external benchmark
KindBench leaderboard
KindBench Psychological Safety Benchmark. Every model the catalog carries a published KindBench value for, ranked by that value.
Categoryexternal
MeasureJudge-scored behavioral audit with human review
Tasks16 multi-turn scenarios, 72 criteria
DifficultyAdversarial psychological-safety evaluation
Published byKindBench methodology
A behavioral benchmark that tests psychological safety across sixteen adversarial multi-turn conversations covering emotional safety, identity, sycophancy, and value integrity.
No model in the catalog has a published KindBench score.
The benchmark is defined by KindBench methodology, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.