---
format: "aidr-story-markdown/v1"
id: "565be2acc4190b332fe03272d48b44706b11514e510e4f5504aae4a63209dc26"
canonical_url: "https://aidr.today/565be2ac?lang=en"
title: "OpenCode Adapter Raises Qwen3.8-27B Coding Score to 51% and Cuts Tokens 6-8x"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-18T13:37:30.000Z"
category: "Tools"
topics: ["coding","devtools","open-source"]
source_urls: ["https://marketbrief.now/ai/opencode-adapter-raises-qwen38-27b-coding-score-to-51percent-and-cuts-to-e4ce7c3c","https://huggingnews.com/ai/opencode-adapter-raises-qwen38-27b-coding-score-to-51percent-and-cuts-to-e4ce7c3c"]
summary: "A new LoRA adapter for Alibaba's Qwen3.8-27B model optimized for the OpenCode v2 harness increased the model's pass@1 score on the SWE-Bench Pro (Hard 51 subset) from 35.3% to 51.0%. The adapter also raised the model's Terminal-Bench 2.1 pass@1 score from 47.0% to 53.0% and reduced the number of generated tokens per task by 6 to 8 times. The release follows a similar adapter for the Pi coding agent released Nov. 17, which more than doubled the model's SWE-bench Pro score. The developers aim to adapt models to specific software interfaces, or harnesses, rather than adjusting the interfaces to fit the models. A full reproducible recipe for creating these harness-specific adapters will be published this Friday."
---

# OpenCode Adapter Raises Qwen3\.8\-27B Coding Score to 51% and Cuts Tokens 6\-8x

> [Open the canonical story](<https://aidr.today/565be2ac?lang=en>)

**Published:** 2026-11-18T13:37:30.000Z
**Category:** Tools
**Topics:** coding, devtools, open\-source

## Summary

A new LoRA adapter for Alibaba's Qwen3\.8\-27B model optimized for the OpenCode v2 harness increased the model's pass@1 score on the SWE\-Bench Pro \(Hard 51 subset\) from 35\.3% to 51\.0%\. The adapter also raised the model's Terminal\-Bench 2\.1 pass@1 score from 47\.0% to 53\.0% and reduced the number of generated tokens per task by 6 to 8 times\. The release follows a similar adapter for the Pi coding agent released Nov\. 17, which more than doubled the model's SWE\-bench Pro score\. The developers aim to adapt models to specific software interfaces, or harnesses, rather than adjusting the interfaces to fit the models\. A full reproducible recipe for creating these harness\-specific adapters will be published this Friday\.

## Sources

- [Story source](<https://marketbrief.now/ai/opencode-adapter-raises-qwen38-27b-coding-score-to-51percent-and-cuts-to-e4ce7c3c>)
- [Story source](<https://huggingnews.com/ai/opencode-adapter-raises-qwen38-27b-coding-score-to-51percent-and-cuts-to-e4ce7c3c>)

