HOT RADAR
llmHEAT 21.3°

AI CURATED HOT STORY · 11/19/2026

RadixArk Open-Sources 27B Agent Model Doubling Terminal Task Success Rate

2 reports archived2 independent sourcesupdated 11/19/2026, 03:54:56
Synthesis & Latest Updates
2 Sources Cross-Validated

RadixArk has released DaisyRose-27B, its first open-source agent model built on Qwen3.8-27B and post-trained with reinforcement learning on long-horizon agent tasks. The model was trained on only 1,200 curated tasks using 144 H200 GPUs for 18 days, and it doubles the pass@1 on Terminal-Bench 4.1 from 5.6% to 12.0%, while supporting up to 1M token context per session.

Technically, DaisyRose-27B scores 75.5 on Terminal-Bench 2.1 and 46.2 on DeepSWE v1.1, with broad gains across reasoning, instruction-following, and coding benchmarks. RadixArk has open-sourced three weight formats—BF16, FP8, and NVFP4—under the Apache 2.0 license, facilitating deployment and further development across different hardware setups.

The release demonstrates that a high-quality small task set combined with efficient training can significantly enhance an agent's long-horizon capabilities under limited compute, offering the open-source community a reproducible training paradigm and potentially accelerating terminal automation and software engineering agents.

LATEST/After RadixArk released DaisyRose-27B on Hugging Face, the community highlighted its doubling of terminal task success rate with only 1,200 tasks and 144 H200 GPUs over 18 days, along with three open weight formats, sparking discussions on agent training efficiency.

Hourly heat curve

23 fully observed hours
Now
21.3
Peak
34.604:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 2 reports · Latest first