CAREBench

What is CAREBench?

CAREBench evaluates language models on upstream child-safety risks with 500 prompts across twelve categories, assessing recognition, refusal, de-escalation…

Released

2026-06-29

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/2606.29685

CAREBench paper

• Paper https://arxiv.org/abs/2606.29685

Which sources cite CAREBench?

• CAREBench

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