Are Bias Evaluation Methods Biased?

The creation of benchmarks to evaluate the safety of Large Language Models is one of the key activities within the trusted AI community. These benchmarks allow models to be compared for different aspects of safety such as toxicity, bias, harmful behavior etc. Independent benchmarks adopt different approaches with distinct data sets and evaluation methods. We investigate how robust such benchmarks are by using different approaches to rank a set of representative models for bias and compare how similar are the overall rankings. We show that different but widely used bias evaluations methods result in disparate model rankings. We conclude with recommendations for the community in the usage of such benchmarks.