RadixArk Ships DaisyRose-27B, a 27B Agentic Coding Model Trained With Reinforcement Learning Only
MarkTechPost ·
Summary
RadixArk released DaisyRose-27B, an Apache 2.0 agentic coding model post-trained from Qwen3.8-27B with reinforcement learning only. It more than doubles Terminal Bench 4.1 pass@1 to 12.0 and runs on a single GPU. The post RadixArk Ships DaisyRose-27B, a 27B Agentic Coding Model T
- Source
- MarkTechPost
- Published (IST)
Original reporting belongs to MarkTechPost. DEEKOYA links the headline and a short excerpt only; we do not republish the full article.
Explore more: Today in AI · Research papers · AI tools · Learn AI
Related stories
- Phys.org
Anthropic researcher says Claude solved math's greatest riddle
Phys.orgModels
The Guardian AI
Anthropic hits over $1 trillion: is it worth the hype? - The Latest
The AI firm and Claude chatbot maker Anthropic has made a historic stock market debut, with a peak valuation of $1.3tn…
The Guardian AIFunding
SiliconANGLE AI
Own, don t rent: Why agentic AI is pulling cloud computing back on-prem
Agentic AI is reviving an argument over renting versus owning compute, and the model plane — the layer that decides…
SiliconANGLE AIModels
- Nextgov/FCW
House members launch bipartisan AI safety and innovation caucus
Nextgov/FCWsafety
Unite.AI
Andrew Nassar, CTO of IC Realtime – Interview Series
Andrew Nassar is CTO of IC Realtime, where he has helped guide the company through shifts from analog cameras to…
Unite.AIBusiness
Unite.AI
BoodleBox Joins Montana’s AI Procurement Program
BoodleBox says Montana has approved it as a vendor in the state’s Master AI Products and Services procurement program.…
Unite.AIAI
Who reported “RadixArk Ships DaisyRose-27B, a 27B Agentic Coding Model Trained With…”?
MarkTechPost, on 20 Nov 2026. The full article is at the source link on this page.
Comments
No comments yet. Share your own experience below.
Visitor posts are moderated before they appear and are the opinion of their authors, not DEEKOYA AI. Names are not verified. See our privacy policy.