Reflection 发布 Beam：501B 参数 MoE 模型，本月开放全部权重
Reflection 的 Beam 开源在即，501B 参数只激活 23B，SWE-bench Verified 拿到 80.9 分，效率号称比 GLM 5.2 高 3-4 倍，写代码跑智能体的可以盯一下。
Reflection 宣布推出 Beam，一个 501B 参数、23B 激活的 MoE 模型，从零开始训练，主打编程、推理和智能体任务，并计划本月放出全部权重。模型用 24T token 预训练四周，随后在 10,500 块 GB300 上做了四周强化学习。官方称推理效率比 GLM 5.2 高 3-4 倍，比同级别领先的开源模型高 4 倍以上。基准成绩包括 Terminal Bench v2.1 领先表现和 SWE-bench Verified 的 80.9 分。
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.
