Reflection releases Beam, an open-weight reasoning model
Reflection AI has introduced Beam, a new 501-billion-parameter open-weight model designed to match leading reasoning benchmarks at lower operational costs.
2 min read, Tuesday, 6 October

Brooklyn-based startup Reflection AI has officially unveiled Beam, its first frontier, open-weight artificial intelligence model. The text-only system uses a mixture-of-experts architecture — a design where the model routes each token to specialized sub-networks — and is trained on high-compute reinforcement learning.
Key facts
- CEO
- Misha Laskin
- Key Partner
- Shinsegae Group
- Infrastructure Partners
- Nebius and SpaceX
- Backer
- Nvidia
Model architecture and specifications
Beam features 501 billion total parameters with 23 billion active parameters. It was pretrained on 23.8 trillion tokens and includes a 1 million token context window. According to the company, the model is designed to handle reasoning, coding, and agentic tasks while using significantly less inference compute than comparable systems.

Performance and positioning
On advanced reasoning benchmarks, Reflection reports that Beam scores on par with Z.ai's GLM-5.2 model while outperforming several other open alternatives. The startup intends for Beam to serve as a workhorse model for enterprises, developers, and the public sector.
Infrastructure and future releases
Founded in 2024 by former Google DeepMind researchers, Reflection has secured billions in funding from backers including Nvidia, Sequoia Capital, and Lightspeed Venture Partners. The startup also signed infrastructure deals with SpaceX and Nebius to access Nvidia chips through 2029.
Reflection plans to release Beam's weights and full technical documentation this month, with distribution through cloud providers and integrations across open-source libraries.
Source: Original announcement
Worth a read?



Comments