Accurate estimation of state-of-charge (SOC) in batteries is of paramount importance for effective and safe battery system management. Sodium-ion batteries' distinctive features on open-circuit voltage and their near-linear relationships with SOC provide a fresh perspective on SOC estimation compared to lithium-ion counterparts. Therefore, this study proposes a low-complexity and wide-adaptability data-driven model for SOC estimation of sodium-ion batteries. Enhanced pulse test across a wide spectrum of conditions is conducted to construct the training set and a hierarchical learning strategy is designed to train the model parameters. To validate this model, tests and evaluations using data of three driving cycles are conducted. The proposed model yields root mean square errors of 0.89 % and 0.63 % for 3.2 Ah and 10 Ah sodium-ion batteries from different manufacturers, respectively. Furthermore, we demonstrate the strong robustness of the model by applying Gaussian noises to the sampled data. Compared to existing data-driven methods for battery SOC estimation, our proposed model achieves remarkably promising performance with significantly lower parameter counts and FLOPs, which is quite attractive in implementation. This work underscores the significant potential of leveraging the distinctive characteristics of sodium-ion batteries to achieve practical and reliable state estimation.