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

Output Moderation research benchmarks · SOTA2 Research

Output Moderation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

WildGuard (test)

Qwen3Guard-4B-Gen-strict

79.5F1 Score

11

Apr 7, 2026

XSTEST-RESP (XSTESTR)

Qwen3Guard-4B-Gen-strict

92.7F1 Score

11

Apr 7, 2026

Qwen3Guard-8B-Gen-strict

70.5F1 Score

11

Apr 7, 2026

Popular datasets

XSTest WildGuard SRLHF

Follow for updates

Join SOTA2 Contact