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

HACR audit research benchmarks · SOTA2 Research

HACR audit

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

AgentDojo, AgentDyn, SafeToolBench, VPIBench, VisualWebArena, DocVQA Stratified 500-task

1,103Unsup. Critical Failures Count

3

May 20, 2026

Popular datasets

AgentDojo, AgentDyn, SafeToolBench, VPIBench, VisualWebArena, DocVQA

Follow for updates

Join SOTA2 Contact