Reflection 发布 Beam，一个 501B 总参数、23B 激活的智能体开源模型，全部权重计划本月开放。该模型从零训练，面向编码、推理和智能体任务，官方称其推理效率比 GLM 5.2 高 3–4 倍，比同类西方开源模型高 4 倍以上。预训练使用 24T token、耗时四周，随后在 10,500 张 GB300 上做四周强化学习，SWE-bench Verified 得分 80.9。
同一新闻，精选展示《Reflection AI 开源智能体模型 Beam：501B 总参数、23B 激活》
Reflection has announced Beam: a 501B-parameter model with 23B active, with full weights scheduled for release this month. Frontier capabilities, and holy is this model efficient!
Trained from scratch, Beam targets coding, reasoning and agentic tasks.
Reflection claims 3–4x higher inference efficiency than GLM 5.2 and over 4x higher efficiency than leading Western open models in its class.
24T pretraining tokens in four weeks, followed by four weeks of reinforcement learning on 10,500 GB300s.
Terminal Bench v2.1 and 80.9 on SWE-bench Verified.
But again: look at the efficency, eypecially in Terminal bench v2.1! Congrats on that launch. More western open models to come.
Introducing Beam: a highly efficient agentic open model with 501B total parameters and 23B active. - Frontier reasoning efficiency - Advances the Western open frontier on coding & agentic tasks - Trained end-to-end from scratch Full weights release this month. Learn more about Beam: http://reflection.ai/beam在 X 查看被引用的帖子
来源：Chubby♨️ · x.com