加载中...

AI Safety Benchmark Database

This database collects AI safety benchmarks and their subsets, organized by risk domain, evaluation type, target model type, availability, and Inspect support status. 了解更多

Risk Domain

Evaluation Type

Evaluating Function

Platform Version

Target Type

Adopted By

Availability

Supports Inspect

Release Month From

Keyword

Benchmark List

Name	Risk Domain	Evaluation Type	Subset	Description	Platform Version	Target Type	Adopted By	?	Availability	Actions