MiniMax 已在 Hugging Face 公开 MiniMax M3.1 Flash 模型权重，该模型总参数 428B、每 token 激活 23B。官方称其在智能体任务、编码与网络安全上大幅提升，BankerToolBench 得 76.2、DeepSWE v1.1 得 73.7%、OSWorld V2 得 61.7、Agents' Last Exam 得 29.6、CyberGym 得 82.2，并采用 MiniMax Sparse Attention 与 DSpark 投机解码提升推理效率。该模型即 OpenRouter 上的匿名模型 Space Bunny，于 10 月 19 日发布，现已在 MiniMax 平台和 API 上线，同时提供 ModelScope 与桌面端 MCode 入口。
材料给出 428B 总参数、23B 激活的稀疏结构和多项智能体基准分数，可据此判断其开源模型的定位。
MiniMax has published MiniMax M3.1 Flash weights on HuggingFace.
The model has 428B parameters total, 23B activated per token.
MiniMax M3.1 Flash, also known as "Space Bunny" stealth model from OpenRouter, was announced on October 19 and is now available on MiniMax platform and APIs.
【引用 @MiniMax_AI】MiniMax M3.1 Flash weights are now public. 428B parameters total, 23B activated per token.
Agentic performance: A generational leap in agentic tasks, coding, and cybersecurity — 76.2 on BankerToolBench, 73.7% on DeepSWE v1.1, 61.7 on OSWorld V2, 29.6 on Agents' Last Exam, and 82.2 on CyberGym.
Efficient by design: MiniMax Sparse Attention and DSpark speculative decoding improve inference efficiency.
Hugging Face:
https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash
ModelScope:
https://modelscope.cn/models/MiniMax/MiniMax-M3.1-Flash
API: http://platform.minimax.io
M Plan: https://minimax.io/m-planMiniMax
MCode for desktop: https://agent.minimax.io/download
MiniMax M3.1 Flash weights are now public. 428B parameters total, 23B activated per token. Agentic performance: A generational leap in agentic tasks, coding, and cybersecurity — 76.2 on BankerToolBench, 73.7% on DeepSWE v1.1, 61.7 on OSWorld V2, 29.6 on Agents' Last Exam, and 82.2 on CyberGym. Efficient by design: MiniMax Sparse Attention and DSpark speculative decoding improve inference efficiency. Hugging Face: https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash ModelScope: https://modelscope.cn/models/MiniMax/MiniMax-M3.1-Flash API: http://platform.minimax.io M Plan: https://minimax.io/m-planMiniMax MCode for desktop: https://agent.minimax.io/download在 X 查看被引用的帖子
来源：🚨 AI News | TestingCatalog · x.com