Same SWE-Bench task: base model burns 100-step budget, adapter passes in 35 calls

yb2698 · x · 2026-11-19

On a real SWE-Bench Pro task, the base model broke the test file and ran out of its 100-step budget, while the Hermes adapter version fixed the bug, verified the task's scenarios and passed in 35 tool calls.

Related event: NousResearch Releases Hermes Adapter for Qwen3.8-27B, Boosting SWE-Bench Pro to 43.1%(10 posts)→

Original post →

More from coding & agent

coding & agent channel →