Latent Space · 10/6/2026, 6:28:43 AM
Reflection Launches Beam: 501B-Param US-Trained Open Model
Startup Reflection has officially launched Beam, a large language model with 501B total and 23B active parameters. Trained from scratch in the US to address the demand for domestic open-source options, the model trails current SOTA leaders like GLM 5.3 but marks Reflection's arrival as a functional new AI lab.
SOURCE COVERAGEOriginal coverage
It’s been over a year since Reflection launched with us with big goals on coding (and hinted about their RL approach):
But they stayed “stealth” longer than Thinking Machines and it was not clear we would ever get a model launch out of them, as the broader open model ecosystem did not slow down one bigt for them. Well, we did:
They compare themselves to Inkling, Nemotron, and GLM 5.2, but the SOTA GLM 5.3, Kimi K3, Qwen 3.8 Max, and DeepSeek V4.1 Flash are generally ahead. Still, since this is US-trained from scratch, there’s a segment of the market that has been eagerly waiting for more options here, and more importantly, Reflection has now announced its arrival as a functional neolab!