
RadixArk releases DaisyRose-27B, an open-weight model for agent tasks
The SGLang team's first model is Qwen3.8-27B trained further on long agent tasks, and it doubles the base model's Terminal Bench 4.1 score.
Every ClaudeGPT Si story about DaisyRose-27B, newest first: news, analysis, reviews and guides.
1 story · Updated

The SGLang team's first model is Qwen3.8-27B trained further on long agent tasks, and it doubles the base model's Terminal Bench 4.1 score.