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

Harmful behavior detection research benchmarks · SOTA2 Research

Harmful behavior detection

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Constructed in-domain dataset (test)

WebAgentGuard-8B

99.2Accuracy

13

Apr 15, 2026

Popular datasets

Constructed in-domain dataset

Follow for updates

Join SOTA2 Contact