[AINews] Reflection Beam - 501B-A23B American Open Model
Reflection launched Beam, a US-trained 501B-total, 23B-active MoE for coding and agents, with Apache 2.0 weights due this month.
Reflection announced Beam, a text-only mixture-of-experts model with 501 billion total parameters and 23 billion active, aimed at coding, agentic, and scientific work. It was trained from scratch on 23.8 trillion tokens, including OCR over hundreds of millions of PDFs, with reinforcement learning described as more than 100 million rollouts on about 10,500 NVIDIA GB300s. Reflection claims 80.9 on SWE-bench Verified and three to four times the inference efficiency of GLM 5.2; full Apache 2.0 weights are due this month. Independent observers place it near GLM-5.2 and behind newer Chinese models such as DeepSeek V4 and GLM 5.3.