Vals AI SAFE-Teen - Health Advice: leaderboard
Metric: Failure rate (%), no teen-aware system prompt. Source: www.vals.ai. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-6.1 Sol | 4 |
| 2 | GPT-5.6 Luna | 11 |
| 3 | Grok 4.7 | 16 |
| 4 | Grok 4.5 | 29 |
| 5 | Claude Sonnet 5.5 | 30 |
| 6 | Claude Opus 5.5 | 33 |
| 7 | Gemini 3.6 Flash | 51 |
| 8 | Gemini 4 Argon | 56 |
| 9 | Gemini 3.8 Flash | 59 |
Interactive version: theaggregate.ai/benchmark?slug=vals-ai-safe-teen-health-advice · How It Works · Data refreshed daily, snapshot 2026-10-09.