Reflection releases Beam, a 501B open-weights MoE under Apache 2.0
Beam is Reflection's first open model: 501B total and 23B active parameters, 1M-token context, under Apache 2.0.
The AI that actually shipped
Beam is Reflection's first open model: 501B total and 23B active parameters, 1M-token context, under Apache 2.0.
Mellum2.1 Thinking is a 12B mixture-of-experts reasoning model with 2.5B active, retrained mostly with reinforcement learning on real repositories.
GLM-5.3 reuses the GLM-5.2 base with new post-training. The weights are public under a custom glm-5.3 licence.