The model with the top score on questionnaire items gets 0.813, level with a baseline

Researchers compared 14 decision models with 47 generative models. They used the models as replacements for human respondents on a Lithuanian questionnaire with 263 respondents. The model with the top score, MiniMax M3, got 0.813 on the Psychometric Similarity Score. The Gaussian copula baseline got 0.824.