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

Agent Action dataset and benchmarks · SOTA2 Research

Research Datasets

Agent Action

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Indirect Prompt Injection

Agent Action Subset 2

0IR

24

Agent Action subset

98RR

12

Prompt Injection Attack Success

Agent Action

85IR

10

Indirect Prompt Injection Attack Success Evaluation

Agent Action Goal-Distant 2

88IRany

5

Indirect Prompt Injection Attack Success Evaluation

Agent Action Goal-Adjacent 2

85IRany

5

Popular tasks

Indirect Prompt Injection Attack Success Evaluation Indirect Prompt Injection Agent Action Prompt Injection Attack Success

Follow for updates

Join SOTA2 Contact