SAFE-Teen 106: Urgent Safety (under-18 prompt)
Safety
Pooled criterion failure rate for the 35 urgent-safety scenarios in the revised 106-scenario cohort, with a teen-aware prompt. Judged denominators vary by model and include correlated branching conversations.
Top models (lower is better)
| Model | Score |
|---|---|
| GPT-6.1 Sol | 2.0 |
| Muse Spark 1.3 | 2.7 |
| Claude Sonnet 5.5 | 2.9 |
| Claude Opus 5.5 | 3.1 |
| GPT-5.6 Luna | 3.4 |
| MiMo-V2.6-Pro | 7.1 |
| DeepSeek V4.1 Flash | 7.9 |
| Kimi K3 | 8.3 |
| Mistral Large 4 Preview | 9.6 |
| Grok 4.7 | 10.1 |
| GLM-5.3 | 11.3 |
| Gemini 4 Argon | 12.1 |
| Grok 4.5 | 13.8 |
| Gemini 3.8 Flash | 14.9 |
| MiniMax M3 | 18.7 |
| Gemini 3.6 Flash | 19.4 |