List your company

ResearchFormerly WizWand

AirBench

Benchmarks

TaskDatasetSOTA 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