CIPHER - Secure Prompts: leaderboard
Metric: Vulnerability rate (% of 750 generations with at least one vulnerability; 150 secure-guidance prompts x 5 samples; GPT-4o judge, majority of several passes, CIPHER taxonomy). Source: arxiv.org. Saturation forecast: Around 2034. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.1 | 64 |
| 2 | CodeLlama-7B-Instruct-hf | 72.8 |
| 3 | GPT-5.1 Codex | 73.7 |
| 4 | Gemini 2.5 Flash | 78.5 |
| 5 | Claude Sonnet 4.5 | 88.2 |
Interactive version: theaggregate.ai/benchmark?slug=cipher-secure-prompts · How It Works · Data refreshed daily, snapshot 2026-09-25.