KIDBench

What is KIDBench?

KIDBench evaluates child-facing safety of LLMs for ages 7-11 using realistic queries and multi-turn child-actor simulations, scored by an LLM-as-a-Judge rubric.

Released

2026-05-25

Evaluates

General AI, Safety, Safety & Trustworthiness

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2605.25510

KIDBench paper

• Paper https://arxiv.org/abs/2605.25510

Which sources cite KIDBench?

• KIDBench

Related General AI, Safety, Safety & Trustworthiness benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveSciBench
• ActiveVision