Reflection AI debuts Beam, a 501B open-weight model rivaling GLM 5.2 with 3-4x less compute
Reflection AI has released Beam, its first open-weight AI model, a 501-billion-parameter Mixture-of-Experts model with 23 billion active parameters. The model was pretrained on 23.8 trillion tokens and trained using reinforcement learning on 10,500 NVIDIA GB300 GPUs over four weeks, generating over 100 million rollouts. Reflection claims Beam matches the reasoning performance of Z.ai’s GLM-5.2…
Key points
- Beam is a 501B-parameter, 23B-active MoE model pretrained on 23.8T tokens
- Reflection claims Beam matches GLM-5.2 reasoning with 3-4x less inference compute
- Beam’s weights will be released under Apache 2.0 later this month
Model page: GLM 5.3 →
The story so far
4 episodes →- Reflection AI debuts Beam, a 501B open-weight model rivaling GLM 5.2 with 3-4x less computethis story
Reflection unveils Beam, an open model it says rivals GLM 5.2 on reasoning while using 3x-4× less compute and approaches Qwen3.8-Max on coding and agentic tasks
semafor.com · 5 October 2026
Loading the full article…
This text was published by semafor.com and written by https://www.semafor.com/author/jd-capelouto, https://www.semafor.com/author/ashley-gold. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
Coverage and discussion
10sources- Reflection's Beam becomes the most capable open-weight model built outside ChinaPress · The Decoder ·
- The 'DeepSeek of the West' finally has a modelNewsletter · The Rundown AI ·
- [AINews] Reflection Beam - 501B-A23B American Open ModelNewsletter · Latent Space ·
- Reflection AI’s Beam model challenges Anthropic’s AI dominancePress · cryptobriefing.com ·
- Reflection AI Introduces Beam: A 501B Open-Weight MoE Model With 23B Active Parameters for Coding and Agentic WorkloadsPress · MarkTechPost ·
- Reflection AI Unveils Beam, a 501B-Parameter Open-Weight ModelPress · Unite.AI ·
- Reflection debuts Beam, an open-weight AI model to rival Chinese models at lower compute costPress · TechCrunch AI ·
- Nvidia-backed Reflection unveils Open AI model, taking on ChinaPress · thehindubusinessline.com ·
- What is Beam? The buzzy American AI model being called the 'DeepSeek of the West'Press · businessinsider.com ·
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Generative AI & Models
All →- Apiiro finds 1,122 public GitHub files with secrets saved by Claude Code · 1 src
- Thinking Machines releases Inkling 2 Small, a 594B MoE model with 17B active parameters · 8 src
- OpenAI releases GPT-6 Cyber, a Critical-rated model that outperforms predecessors in vulnerability detection and alignment · 25 src
- Google releases Gemini Omni 1.2 Flash with 15-second video generation and 30% price cut to $0.07 per second · 10 src
- US accuses Chinese executive of allegedly sharing Nvidia chip info with Beijing · 11 src
Comments
via GitHub Discussions