Recently, the application of advanced AI algorithms represented by deep neural network (DNN) in various fields of human society has shown explosive growth. These powerful AI tools have not only revolutionized the traditional working mode of the technology industry, but also deeply penetrated into people’s daily life. However, since AI algorithms generally have problems such as uncertain capability boundaries and difficult interpretability, failing to adequately and accurately measure their quality will bring about great hidden dangers. Traditional software testing and evaluation methods can hardly meet the need of comprehensively measuring the quality of DNN models. To solve this problem, we propose a testing and evaluation framework for the quality of DNN models. Experiments demonstrate that our proposed framework can comprehensively test and evaluate the quality of DNN models, as well as improve the adequacy and accuracy of testing and evaluation through dataset quality analysis and test adequacy analysis.