RadixArk releases DaisyRose-27B model
What happened
At 03:39 on November 19, Hacker News' front page reported that RadixArk released the DaisyRose-27B model. The model is built on Qwen3.8-27B with reinforcement learning. The reported evaluation shows pass@1 on Terminal-Bench 4.1 rising from 5.6% to 12.0%, a gain of 6.4 percentage points. The coverage so far covers only the release and these benchmark results, with no later updates.
Written by AI from the coverage · updated 2 days ago
Coverage
Follow the reports to see the story from different sides.
- Hacker News front pageDaisyRose-27B
RadixArk 发布 DaisyRose-27B,基于 Qwen3.8-27B 进行强化学习,将 Terminal-Bench 4.1 的 pass@1 从 5.6% 提升至 12.0%。
Heat over time
Heat now 3·Comparable peak 10(Nov 19 05:00)·Comparable change over 24 hours -49%
The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.