Open sourceNov 18, 2026, 2:54 PM EST

RadixArk releases DaisyRose-27B, an open agent model built on Qwen3.8-27B

RadixArk has released DaisyRose-27B, its first model, post-trained from Qwen3.8-27B with reinforcement learning on long-horizon agent tasks. Checkpoints are published under Apache 2.0 in BF16, FP8 and NVFP4, and the model keeps the base model's 256K-token context window and image understanding. On Terminal-Bench 4.1, pass@1 rose from 5.6% to 12.0%, and RadixArk reports smaller gains on other coding, reasoning and instruction-following benchmarks. The team recommends serving it with SGLang.

Why it matters

An openly licensed agent model that keeps a 256K context window gives teams a self-hostable option for long-running terminal and coding agents, with published benchmark comparisons against the base model it was trained from.

Sources

Written by AIToolMaps from the source above and checked against it sentence by sentence.

Comments

No comments yet