AI News/Wire summary
Reflection announces Beam, a 501B-parameter open-weight MoE for coding
Key points
- Full weights under Apache 2.0 are due this month. The text-only model has 23B active parameters per token.
- Team posts cite 23.8T pretraining tokens. Reflection's claimed 80.9 on SWE-bench Verified is unverified, and a tech report is promised.
- Observers reportedly place Beam around GLM-5.2 level and below DeepSeek V4 Flash on some benchmarks.
- Artificial Analysis, which had early access, expects Beam to be among the most token-efficient open models for its intelligence.
Why it matters for marketers: Content and marketing teams citing open-model benchmarks should wait for the promised weights and tech report before repeating Beam's self-reported scores.
Summary by the Z Media news desk, from the outlets' reporting. Read the full stories at the source.
Read the original
Latent Space: [AINews] Reflection Beam - 501B-A23B American Open Model
More coverage
Related on Z Media
- Google ships Gemini 4 Argon with tiered access and a price that doubles in NovemberOur brief, via Google DeepMind, 2 days ago
- Meta ships Muse Wonder, its first frontier-class models, with new agent memory featuresOur brief, via TechCrunch, 3 days ago
- Meta releases Muse Spark Open, runnable on two Apple Mac Studiosvia The Verge, 6 hr ago
- SpaceXSI folds X Premium, Grok and Cursor into one five-tier subscriptionOur brief, via TechCrunch, 2 days ago
- Nvidia opens up Super VL, a model for always-on enterprise agentsOur brief, via The Decoder, 8 hr ago
- FLUX.3 Image Klein lands in Diffusers with bounding-box layout controlvia Hugging Face, yesterday