Nous Research Releases Arete-27B that Cuts Qwen3.8-27B Propaganda From 22% to 0.9%
Nous Research released Arete-27B, an Apache 2.0 fine-tune of Qwen3.8-27B. On Nous’s 803-prompt eval, propaganda answers fell from 22% to 0.9% while Hermes Bench stayed flat at 65.60%.
In brief
- What: Nous Research Releases Arete-27B that Cuts Qwen3.8-27B Propaganda From 22% to 0.9%
- When: November 8, 2026 at 07:45
- Source: MarkTechPost (media)
- Topic: Models
Prepared by Ilya Tarasov’s Tarasov Code newsroom based on a report by MarkTechPost.
