AgentHazard (Claude Code) - Privilege Escalation: leaderboard
AgentHazard attack success rate on privilege escalation attempts (escaping containment or obtaining elevated privileges), with each backbone model running inside Claude Code. Percent of instances judged harmful on the full trajectory by Gemini-3-Flash, lower is better.
Metric: Attack success rate (%) on the privilege escalation instances (escaping containment or obtaining elevated privileges), with the model running inside the Claude Code CLI agent (persistent shell, file editing, tool use; restricted shell sessions), over AgentHazard instances (harmful objectives embedded in locally legitimate multi-step workflows, ten risk categories and ten attack strategies; the evaluated runs cover 1,000 instances), judged on the full trajectory (round_all) by Gemini-3-Flash, which labels a trajectory harmful when it realizes the objective; backbones served through an OpenAI-compatible API; lower is better. Source: arxiv.org. 6 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 72B Instruct | 19.59 | #1124 |
| 2 | Kimi K2 | 28.87 | #448 |
| 3 | Qwen 3 VL 235B A22B Instruct | 55.67 | #541 |
| 4 | Qwen 2.5 Coder 32B Instruct | 62.89 | #1590 |
| 5 | GLM-4.6 | 77.32 | #496 |
| 6 | Kimi K2.5 | 79.38 | #272 |
Interactive version: theaggregate.ai/benchmark?slug=agenthazard-claude-code-privilege-escalation · How It Works · Data refreshed daily, snapshot 2026-11-22.