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

Safety research benchmarks – Page 2 · SOTA2 Research

Safety

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

91.39F1 Score

7

Feb 26, 2026

Harmful Questions

STAR1-R1-Distill-7B

0ASR (None)

6

Apr 21, 2026

53.8Harm Score

4

Apr 21, 2026

KGC-SAFETY in-house

88.4Safety Score

4

Feb 26, 2026

Page 2 of 2

Popular datasets

AIR-Bench Safety Evaluation Suite Safety AdvBench 8 jailbreak attacks

Follow for updates

Join SOTA2 Contact