Abstract: Fishing vessels are closely related to the energy efficiency in the sustainable maritime industry. However, some challenges are still remained to evaluate the energy efficiency of fishing vessels, particularly on the limited data of sample sizes. It is also lacking on a specific quantification formula for the energy efficiency of existing fishing vessels. Furthermore, the EEXI (energy efficiency existing ship index) standards that developed by the International Maritime Organization (IMO) cannot include the current fishing vessels. In this study, a reference line model was constructed for the EEXI of fishing vessels. Various types of fishing vessels were also selected, including trawlers, gillnetters, and purse seine vessels. The key parameters were then evaluated, such as the total tonnage, the number of main engines, total engine power, and cruising speed. Finally, the comparison was made using the nonlinear least squares and feedforward neural networks. The results demonstrate that the nonlinear least squares outperformed the feedforward neural networks over the multiple evaluation metrics. Specifically, mean squared error (MSE), mean absolute error (MAE), root mean squared error (RMSE), mean absolute percentage error (MAPE), and R² were found to be 131.20 (g/(t∙nm))², 7.77 g/(t∙nm), 11.45 g/(t∙nm), 15% and 0.63, respectively, when using nonlinear least squares to fit the fishing vessel EEXI reference line formula. The excellent generalization and robustness were achieved reliable for the practical applications. In addition, a case study was carried out to verify the effectiveness of the improved model. The practical applicability was further validated in the real-world scenarios. As such, the reference line calculation model was suitable for the EEXI of existing fishing vessels. New insights and technical support were provided to evaluate the energy efficiency of fishing vessels. A data-driven research approach was also adopted to improve the energy efficiency of fishing vessels. The findings can greatly contribute to promote the IMO’s standards in the sustainable maritime industry.