Reflection releases first model Beam: 501B-A23B open MoE trained on 10K GB300s
brandondamos · x · 2026-10-06
Reflection.AI has released its first model, Beam:
- A 501B-A23B text-only MoE model, openly released under Apache 2.0, described as competitive.
- The team spent a year scaling a production RL/OPD stack and completed a stable run on 10,000 GB300 GPUs.
- Training produced over 100M rollouts across 1M tasks, significantly improving final performance.
More from Models
- Jeremy Howard: Google shipped the best model ever made; OpenAI its worst, same day — hugobowne · 2026-11-20
- Polymarket puts 83% odds on Google having the best AI model by year-end — Polymarket · 2026-11-20
- One year later, model naming is still a mess: the gpt-5.1-codex-max anniversary — heyneighbor · 2026-11-20
- Developer slams Grok models as 'garbage', shares coding agent's repetitive trial-and-error log — feregri_no · 2026-11-20
- Drex Router cuts small-game build cost to $1.26 vs $13.44 on Claude Opus alone — testingcatalog · 2026-11-20
- OpenAI slammed for AI slop: 'Just hire photographers to RLHF imagegen for a day' — flowersslop · 2026-11-20