# New LoRA Adapter Lifts Qwen3.8 Coding Success From 39% to 65%

> Source: <https://www.marktechpost.com/2026/11/18/hugging-face-qwen3-8-27b-pi-adapted-lora/>
> Published: 2026-11-18 16:07:50+00:00

**Recommendation:** For coding-agent work on Qwen3.8-27B, apply the Apache-2.0 pi-adapted LoRA adapter rather than the base model; it lifted SWE-bench Pro hard-51 pass@1 from 39.2% to 64.7%.
More in the playbook "Working with AI coding agents": <https://wpnews.pro/playbooks/coding-agents>

Hugging Face released Qwen3.8-27B-pi-adapted, an Apache-2.0 LoRA adapter trained with reinforcement learning for the pi coding agent. It lifts SWE-bench Pro hard-51 pass@1 from 39.2% to 64.7% and Terminal-Bench 2.1 from 39.5% to 55.8%.

The post [New LoRA Adapter Lifts Qwen3.8 Coding Success From 39% to 65%](https://www.marktechpost.com/2026/11/18/hugging-face-qwen3-8-27b-pi-adapted-lora/) appeared first on [MarkTechPost](https://www.marktechpost.com).
