List your company

Top-N Saturation on Tool selection benchmark

20Certified Upper Bound (pu)None
1925.7532.539.25Oct 5, 2025

Evaluation results

MethodLinks
NoneMitigation=None, Selector model=Llama-3.1, Generator model=Gemma-32025.1020
Anomaly mon.Mitigation=Anomaly mon., Selector model=Llama-3.1, Generator model=Gemma-32025.1024
StruQMitigation=StruQ, Selector model=Llama-3.1, Generator model=Gemma-32025.1027
SecAlignMitigation=SecAlign, Selector model=Llama-3.1, Generator model=Gemma-32025.1033
PerplexityMitigation=Perplexity, Selector model=Llama-3.1, Generator model=Gemma-32025.1039
Defended retr.Mitigation=Defended retr., Selector model=Llama-3.1, Generator model=Gemma-32025.1045