LivePI - Email: leaderboard
Metric: Attack success rate (%; 50 injected Gmail messages, ten techniques by five goals). Source: arxiv.org. Saturation forecast: Estimated already saturated. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 2 |
| 2 | Kimi K2.5 | 6 |
| 3 | GLM-5 | 6 |
| 4 | Gemini 3.1 Pro (Preview) | 12 |
| 5 | GPT-5.3 Codex | 20 |
Interactive version: theaggregate.ai/benchmark?slug=livepi-email · How It Works · Data refreshed daily, snapshot 2026-09-25.