AgentLeak: leaderboard
Full-stack privacy leakage benchmark for multi-agent LLM systems, auditing internal channels such as inter-agent messages, shared memory, and tool arguments in addition to final outputs.
Metric: Total Leak (imported). Source: arxiv.org. Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude 3.5 Sonnet | 55.2 | #350 |
| 2 | GPT-4o Mini | 76.3 | #599 |
| 3 | GPT-4o | 77.6 | #343 |
| 4 | Llama 3.3 70B | 89.9 | #579 |
| 5 | Mistral Large | 99.3 | #710 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=agentleak · How It Works · Data refreshed daily, snapshot 2026-10-20.