List your company

ResearchFormerly WizWand

Tool-use behavioral profiling

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

Malicious regime n=30

50Metric A

12

Apr 15, 2026

Gray regime n=30

93A Score

12

Apr 15, 2026

Dilemma regime n=30

87A Score

12

Apr 15, 2026

Control regime n=10

100Metric A

12

Apr 15, 2026