Coding agent rankings change when bug fixing becomes a back-and-forth with users
UserSWE tests coding agents on fixing repository bugs over several turns with a simulated user who reveals details gradually, with tests run after every turn. Across eleven agents on 72 tasks from 42 repositories, the leader changed with the number of turns allowed. Claude Fable 5.1 solved the most tasks in one turn, GPT-6-Astra the most by the eighth, and Claude Opus 5 led at most budgets in between.