We introduce a new and general quantity to evaluate a statistical model called the e-value. We develop a framework that considers a very broad definition of a statistical model and establish several results in a parametric modelling context to separate out ‘good’ models from ‘bad’ models. This is a generalization of the conventional hypothesis testing structure and p-values. This results in a fast and parallel algorithm that fits only a single model and evaluates p+1 models, as opposed to the traditional requirement of fitting and evaluating 2p models, or using greedy methods like forward selection and backward deletion. We illustrate in simulation experiments that our proposed method typically performs better than or competitively with currently used methods for model selection: in linear models and fixed effect selection in linear mixed models. As a real data application, we use our procedure to elicit climatic drivers of Indian summer monsoon precipitation.