新浪科技讯 4月30日上午消息，小米开源首个为推理（Reasoning）而生的大模型‘Xiaomi MiMo’，联动预训练到后训练，全面提升推理能力。

　　据介绍，在数学推理（AIME 24-25）和 代码竞赛（LiveCodeBench v5）公开测评集上，MiMo 仅用 7B 的参数规模，超越了 OpenAI 的闭源推理模型 o1-mini 和阿里 Qwen 更大规模的开源推理模型 QwQ-32B-Preview。

　　随着DeepSeek-R1引发业界强化学习（RL）共创潮，DeepSeek-R1-Distill-7B和Qwen2.5-32B已成为广泛使用的强化学习起步模型。在相同RL训练数据情况下，MiMo-7B 的数学&代码领域的强化学习潜力显著领先。

　　值得注意的是，MiMo-7B全系列模型均已开源。据了解，MiMo 来自小米全新成立不久的“小米大模型Core团队”的初步尝试。（闫妍）

海量资讯、精准解读，尽在新浪财经APP

责任编辑：郝欣煜

Disclaimer: Investing carries risk. This is not financial advice. The above content should not be regarded as an offer, recommendation, or solicitation on acquiring or disposing of any financial products, any associated discussions, comments, or posts by author or other users should not be considered as such either. It is solely for general information purpose only, which does not consider your own investment objectives, financial situations or needs. TTM assumes no responsibility or warranty for the accuracy and completeness of the information, investors should do their own research and may seek professional advice before investing.