PhoneSafety - User Confirmation: leaderboard
Metric: Safe-action rate (%; 221 user-confirmation moments). Source: arxiv.org. Saturation forecast: Around December 2026. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Seed 2.0 Pro | 77.8 |
| 2 | Gemini 3.1 Pro (Preview) | 69.7 |
| 3 | Claude Opus 4.6 | 61.5 |
| 4 | Kimi K2.5 | 36.2 |
Interactive version: theaggregate.ai/benchmark?slug=phonesafety-user-confirmation · How It Works · Data refreshed daily, snapshot 2026-09-25.