<p>Developing a powerful goodness-of-fit test for the Inverse Gaussian distribution is of significant importance due to its wide practical application. In this article, we introduce and investigate a novel goodness-of-fit test specifically designed for the Inverse Gaussian distribution. Our method employs a local linear regression approach to estimate Kullback–Leibler information, enhancing the accuracy of the test. The properties of the proposed test statistic are presented. To calculate the test statistic, maximum likelihood estimators, which are straightforward and explicit, are employed to estimate the parameters of the Inverse Gaussian distribution. Critical values and the actual sizes of the proposed test are determined by Monte Carlo simulation. A comprehensive simulation study is conducted to compare the power values of the proposed test with those of other well-known existing tests. Finally, two illustrative examples are presented and analyzed to showcase the practical application of the proposed test.</p>