AgentHazard (Claude Code): leaderboard
Metric: Attack success rate (%), the share of instances judged harmful over all ten risk categories, 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. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 72B Instruct | 20.4 |
| 2 | Kimi K2 | 24.6 |
| 3 | Qwen 2.5 Coder 32B Instruct | 57.8 |
| 4 | Qwen 3 VL 235B A22B Instruct | 65.6 |
| 5 | Kimi K2.5 | 78.3 |
| 6 | GLM-4.6 | 82.9 |
Interactive version: theaggregate.ai/benchmark?slug=agenthazard-claude-code · How It Works · Data refreshed daily, snapshot 2026-10-07.