3月6日,阿里Qwen团队正式发布他们最新的研究成果 —— QwQ-32B大语言模型!QwQ-32B在仅有DeepSeek-R1约1/20参数量的情况下, 用强化学习,实现了性能上的惊人跨越!
官方给出基准评测结果,涵盖了数学推理、代码能力和通用问题解决等多个方面。从数据中我们可以清晰地看到,在 AIME24 和 IFEval 等关键基准测试中,QwQ-32B 的表现甚至略微超过了参数量巨大的 DeepSeek-R1! 而在其他基准测试中,也基本与 DeepSeek-R1 持平,远超其他对比模型。
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.