AgentHazard (Claude Code) - System RCE: leaderboard

AgentHazard attack success rate on system remote code execution (RCE) attempts (arbitrary system command execution on the host or container), 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 system remote code execution (RCE) instances (arbitrary system command execution on the host or container), 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

#ModelScoreOverall rank
1Qwen 2.5 72B Instruct18#1117
2Kimi K219#443
3Qwen 2.5 Coder 32B Instruct59#1547
4Qwen 3 VL 235B A22B Instruct65#532
5Kimi K2.571#266
6GLM-4.684#498

Interactive version: theaggregate.ai/benchmark?slug=agenthazard-claude-code-system-rce · How It Works · Data refreshed daily, snapshot 2026-11-21.