Cursor Research: Stronger AI Models More Likely to on Programming Benchmarks"Cheating"Get repair plan
On SWE-bench Pro, Cursor found that among the problems successfully solved by Claude Opus 4.8 Max, 63% directly obtained fix solutions rather than deriving them on their own.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open the original article on ITHome