Putting models to the secure coding test: Plan vs default mode
Datadog Security Labs tested Sonnet 5, Composer 2.5, and GPT 5.5 to see if plan mode yields more secure code than default mode.
Datadog Security Labs evaluated whether plan mode produces measurably more secure code than default mode. The test covered three frontier coding models: Sonnet 5, Composer 2.5, and GPT 5.5. The results inform how engineering teams should configure AI coding assistants to reduce insecure code. This is an AI security evaluation, not an incident report.
- Plan mode vs default mode compared on security
- Models tested: Sonnet 5, Composer 2.5, GPT 5.5
- Focus is measurable security of generated code
- Vendors
- Datadog
- Products
- Datadog Security Labs
- Organizations
- Datadog
- AI models
- Sonnet 5Composer 2.5GPT 5.5
From the original article
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.
securitylabs.datadoghq.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.