CWE-bench v1 leaderboard

CWE-bench v1 is an agentic benchmark published by CWE-bench v1 leaderboard and methodology. Defensive vulnerability patching on 120 held-out tasks spanning 73 weakness types. Its evaluation set is described by the source as audit and patch held-out C/C++, Go, Java, TypeScript/JavaScript, Python, and Rust repositories. The source rates its difficulty as frontier agent evaluation.

Each model's result is published by CWE-bench v1 leaderboard and methodology as pass@1. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 11 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.