ROGUE-AI - Overall Harm Rate: leaderboard
ROGUE-AI (arXiv:2611.26553v1, Table 4): executable replications of 108 real-world agentic security incidents across 10 sandboxed environments (3 runs per condition per model; 6,439 finished main sessions). Incident-condition harm rate (%); lower is better.
Metric: Incident Harm Rate (%, lower is better). Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked. Updated 21 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Luna | 18 | #131 |
| 2 | Claude Sonnet 4.6 | 19 | #173 |
| 3 | GPT-5.6 Sol | 25 | #37 |
| 4 | Gemini 3.5 Flash | 31 | #106 |
| 5 | DeepSeek V4 Flash | 33 | #267 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=rogue-ai-overall-harm-rate · How It Works · Data refreshed daily, snapshot 2026-11-21.