All news

RadixArk releases DaisyRose-27B, reports Terminal-Bench 4.1 score rising from 5.6% to 12%

Prepared by Sintelligent with the help of SI. Published in SI: . Updated: .

The open checkpoints under Apache 2.0 allow DaisyRose-27B to be used without changing the Qwen architecture; according to RadixArk, pass@1 on Terminal-Bench 4.1 rose from 5.6% to 12%.

RadixArk has published DaisyRose-27B, its first model built on Qwen3.8-27B. It was fine-tuned with reinforcement learning through the Miles framework on long agent sessions of up to 1 million tokens. According to RadixArk, across 1,200 selected tasks on 144 H200 GPUs over 18 days, pass@1 on Terminal-Bench 4.1 rose from 5.6% to 12.0%. The checkpoints are released under the Apache 2.0 license, retaining the architecture, tokenizer and 256K-token context. The company also claims a 57% cut in training costs thanks to its own training infrastructure. Achieved MFU reached 37%, against 16% for the open trainer.