Reflection AI open-sources Beam: 501B params, 23B active, built for reasoning efficiency

SergioPaniego · x · 2026-10-06

Reflection AI has introduced Beam, a highly efficient agentic open model with 501B total parameters and only 23B active, trained end-to-end from scratch. The company says it delivers frontier reasoning efficiency and advances the Western open frontier on coding and agentic tasks, with full weights releasing this month. Commenters in open source note that Reflection AI engineers have been quietly committing to projects like transformers, vLLM, SGLang, TRL and OpenEnv for months — a "low on tweets, high on commits" lab identity behind the release.

Related event: Reflection AI Launches Beam, Its First Open-Weight Model: 501B Total Params, 23B Active(38 posts)→

Original post →

More from coding & agent

coding & agent channel →