cd /news/artificial-intelligence/daisyrose-27b-pushing-the-frontier-o… · home › topics › artificial-intelligence › article
[ARTICLE · art-172402] src=snipvote.com ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

DaisyRose-27B: Pushing the Frontier of Post-Training Efficiency

RadixArk's DaisyRose-27B doubled Terminal-Bench 4.1 pass@1 from 5.6% to 12.0% using 1,200 curated tasks and 18 days of training on 144 H200 GPUs, according to the model's Hugging Face release post. The Apache-2.0 checkpoint retains Qwen3.8-27B's 256K context window, adds default chain-of-thought reasoning, and is positioned as a drop-in upgrade that runs with SGLang plus DSpark speculative decoding for roughly 2x lower latency than vanilla vLLM. The release indicates targeted reinforcement learning on a small, high-quality dataset can lift long-horizon agent performance without scaling data or compute.

recommendation

When post-training an agent model, invest in a small curated task set rather than scale: 1,200 tasks and 18 days on 144 H200s doubled Terminal-Bench 4.1 pass@1 from 5.6% to 12.0%.

more in playbook: Fine-tuning and data
read1 min views5 publishedNov 19, 2026
DaisyRose-27B: Pushing the Frontier of Post-Training Efficiency
Image: Snipvote (auto-discovered)

Hugging Face

DaisyRose-27B: Pushing the Frontier of Post-Training Efficiency

Which summary reads better? Pick one — models revealed after.Both summaries are AI-generated.

DaisyRose-27B doubles Terminal-Bench 4.1 pass@1 from 5.6% to 12.0% using just 1,200 curated tasks and 144 H200s for 18 days. This means you can now ship agentic workflows with 2x higher success rates on long-horizon tasks without scaling data or compute—just drop in the Apache-2.0 checkpoint and serve it with SGLang + DSpark speculative decoding for ~2x lower latency than vanilla vLLM.

DaisyRose-27B doubles Terminal-Bench 4.1 pass@1 performance from 5.6% to 12.0% with just 1,200 curated tasks and 18 days of training on 144 H200 GPUs. This shows how targeted reinforcement learning on small, high-quality datasets can dramatically improve agent capabilities without massive compute, enabling faster iteration on specialized agent workflows in production. The model retains Qwen3.8-27B's 256K context window and adds default chain-of-thought reasoning, making it a drop-in upgrade for existing deployments needing better long-horizon task performance.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @radixark 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/daisyrose-27b-pushin…] indexed:0 read:1min 2026-11-19 · —