
- Who
- RadixArk
- What
- releases DaisyRose-27B, its first model, with Apache 2.0 checkpoints
- Quote
Today we are releasing DaisyRose-27B , RadixArk’s first model, built on Qwen3.8-27B and trained with reinforcement learning using Miles .
What happened
RadixArk released DaisyRose-27B, its first model, built on Qwen3.8-27B and trained with reinforcement learning using Miles. Trained on 1,200 curated agent tasks over 18 days on 144 H200 GPUs, it raises Terminal-Bench 4.1 pass@1 from 5.6% to 12.0% and scores higher than Qwen3.8-27B on every benchmark listed. Checkpoints are available under Apache 2.0.
Why it matters
DaisyRose-27B raises Terminal-Bench 4.1 pass@1 from 5.6% to 12.0% over Qwen3.8-27B after training on 1,200 curated tasks, while its Apache 2.0 checkpoints make the model available for others to run.
The story so far
RadixArk has released DaisyRose-27B, its first AI model, which utilizes reinforcement learning to improve agent task performance over its base, Qwen3.8-27B. The company stated that the model was trained using a method called Miles on 1,200 curated agent tasks over 18 days, utilizing 144 H200 GPUs. According to RadixArk, the model outperforms the base Qwen3.8-27B on every listed benchmark. Specifically, the company reported that DaisyRose-27B increased the Terminal-Bench 4.1 pass@1 rate from 5.6% to 12.0%. The model's checkpoints are available for public use under the Apache 2.0 license, supporting BF16, FP8, and NVFP4 formats.
