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

Trajectory-level safety evaluation research benchmarks · SOTA2 Research

Trajectory-level safety evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

95.2Accuracy

32

Jun 2, 2026

AgentDoG-Qwen3-4B

0.928Accuracy

20

Feb 26, 2026

ASSE-Safety (test)

AgentDoG-Llama3.1-8B

81.1Accuracy

20

Feb 26, 2026

Popular datasets

R-judge ASSE-Safety ATBench

Follow for updates

Join SOTA2 Contact