Reflection 发布开源权重模型 Beam，主打效率对标 GLM 5.2
Reflection's Beam becomes the most capable open-weight model built outside China
美国 Reflection 放出了首个开源模型 Beam，500 多亿参数只激活 23B，想用更低算力打 DeepSeek 和 Qwen，写代码推理的可以看看。
美国公司 Reflection 发布首个开源权重模型 Beam。该模型采用 MoE 架构，总参数 501B，每 token 仅激活 23B，目标是把 GLM 5.2 的编码与推理水平做到 3 到 4 倍的算力效率。Reflection 的路线是用效率而非原始性能，来对抗 DeepSeek 和 Qwen 等中国开源模型。
Reflection's Beam becomes the most capable open-weight model built outside China
Reflection has released Beam, its first open-weight model. The mixture-of-experts system activates just 23 billion of its 501 billion parameters per token and aims to match GLM 5.2 on coding and reasoning while using three to four times less compute. The strategy against Chinese open-weight rivals like Deepseek and Qwen is efficiency over raw performance. The article Reflection's Beam becomes the most capable open-weight model built outside China appeared first on The Decoder .
