RadixArk Releases DaisyRose-27B, Terminal-Bench 4.1…
AI summary
RadixArk has released DaisyRose-27B, based on Qwen3.8-27B, raising its Terminal-Bench 4.1 pass@1 score from 5.6% to 12.0%. The model was trained using the Miles reinforcement learning framework on approximately 1,200 curated tasks with 144 H200 GPUs for 18 days, with long-horizon agent sessions reaching up to 1M tokens. RadixArk has also made BF16, FP8, and NVFP4 checkpoints available for download and further development.
Why read this
AI score 66
The release details data filtering, asynchronous training, and sandbox scale for long-horizon agent post-training, offering an engineering reference for improving training efficiency under limited compute resources.
Topics
Body
Only a summary is authorized here. Continue at the validated source link.
AI Trends