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

AirBench dataset and benchmarks · SOTA2 Research

Research Datasets

AirBench

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

General Utility

AirBench 1-10

8.1Speech Score

12

Toxicity and Harmful Content Detection

Airbench

98.59Score

5

Multiple-choice Question Answering

AirBench Foundational

44Total Average Score

4

Jailbreak Attack Evaluation

AirBench

1,390Attack Success Count

2

Popular tasks

Multiple-choice Question Answering Jailbreak Attack Evaluation General Utility Toxicity and Harmful Content Detection

Follow for updates

Join SOTA2 Contact