OpenCode adapter boosts local Qwen3.8-27B: SWE-Bench 35.3%→51%, 6-8x fewer tokens
yb2698 · x · 2026-11-18
Following the Pi adapter, the community released an OpenCode harness adapter for Qwen3.8-27B, trained on v2 data and ready for local inference. SWE-Bench Pro (Hard 51) pass@1 jumps 35.3%→51.0% (47.1%→54.9% in xhigh thinking); Terminal Bench 2.1 47.0→53.0 (55.4→56.6 xhigh). Tasks generate 6-8x fewer tokens. Full training recipe coming soon for applying it to your own tasks.
Related event: Community OpenCode Adapter Boosts Qwen3.8-27B on SWE-Bench by 16 Points(2 posts)→
More from coding & agent
- Telegram preps built-in AI agent "Dictator" on Nous Research's Hermes for 1B+ users — testingcatalog · 2026-11-18
- Google rolls out Antigravity Orchestrator: dynamic in-task model switching, 24% less quota — rseroter · 2026-11-18
- Using Google Antigravity agent swarms to analyze the November 2026 Core Update — gaganghotra_ · 2026-11-18
- Dev builds MCP skills tool so Claude, Cursor and Copilot share one set of instructions — EntrepreneurOk5764 · 2026-11-18
- 12 indie AI mini-game devs share real revenue: top Steam title made $42K RMB in 49 days — sujingshen · 2026-11-18
- Oracle agent memory cuts input tokens ~10x at turn 80 vs full chat replay — bibryam · 2026-11-18