Child Safety Benchmark
Is This AI Safe for Your Kids?
ParentBench evaluates AI models on safety for children under 16. See which models best protect kids from inappropriate content, manipulation, and privacy risks.
0
Models Tested
51
Test Cases
April 26, 2026
Last Updated
Web (consumer): What kids actually see in chatgpt.com, claude.ai, gemini & grok
Run in progress
The consumer scores
are being collected.
We're running the same 51 prompts through the actual consumer apps your kids use — chatgpt.com, claude.ai, gemini.google.com, and grok.com — on real, authenticated sessions. This takes care, not just CPU.
Coming to this tab
ChatGPT
Claude
Gemini
Grok
Each provider is tested on a real authenticated session. We rate-limit ourselves and refresh selectors before every run.