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

> Source: <https://www.snipvote.com/story/cmwn879xx0004b5bg3dc7w8qj>
> Published: 2026-11-19 07:43:08.368313+00:00

**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 the playbook "Fine-tuning and data": <https://wpnews.pro/playbooks/training-data>

[Hugging Face](https://huggingface.co/blog/RadixArk/daisyrose-27b-pushing-the-frontier-of-post-trainin)

### 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.
