As oil and gas exploration extends to deep, ultra-deep, and unconventional reservoirs, high drilling costs persist. Drill bit performance, as the critical rock-breaking component, directly governs efficiency and economics. While optimal bit selection boosts rate of penetration (ROP) and cuts costs, traditional expert-dependent methods struggle to address complex formation bit parameter interactions, suffering from low accuracy and poor adaptability. With artificial intelligence gaining traction in petroleum engineering, machine learning-based bit selection has emerged as a key solution. This study focuses on polycrystalline diamond compact (PDC) bits and proposes an intelligent bit selection method based on graph neural networks (GNNs), utilizing drilling records from over 100 wells encompassing 40 multidimensional features. Through comparative analysis of four intelligent models—random forest, gradient boosting (XGBoost), gated recurrent unit (GRU), and the GNN, the results demonstrate that the GNN achieves superior performance with an R² (coefficient of determination) of 0.932 and MAPE (mean absolute percentage error) of 6.88%. The GNN significantly outperforms conventional models in rock-breaking performance prediction. By establishing this GNN model for ROP and footage per run prediction, this study achieves intelligent bit selection that substantially enhances drilling efficiency, reduces operational costs, and provides scientifically reliable technical support for drilling operations in complex formation conditions.