SWE Atlas - Codebase QnA
Codebase comprehension, testing, and refactoring.
124Public tasks
52.7%Highest score
The SWE Atlas - Codebase QnA leaderboard
Benchmarks coding agents beyond issue resolution across Codebase Q&A (124 tasks), test writing (90), and refactoring (70), combining programmatic validation with rubric-based software-quality scoring (maintainability, abstractions, hygiene). Uses under-specified, agentic task formulations.