学和编码）和 非思考模式 （用于高效通用对话）之间**无缝切换**，确保在各种场景下的最佳性能。

  • 显著增强的推理能力，在数学、代码生成和常识逻辑推理方面超越了之前的 QwQ（在思考模式下）和 Qwen2.5 指令模型（在非思考模式下）。

  • 卓越的人类偏好对齐，在创意写作、角色扮演、多轮对话和指令跟随方面表现出色，提供更自然、更吸引人和更具沉浸感的对话体验。

  • 擅长智能体能力，可以在思考和非思考模式下精确集成外部工具，在复杂的基于代理的任务中在开源模型中表现领先。

  • 支持 100 多种语言和方言，具有强大的多语言理解、推理、指令跟随和生成能力。