Reflection's Beam: a 501B open-weight model with only 23B active
Why it matters
Reflection, a new US lab, released open weights for Beam, its first open-weight model, on Hugging Face under Apache 2.0: a mixture-of-experts with 501B total parameters, 23B active per token and a 1M-token context. Built for coding and agents; Reflection's model card reports 81.6% on SWE-bench Verified and 80.1% on Terminal Bench 2.1, and says it needs ~3x fewer reasoning tokens than leading open models for comparable quality. Caveat: those are Reflection's own numbers, and even the NVFP4 checkpoint is ~280 GB (Hugging Face suggests four B200s).
Read the source: Reflection (opens in a new tab)
All hits from 17 Oct 2026More Open ModelsGet the daily hits by email