Congrats to the Kaggle Benchmarking Challenge Winners!

Automated excerpt

So they measured the real numbers themself across four versions of each language, then asked 12 models the same questions. Plenty of models produced code that ran fine while stating nothing had changed between versions. The models flagged a problem almost every time, but frequently for the wrong reason, including spotting SQL injection in code that never touches a database.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.