Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Illicit task completion research benchmarks · SOTA2 Research

Illicit task completion

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

AgentHarm English prompts

72.7AgentHarm Score (AHS)

20

Feb 26, 2026

Popular datasets

Follow for updates

Join SOTA2 Contact