LoRA adapter tunes Qwen3.8-27B for the OpenCode coding agent
The publisher reports 51.0% on SWE-bench Pro hard 51 with thinking off, above the base model’s high-effort score.
48
The publisher reports 51.0% on SWE-bench Pro hard 51 with thinking off, above the base model’s high-effort score.
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.
Today 1K readers · 1.1K views · 101 reads · all time 211K views