Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
FairXgithub.com · Low evidenceFairX is a comprehensive benchmarking tool for model analysis that evaluates fairness, utility, and explainability. It provides data loaders, custom dataset support, various fairness models, and a wide range of evaluation metrics.
Parse Score