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

Skill Invocation Safety Auditing research benchmarks · SOTA2 Research

Skill Invocation Safety Auditing

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

SIA-Bench Held-out indirect prompt injection

43.9HR-AUPRC

7

Apr 14, 2026

SIA-Bench Locked in-distribution (test)

20.4HR-AUPRC

7

Apr 14, 2026

Popular datasets

Follow for updates

Join SOTA2 Contact