Home/Events/DaisyRose-27B: Pushing the Frontier of Post-Training Efficiency by RadixArk

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

Confirmed
Confidence
90%
Impact: 80%
Updated 2m ago

Consensus Brief

RadixArk has released DaisyRose-27B, a model built on Qwen3.8-27B, which has shown significant improvements in various benchmarks, particularly in Terminal-Bench 4.1 where pass@1 increased from 5.6% to 12.0%. The model was trained using an efficient reinforcement learning framework and features a longer context window and improved task design.

Sourced from
Primary: Hugging Face

What Changed Since Last Update

2m ago

New official source added: Hugging Face published an update on Wed, 18 No ("DaisyRose-27B: Pushing the Frontier of Post-Training Efficiency").

Claim Ledger

4 claims tracked across sources

Confirmed Fact

DaisyRose-27B improves Terminal-Bench 4.1 pass@1 from 5.6% to 12.0%.

Confirmed Fact

The model was trained on long-horizon agent tasks with sessions up to 1M tokens.

Confirmed Fact

DaisyRose-27B was trained with 1,200 curated tasks in 18 days on 144 H200 GPUs.

Confirmed Fact

The training setup achieved a 57% lower training cost compared to previous methods.

Role-Based Impact Analysis