Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now DeepSeek, an AI offshoot of Chinese ...

DeepSeek-R1 demonstrates strong performance across multiple educational and reasoning benchmarks. It achieves 79.8% Pass@1 on AIME 2024, slightly surpassing OpenAI-o1-1217. On MATH-500, it reaches ...

【新智元导读】R1论文暴涨至86页！DeepSeek向世界证明：开源不仅能追平闭源，还能教闭源做事！ 两天前，DeepSeek悄无声息地把R1的论文更新了，从原来22页「膨胀」到86页。 全新的论文证明，只需要强化学习就能提升AI推理能力！ DeepSeek似乎在憋大招，甚至有网友 ...

2025 年 9 月，DeepSeek－R1 论文以封面文章的形式登上 Nature 杂志，成为全球首个通过顶级期刊独立同行评审的主流大语言模型。从 2 月 14 日投稿到 9 月 17 日正式发表，8 位外部专家历时 5 个月对论文的原创性、方法论和稳健性进行了严格审查。Nature 在编辑评论中 ...

What if artificial intelligence could not only write code but also think through problems like a seasoned developer? Enter DeepSeek R1, the latest breakthrough in AI-driven coding and creativity.

Researchers have introduced Light-R1-32B, a new open-source AI model optimized to solve advanced math problems. It is now available on Hugging Face under a permissive Apache 2.0 license — free for ...

Chinese AI lab DeepSeek has released an open version of DeepSeek-R1, its so-called reasoning model, that it claims performs as well as OpenAI’s o1 on certain AI benchmarks. R1 is available from the AI ...

The Chinese artificial intelligence company DeepSeek (DEEPSEEK), which roiled the tech world when it released its R1 large language model in January, released an upgraded version, which it claims is ...

DeepSeek开源了R1的更多技术细节。 1月4日，DeepSeek在arXiv上更新了R1论文。 没有官宣，没有推文，只是版本号从v1变成了v2。但打开PDF的人都会发现一个变化，页数从22页膨胀到了86页，文件大小从928KB涨到1562KB。 新增内容包括完整的训练管线拆解、20多个评测基准的 ...