Skip to content
NewA calmer, faster ZeroHour
StoryModel releaseinfo

RadixArk releases DaisyRose-27B with company-reported Terminal-Bench gains

2 sources · 4 articlesFirst reported Updated ()1 · 1 read
What's new

November 18: Hacker News adds that Eigent AI built the tasks and about 944,000 AgentENV sandboxes were created; the card says scores take the higher of BF16 and FP8.

Merged summary · x-ai/grok-4.7 · rewritten as coverage arrivesSummaries by Vani AI

RadixArk’s first model, DaisyRose-27B, is on Hugging Face with company-reported Terminal-Bench 4.1 gains over Qwen3.8-27B.

RadixArk released DaisyRose-27B, its first model, as Apache-2.0 weights in BF16, FP8 and NVFP4. It is a multimodal reasoning model built on Qwen3.8-27B and trained only with reinforcement learning through RadixArk’s Miles framework, without supervised fine-tuning or distillation. The company says training used about 1,200 long-horizon agent tasks, built with Eigent AI, over 18 days on 144 H200 GPUs, totaling 63,000 GPU-hours, with sessions up to 1 million tokens and about 944,000 AgentENV sandboxes. The weights keep the base architecture, tokenizer, chat template, image understanding and 256K context. RadixArk reports Terminal-Bench 4.1 pass@1 rising from 5.6 to 12.0 and IFBench at 82.4 versus 79.5; published scores take the higher of BF16 and FP8 and are the company’s own figures.

Key facts
  • Apache-2.0 BF16, FP8 and NVFP4 checkpoints are on Hugging Face.
  • Training used about 1,200 tasks and 63,000 GPU-hours on 144 H200s, RadixArk says.
  • Sessions ran up to 1 million tokens; about 944,000 AgentENV sandboxes were created.
  • Terminal-Bench 4.1 pass@1 is reported at 12.0 versus 5.6 for the base model.
  • IFBench is 82.4 versus 79.5; scores take the higher of BF16 and FP8.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

What each outlet adds

beyond the shared facts
  • Hugging Face trending modelsIFBench scores and that published numbers take the higher of BF16 and FP8.
  • Hacker NewsEigent AI tasks, 63,000 GPU-hours, and about 944,000 AgentENV sandboxes.

Coverage

oldest first · one row per article · UTC
  1. · 4d ago Hugging Face trending modelsFirst report

    harness-hub releases a Qwen3.8-27B LoRA for the pi agent

    Authors report Terminal-Bench 2.1 at 55.8% versus 39.5% for the base model, with 62% fewer tool calls.

  2. · 4d ago Hugging Face trending models

    LoRA adapter tunes Qwen3.8-27B for the OpenCode coding agent

    The publisher reports 51.0% on SWE-bench Pro hard 51 with thinking off, above the base model’s high-effort score.

  3. · 2d ago Hugging Face trending models

    RadixArk releases DaisyRose-27B, an RL-only Qwen3.8 model

    Apache-2.0 BF16, FP8 and NVFP4 weights keep the 256K context; Terminal Bench 4.1 pass@1 moves from 5.6 to 12.0.

  4. · 1d ago Hacker News · AI

    RadixArk releases DaisyRose-27B, trained from Qwen3.8-27B

    RadixArk says 1,200 reinforcement-learning tasks raised Terminal-Bench 4.1 pass@1 from 5.6% to 12.0%.