This paper provides a comprehensive review of current methods for predicting RNA 3D structures, including ab initio, template-based, and deep learning approaches. The authors benchmark nine methods using the RNA-Puzzles dataset and provide an online dashboard for visualizing predictions. The methods are evaluated using various metrics, including RMSD, INF, P-VALUE, and TM-score. Deep learning methods generally outperform ab initio and template-based methods in most metrics, although they do not capture all key RNA interactions. The paper highlights the challenges of RNA 3D structure prediction, including the lack of structural data and the need for large datasets. The authors also discuss the limitations of current methods, such as computational time and the difficulty of using standalone codes. The State-of-the-RNArt dashboard is made available for users to compare predictions from different methods. The results show that deep learning methods are promising but still require further development to achieve accurate and efficient RNA 3D structure prediction. The paper concludes that further research is needed to improve the accuracy and efficiency of RNA 3D structure prediction methods.This paper provides a comprehensive review of current methods for predicting RNA 3D structures, including ab initio, template-based, and deep learning approaches. The authors benchmark nine methods using the RNA-Puzzles dataset and provide an online dashboard for visualizing predictions. The methods are evaluated using various metrics, including RMSD, INF, P-VALUE, and TM-score. Deep learning methods generally outperform ab initio and template-based methods in most metrics, although they do not capture all key RNA interactions. The paper highlights the challenges of RNA 3D structure prediction, including the lack of structural data and the need for large datasets. The authors also discuss the limitations of current methods, such as computational time and the difficulty of using standalone codes. The State-of-the-RNArt dashboard is made available for users to compare predictions from different methods. The results show that deep learning methods are promising but still require further development to achieve accurate and efficient RNA 3D structure prediction. The paper concludes that further research is needed to improve the accuracy and efficiency of RNA 3D structure prediction methods.