Skip to content

Qwen3.8-27B-pi-adapted Targets the pi Coding Agent

clem 🤗 · X· @ClementDelangue·· 11 hours agoPicks

29K views · 876 likes · 112 reposts (at collection)

Original

What happened

Clément Delangue introduced Qwen3.8-27B-pi-adapted, a Qwen model adapted for the pi coding agent with reinforcement learning and a LoRA adapter. The post reports pass@1 increases from 29.4% to 62.7% on SWE-bench Pro (Hard 51) and from 39.5% to 55.8% on Terminal-Bench 2.1, with 55–62% fewer tool calls per task. Open weights and the methodology are linked.

Why it matters

The adapted model improves pass@1 on SWE-bench Pro (Hard 51) and Terminal-Bench 2.1 while using 55–62% fewer tool calls per task, suggesting coding agents can benefit from models tuned to their specific tools.

Article

Introducing Qwen3.8-27B-pi-adapted 🤗

We adapted Qwen's model specifically for the pi coding agent using reinforcement learning and a LoRA adapter.

The results, measured as pass@1:
🚀 SWE-bench Pro (Hard 51): 29.4% → 62.7%
💻 Terminal-Bench 2.1: 39.5% → 55.8%
⚡ 55–62% fewer tool calls per task

This is the power of open models: you can adapt them to YOUR tools and YOUR use cases. Let’s build! 💛

Open weights: huggingface.co/harness-hub/Qw…
Methodology: huggingface.co/blog/harness-h…

The story so far

Harness Hub has released Qwen3.8-27B-pi-adapted, an iteration of the Qwen model optimized for the pi coding agent using reinforcement learning and a LoRA adapter. The model's weights and methodology are available publicly. Clément Delangue reported that this adaptation improves performance across coding benchmarks. On SWE-bench Pro (Hard 51), pass@1 rates increased from 29.4% to 62.7%, while scores on Terminal-Bench 2.1 rose from 39.5% to 55.8%. Additionally, the model reportedly requires 55–62% fewer tool calls per task.

Read next

See the full storyHarness Hub Releases Qwen3.8-27B-pi-adapted for Improved Coding Agent Performance
This story is in 11/18 AI DailyRead the whole issue