AI Trends

Trending story Continuously updated

RadixArk Uses Miles to Train DaisyRose-27B

2 reports2 story updatesUpdated Nov 19 03:54

Understand this story

Story summary

The English summary is being updated. See the reporting timeline below.

Latest development · Report

DaisyRose-27B Released, Improving Agent Post-Training Efficiency and Benchmark Performance

Developments

1 confirmed developments

  1. English translation is being prepared.

    Source:Hugging Face

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Nov 19

  1. Hugging FaceFirst-partySelected

    DaisyRose-27B Released, Improving Agent Post-Training Efficiency and Benchmark Performance

    DaisyRose-27B has been released, outperforming the original Qwen3.8-27B on every benchmark listed in the article, including an increase in pass@1 on Terminal Bench 4.1 from 5.6% to 12.0%. The model was trained on approximately 1,200 curated tasks, with the release training run lasting several weeks on 144 H200 GPUs and consuming a total of 63,000 GPU-hours. Its in-house backend achieved 37% MFU, reduced GPU time by 57% compared with open-source trainers, and increased end-to-end training speed by approximately 2×.

Nov 18

  1. Popular on Hacker News

    RadixArk Releases DaisyRose-27B, Terminal-Bench 4.1…

    RadixArk has released DaisyRose-27B, based on Qwen3.8-27B, raising its Terminal-Bench 4.1 pass@1 score from 5.6% to 12.0%. The model was trained using the Miles reinforcement learning framework on approximately 1,200 curated tasks with 144 H200 GPUs for 18 days, with long-horizon agent sessions reaching up to 1M tokens. RadixArk has also made BF16, FP8, and NVFP4 checkpoints available for download and further development.

Heat trend for this story

Not enough continuous observations to show a trend.

Related stories

  1. Related storiesSGLang natively supports and powers the Beam production API
  2. Related storiesMeta releases open-weight model Muse Spark Open
  3. Related storiesEnglish translation is being prepared.
  4. Related storiesXiaomi MiMo Releases MiMo-V2.6 Pro and Flash