Nous releases Hermes adapter for Qwen3.8-27B: +14 points on two agent benchmarks
yb2698 · x · 2026-11-19
Nous Research announced a Hermes LoRA adapter for Alibaba's Qwen3.8-27B, trained with RL inside the Hermes Agent environment for more efficient and accurate agentic development.
- SWE-Bench Pro (hard 51) pass@1: 29.4% → 43.1%; with xhigh thinking: 45.1% → 51.0%
- Terminal-Bench 2.1 pass@1: 44.7% → 58.8%; with xhigh thinking: 58.8% → 57.6% (slightly worse)
The headline: with thinking off it matches the base model at xhigh reasoning while using 3.5–4.4× fewer tokens. Released openly on Hugging Face under apache-2.0.
More from coding & agent
- Ex-DeepSeek core member open-sources Linger, a personal AI agent that runs local models on your PC — FellMentKE · 2026-11-19
- Apple opens iWork to external LLMs: Pages, Numbers, Keynote gain MCP support — dsp_ · 2026-11-19
- Hermes adapter gets GGUF release: matches xhigh thinking at a quarter of the tokens — yb2698 · 2026-11-19
- Gym's chatbot invented a free membership-pause policy; team shares its guardrail lessons — Fit_Satisfaction541 · 2026-11-19
- Anthropic engineer shares free 30-minute Claude Code SDK + GitHub Actions automation walkthrough — aftahi_ai · 2026-11-19
- Snowflake Labs open-sources Cortex AI 101 notebook calling OpenAI models via SQL — adnan_hashmi · 2026-11-19