The calibration of total station distance measurement accuracy needs to be carried out on a standard baseline field, and it is of great significance to judge the reliability of the measurement results of the total station due to the uncontrollable field environment and the drastic fluctuation of meteorological conditions. In order to solve the problems of nonlinearity and strong correlation of inputs of the total station distance measurement uncertainty evaluation model, this paper firstly adopts the adaptive Monte Carlo method to evaluate the uncertainty, and then compares the uncertainty evaluation results with those of the GUM. When the ranging distance is 1 176 m, the uncertainty evaluation results of the adaptive Monte Carlo method is 2.2 mm, and the GUM is 2.6 mm. The results show that the measurement results of both uncertainty assessment methods are within reasonable expectations, and the uncertainty confidence interval of the adaptive Monte Carlo method is narrower. The adaptive Monte Carlo method combines the advantages of a large number of data samples and adaptive optimization of the simulation times, which not only provides a more comprehensive assessment of the uncertainty components introduced by various error sources in the process of total station distance measurement, but also saves 70% of samples compared with the Monte Carlo method, while guaranteeing the accuracy of the uncertainty assessment results of the total station distance measurement.