AgentS4D (Hermes Agent): leaderboard

Metric: Conditional attack success rate (%, cASR): unsafe runs over runs that were unsafe, explicitly defended, or safe after confirmed payload contact, over the 328 risk-injected cases run once in the Hermes agent (0.14.0) harness; lower is better. Source: arxiv.org. Saturation forecast: Around 2030. 5 models tracked.

Top models

#ModelScore
1Qwen 3.7 Plus58.13
2MiniMax-M364.69
3GPT-5.570.67
4Gemini 3.1 Pro (Preview)90.28
5DeepSeek V4 Pro91.02

Interactive version: theaggregate.ai/benchmark?slug=agents4d-hermes-agent · How It Works · Data refreshed daily, snapshot 2026-09-29.