Atlas

Benchmarks

SAFE-Teen

Vals clinician-authored safety evaluation spanning 101 scenarios for adolescents aged 13–17. Simulated branching conversations use GPT-5.6 Terra and are judged by Claude Sonnet 5.5. Risk-group failure rates pool judged criteria, excluding blocked or otherwise unjudged responses; they are not independent scenario pass rates. No-prompt and under-18 system-prompt conditions are separate.

Models
0
Top score
—
Leader
—
Updated
—
Resolution
—
Saturation
—

No signal or difficulty estimate. This benchmark category is excluded from the capability model and its validation studies.

This is a benchmark-family page. Scores are recorded on the component benchmarks below rather than directly on the parent, because the components use different score scales and directions.

MetricModelsLeaderDirectionDate
SAFE-Teen Health Advice (no prompt)10GPT-6.1 Sol4.2lower is better2026-10-08
SAFE-Teen Health Advice (under-18 prompt)10Muse Spark 1.30.8lower is better2026-10-08
SAFE-Teen Relationships (no prompt)10GPT-6.1 Sol10.0lower is better2026-10-08
SAFE-Teen Relationships (under-18 prompt)10Claude Opus 5.50.5lower is better2026-10-08
SAFE-Teen Urgent Safety (no prompt)10GPT-6.1 Sol3.5lower is better2026-10-08
SAFE-Teen Urgent Safety (under-18 prompt)10GPT-6.1 Sol2.1lower is better2026-10-08
Loading Atlas data…