Multi-Agent System Red-Teaming Suite
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Multi-Agent System Red-Teaming Suite Target: Claude Opus 4.7
61.7CST Score
5
Multi-Agent System Red-Teaming Suite Target: Gemini 3.1 Pro
28.3CST
5
Multi-Agent System Red-Teaming Suite Target: GPT-5.5
55CST
5