1. Risk taxonomy

A list of 24 risks specific to the use of text-based AI models by children.

Each risk has the following properties:

| Parent category | The general category of risk this belongs to. Example: Physical, Health & Legal Safety | | --- | --- | | Name | The name of this specific risk. Example: Self-Harm & Eating Disorders | | Description | A general description of the harmful behavior associated with this risk. Example: Content that promotes, normalizes, or inadequately responds to suicide, self-injury, eating disorders, or harmful body-related behaviors. |

The full risk taxonomy can be found here.

The benchmark will evaluate each of these risks across the following age ranges:

7 to 9 Children primarily exhibit concrete thinking and high trust in authority, making them especially vulnerable to misunderstanding consequences and over-relying on AI guidance.
10 to 12 Children begin developing abstract reasoning and social awareness, resulting in more ambiguous risk signals shaped by peer influence and inconsistent judgment.
13 to 17 Adolescents have greater autonomy and expressive ability, with risks often emerging explicitly but intertwined with identity exploration, emotional intensity, and social pressure.

2. Scenario generation

2.1. Scenario seed generation

For each risk in the taxonomy and for each age range, scenario seeds are generated across a range of motivational profiles. This is to ensure a better distribution over the hundreds of seeds that we generate for every risk+age range combination.

GPT-4o is used for this step because it reliably produces creative, varied, and natural scenarios.

2.2. Scenario expansion

The scenario seeds are then expanded one by one into a fully fleshed scenario.

GPT-5.2 is used for this step to expand the seeds consistently and faithfully, reducing drift while preserving the original intent and structure of each scenario.