AM-Thinking-v1：推进32B规模推理的前沿
AM-Thinking-v1: Advancing the Frontier of Reasoning at 32B Scale
AI总结：
AM-Thinking-v1是基于Qwen2.5-32B构建的开源稠密推理模型，通过监督微调与强化学习，超越DeepSeek-R1，媲美大型MoE模型，在数学和编码基准上取得领先成绩，平衡了性能与实用性。
摘要：
我们提出AM-Thinking-v1，一个32B稠密语言模型，它推进了推理的前沿，体现了开源创新的协作精神。该模型超越了DeepSeek-R1，并与领先的混合专家（MoE）模型如Qwen3-235B-A22B和Seed1.5-Thinking相抗衡，在AIME 2024上取得85.3分，在AIME 2025上取得74.4分，在LiveCodeBench上取得70.3分，展示了在相似规模开源模型中顶尖的数学与编码能力。AM-Thinking-v1完全基于开源的Qwen2.5-32B基础模型和公开可用的查询构建，利用精心设计的后训练流程——结合监督微调和强化学习——以提供卓越的推理能力。这项工作表明，开源社区可以在32B规模上实现高性能，这是部署和微调的实际甜点。通过在顶级性能和实际可用性之间取得平衡，我们希望AM-Thinking-v1能激发进一步的协作努力，利用中型模型，在保持可访问性作为创新核心的同时，推动推理边界。我们已在Hugging Face上开源了我们的模型。
英文摘要：
We present AM-Thinking-v1, a 32B dense language model that advances the frontier of reasoning, embodying the collaborative spirit of open-source innovation. Outperforming DeepSeek-R1 and rivaling leading Mixture-of-Experts (MoE) models like Qwen3-235B-A22B and Seed1.5-Thinking, AM-Thinking-v1 achieves impressive scores of 85.3 on AIME 2024, 74.4 on AIME 2025, and 70.3 on LiveCodeBench, showcasing state-of-the-art mathematical and coding capabilities among open-source models of similar scale. Built entirely from the open-source Qwen2.5-32B base model and publicly available queries, AM-Thinking-v1 leverages a meticulously crafted post-training pipeline - combining supervised fine-tuning and reinforcement learning - to deliver exceptional reasoning capabilities. This work demonstrates that the open-source community can achieve high performance at the 32B scale, a practical sweet spot for deployment and fine-tuning. By striking a balance between top-tier performance and real-world usability, we hope AM-Thinking-v1 inspires further collaborative efforts to harness mid-scale models, pushing reasoning boundaries while keeping accessibility at the core of innovation. We have open-sourced our model on \href{https://huggingface.co/a-m-team/AM-Thinking-v1}{Hugging Face}.
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。
