Abstract: A vehicle evaluation system includes processing circuitry and a memory device. The memory device stores data of a pretrained model. The pretrained model is a model trained by supervised learning to generate operation data from training sound data. The operation data is data indicating changes in operation information in a measurement operation pattern. The processing circuitry is configured to perform a generation process and an evaluation process. The generation process is a process of outputting generated data which is data of operation information generated by inputting the evaluation data to the pretrained model. The evaluation data includes evaluation sound data recorded while operating a target vehicle in the measurement operation pattern. The evaluation process is a process of comparing the operation data with the generated data and evaluating the target vehicle in accordance with the magnitude of a difference therebetween.