Qwen3 技术报告
Qwen3 Technical Report
AI总结：
本文提出 Qwen3 模型系列，在统一框架中支持思考与非思考模式及思考预算，覆盖 0.6B–235B 密集与 MoE 模型，并在多类基准和多语言能力上取得先进表现。
摘要：
在本工作中，我们提出了 Qwen 模型家族的最新版本 Qwen3。Qwen3 包含一系列大型语言模型（LLM），旨在提升性能、效率和多语言能力。Qwen3 系列同时涵盖密集架构与混合专家（Mixture-of-Expert，MoE）架构模型，参数规模从 0.6 到 2350 亿不等。Qwen3 的一项关键创新是在统一框架中集成了思考模式（用于复杂的多步推理）和非思考模式（用于快速、由上下文驱动的响应）。这消除了在不同模型之间切换的需要，例如在面向聊天优化的模型（如 GPT-4o）和专用推理模型（如 QwQ-32B）之间切换，并支持根据用户查询或聊天模板进行动态模式切换。同时，Qwen3 引入了思考预算机制，允许用户在推理过程中自适应地分配计算资源，从而根据任务复杂度平衡延迟与性能。此外，通过利用旗舰模型的知识，我们显著减少了构建较小规模模型所需的计算资源，同时确保它们具备极具竞争力的性能。实证评估表明，Qwen3 在代码生成、数学推理、智能体任务等多种基准测试中取得了最先进的结果，可与更大规模的 MoE 模型和专有模型相竞争。与其前代 Qwen2.5 相比，Qwen3 将多语言支持从 29 种语言和方言扩展到 119 种，通过增强跨语言理解和生成能力提升全球可及性。为促进可复现性以及社区驱动的研发，所有 Qwen3 模型均依据 Apache 2.0 公开提供。
英文摘要：
In this work, we present Qwen3, the latest version of the Qwen model family. Qwen3 comprises a series of large language models (LLMs) designed to advance performance, efficiency, and multilingual capabilities. The Qwen3 series includes models of both dense and Mixture-of-Expert (MoE) architectures, with parameter scales ranging from 0.6 to 235 billion. A key innovation in Qwen3 is the integration of thinking mode (for complex, multi-step reasoning) and non-thinking mode (for rapid, context-driven responses) into a unified framework. This eliminates the need to switch between different models--such as chat-optimized models (e.g., GPT-4o) and dedicated reasoning models (e.g., QwQ-32B)--and enables dynamic mode switching based on user queries or chat templates. Meanwhile, Qwen3 introduces a thinking budget mechanism, allowing users to allocate computational resources adaptively during inference, thereby balancing latency and performance based on task complexity. Moreover, by leveraging the knowledge from the flagship models, we significantly reduce the computational resources required to build smaller-scale models, while ensuring their highly competitive performance. Empirical evaluations demonstrate that Qwen3 achieves state-of-the-art results across diverse benchmarks, including tasks in code generation, mathematical reasoning, agent tasks, etc., competitive against larger MoE models and proprietary models. Compared to its predecessor Qwen2.5, Qwen3 expands multilingual support from 29 to 119 languages and dialects, enhancing global accessibility through improved cross-lingual understanding and generation capabilities. To facilitate reproducibility and community-driven research and development, all Qwen3 models are publicly accessible under Apache 2.0.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
