Reflection's Beam: A 501B open-weight model that matches giants with 3–4× less compute
Beam: Reflection's 501B open-weight model
Reflection released Beam, its first open-weight model: a 501B-parameter sparse Mixture-of-Experts with 23B active parameters, trained on 23.8T tokens and an RL run of over 100 million rollouts on 10.5K NVIDIA GB300 GPUs. Beam targets coding and agentic tasks, trading raw capability for inference efficiency—matching GLM-5.2 on reasoning with 3–4× less compute. Weights and technical report arrive later this month.
Even when training Beam with one-day staleness—107 weight versions behind the current policy—the numerics remain stable.