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)→

Original post →

More from coding & agent

coding & agent channel →