Beam: Reflection's 501B open-weight model

In one line

Make intelligence open and accessible to all

Opening excerpt

We are introducing Beam, Reflection’s first open-weight model. Beam is a sparse Mixture-of-Experts model with 501 billion total parameters, 23 billion active, built for coding, reasoning, and agentic workloads.

Beam’s capabilities come from major investments in both pretraining and reinforcement learning (RL). We pretrained the model on 23.8 trillion diverse, curated, high-quality tokens from the web and proprietary licensed datasets, matching or outperforming available similar-sized open base models. In parallel, we developed the algorithms, training environments, and infrastructure needed to sustain high-compute RL at exceptional scale. Our high-compute RL run generated over 100 million rollouts on 10.5K NVIDIA GB300 GPUs over 4 weeks of training.

Together, these efforts produced competitive open-weight performance with frontier inference compute efficiency.

We trained Beam with a particular focus on coding and agentic performance. Beam advances the Western open-weight frontier and is competitive with larger open models like GLM 5.2 and approaching Qwen 3.8-Max on coding and agentic …

(Excerpted from the original; full article via the source link below.)

This story hit the Hacker News front page today (196 points / 56 comments, via reflection.ai). Our Tech Radar aggregates daily signals on AI engineering, backend architecture and DevOps — browse the related services and further reading below, or get in touch with our team.