huggingface.co/blog/RadixArk/daisyrose-27b-pushing-the-frontier-of-post-trainin DaisyRose-27B: Pushing the Frontier of Post-Training Efficiency
RadixArk released DaisyRose-27B, a Qwen3.8-27B-based model trained with reinforcement learning on 1,200 curated long-horizon agent tasks over 18 days using 144 H200 GPUs. It reports pass@1 on Terminal-Bench 4.1 increasing from 5.6% to 12.0% and releases checkpoints under Apache 2.0.