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

Utility assessment research benchmarks · SOTA2 Research

Utility assessment

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

AgentDojo (test)

Semantic-Injection

100Utility

128

Feb 26, 2026

Identity-Robust Generation

16.5Personalization Bias (PB)

9

Feb 26, 2026

LLaVA-Bench In-the-Wild

7.88Utility Score

4

Apr 20, 2026

Financial Agent Dialogues

90.13Utility F1

4

Apr 13, 2026

Popular datasets

MMLU LLaVA-Bench AgentDojo Financial Agent Dialogues

Follow for updates

Join SOTA2 Contact