5-person Ricursive releases from-scratch Ripple-65B, claims US open-weight agentic coding SOTA
DZhang50 · x · 2026-11-05
Ricursive released Ripple-65B Preview, a 65B dense LLM pretrained from scratch, claiming a new state-of-the-art for U.S. open-weight models on agentic coding — beating much larger Muse Spark Open-816B, Beam-501B, Inkling-975B, and Nemotron 3 Ultra-550B. Per the team: 5 people, 80.5 on TerminalBench 2.1, 16x more compute-efficient pretraining, runs on a MacBook Pro.
More from Models
- Qwen-powered uni-robot-agent hits 31.39 on RoboDojo, beating GPT-6 Astra at 1/19.5 the cost — dotey · 2026-11-05
- Claude halts mid-task to interrogate an 'A3.5' arm it never defined — unusual LLM self-audit — teortaxesTex · 2026-11-05
- Macrocosmos launches IOTA Decide 4B, its first open-weights model trained on 16 globally distributed GPUs — markjeffrey · 2026-11-05
- Leaked-style chart suggests OpenAI internal model far outperforms GPT-6 Astra on BenchCAD 2.0 — haider1 · 2026-11-05
- Nat Lambert: post-training and post-post-training are really different arts — natolambert · 2026-11-05
- ChatGPT desktop app crashes so often users restart it five times a day — koltregaskes · 2026-11-05