PhoneSafety - Trap Resistance: leaderboard
Metric: Safe-action rate (%; 78 trap-resistance moments). Source: arxiv.org. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 97.4 |
| 2 | Kimi K2.5 | 92.3 |
| 3 | Gemini 3.1 Pro (Preview) | 91 |
| 4 | Seed 2.0 Pro | 89.7 |
Interactive version: theaggregate.ai/benchmark?slug=phonesafety-trap-resistance · How It Works · Data refreshed daily, snapshot 2026-09-25.