AgentHazard (Claude Code) - Persistence Establishment: leaderboard
AgentHazard attack success rate on persistence establishment attempts (backdoors, SSH keys, startup scripts or scheduled jobs that keep long-term access), 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 persistence establishment instances (backdoors, SSH keys, startup scripts or scheduled jobs that keep long-term access), 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 | 22.22 | #1117 |
| 2 | Kimi K2 | 30.3 | #443 |
| 3 | Qwen 2.5 Coder 32B Instruct | 59.6 | #1547 |
| 4 | Qwen 3 VL 235B A22B Instruct | 68.69 | #532 |
| 5 | Kimi K2.5 | 80.81 | #266 |
| 6 | GLM-4.6 | 89.9 | #498 |
Interactive version: theaggregate.ai/benchmark?slug=agenthazard-claude-code-persistence-establishment · How It Works · Data refreshed daily, snapshot 2026-11-21.