This paper provides a comprehensive review of current methods for predicting the 3D structures of RNA molecules, focusing on *ab initio*, template-based, and deep learning approaches. The authors benchmark nine state-of-the-art methods using the RNA-Puzzles dataset and provide an online dashboard (State-of-the-RNArt) to visualize and compare the predictions. The review highlights the strengths and limitations of each method, emphasizing the need for more accurate and efficient algorithms to predict RNA 3D structures. Deep learning methods show promising results but require large datasets, which are currently limited for RNA structures. The benchmark results indicate that deep learning approaches generally outperform *ab initio* and template-based methods, although they may struggle with certain RNA families and complex structures. The paper also discusses the computational efficiency and practical usability of the available tools, noting that many methods have significant computation times or require specific input formats. Overall, the State-of-the-RNArt dashboard serves as a valuable resource for researchers and practitioners in the field of RNA 3D structure prediction.This paper provides a comprehensive review of current methods for predicting the 3D structures of RNA molecules, focusing on *ab initio*, template-based, and deep learning approaches. The authors benchmark nine state-of-the-art methods using the RNA-Puzzles dataset and provide an online dashboard (State-of-the-RNArt) to visualize and compare the predictions. The review highlights the strengths and limitations of each method, emphasizing the need for more accurate and efficient algorithms to predict RNA 3D structures. Deep learning methods show promising results but require large datasets, which are currently limited for RNA structures. The benchmark results indicate that deep learning approaches generally outperform *ab initio* and template-based methods, although they may struggle with certain RNA families and complex structures. The paper also discusses the computational efficiency and practical usability of the available tools, noting that many methods have significant computation times or require specific input formats. Overall, the State-of-the-RNArt dashboard serves as a valuable resource for researchers and practitioners in the field of RNA 3D structure prediction.