Putting models to the secure coding test: Plan vs default mode
We tested Sonnet 5, Composer 2.5, and GPT 5.5 in plan mode and default mode to see whether plan mode produces measurably more secure code.
Summary from Datadog Security Labs.
We tested Sonnet 5, Composer 2.5, and GPT 5.5 in plan mode and default mode to see whether plan mode produces measurably more secure code.
Summary from Datadog Security Labs.