Back to Articles DaisyRose-27B: Pushing the Frontier of Post-Training Efficiency Team Article Published November 18, 2026 Upvote 4 Jason Chen jzsc RadixArk Today we are releasing DaisyRose-27B, RadixArk’s first model, built on Qwen3.8-27B and trained with reinforcement learning using Miles. We trained it on long-horizon agent tasks with sessions up to 1M tokens, with just 1,200 curated tasks in 18 days on 144 H200 GPUs. DaisyRose-27B improves Terminal-Bench 4.1 pass@1 from 5.6% to 12.0%. Beyond Terminal-Bench 4.1, it also delivers gains on a variety of other reasoning, instruction following, and coding benchmarks. The checkpoints are available under Apache 2.0: BF16 FP8 NVFP4 The model retains Qwen3.8-27B’s architecture, tokenizer, chat template, image…
DaisyRose-27B: Pushing the Frontier of Post-Training Efficiency
Advertisement