Gold is a precious metal resistant to corrosion and oxidation, highly valued in investment and trade. Currently, the demand for gold is increasing as it is considered a safe haven. This is evidenced by 48% of respondents out of 2,333 respondents choosing gold as the most preferred investment, based on a survey conducted by Jakpat. However, gold actually has a fluctuating price. The fluctuating price of gold worldwide is influenced by many factors such as economic conditions, inflation rate, supply and demand of gold, and the US dollar exchange rate. Therefore, there is a need for a prediction that can estimate the price of gold based on the movement of gold prices in previous periods. In this study, an evaluation of the performance of GRU for predicting the price of gold will be conducted.. The research methodology includes data collection and processing of gold prices, application of the GRU model, and evaluation of model performance with evaluation metrics such as Mean Squared Error (MSE) and Mean Absolute Error (MAE). Gold price data is taken from Yahoo Finance from December 14, 2017, to March 14, 2024, and processed through normalization and data splitting into training and testing sets. The results of the study show that the GRU model is able to predict gold prices with an adequate level of accuracy. Based on the MSE and MAE values, the combination that provides the best performance is a batch size of 64 with 100 epochs, as it yields the lowest MSE and MAE.