Benchmarks
347 sources · 1,258 models × 3,038 benchmarks · 158,912 scoresVals' revised SAFE-Teen scoring of the 106-scenario cohort: for each model, prompt condition, scenario and safety check, the worst rating across that scenario's conversation branches is kept. Group failure rates pool these worst-case ratings, excluding blocked or unjudged responses, with separate no-prompt and under-18-prompt conditions. Each scenario contributes at most one rating per check, so judged denominators are far smaller than under the earlier per-conversation scoring, which remains separate.
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.
| Metric | Models | Leader | Direction | Date |
|---|---|---|---|---|
| SAFE-Teen 106 worst branch: Health Advice (no prompt) | 16 | GPT-6.1 Sol8.8 | lower is better | 2026-10-13 |
| SAFE-Teen 106 worst branch: Health Advice (under-18 prompt) | 16 | Muse Spark 1.34.5 | lower is better | 2026-10-13 |
| SAFE-Teen 106 worst branch: Relationships (no prompt) | 16 | GPT-6.1 Sol19.1 | lower is better | 2026-10-13 |
| SAFE-Teen 106 worst branch: Relationships (under-18 prompt) | 16 | Claude Opus 5.52.4 | lower is better | 2026-10-13 |
| SAFE-Teen 106 worst branch: Urgent Safety (no prompt) | 16 | GPT-6.1 Sol15.4 | lower is better | 2026-10-13 |
| SAFE-Teen 106 worst branch: Urgent Safety (under-18 prompt) | 16 | Claude Opus 5.510.5 | lower is better | 2026-10-13 |