Predicting gas-bearing properties in tight sandstone reservoirs presents a global challenge. Traditional methods based on well log interpretation rely heavily on individual experience, which can introduce significant unknown errors. Prediction methods using seismic data and logging labels often fail to capture complex interactions between geological features, resulting in low accuracy. Furthermore, these methods typically determine only gas presence without providing quantitative results. To address these limitations, this study proposes a novel interpretable machine learning (ML) framework. Its novelty lies in: (1) directly linking well testing conclusions to logging data to provide high-resolution, semi-quantitative gas-bearing labels, eliminating intermediate interpretation errors; (2) a systematic comparison of 19 ML algorithms across different paradigms (traditional ML, deep learning, and ensemble learning) using five tailored evaluation metrics, identifying LightGBM as the optimal model for this task (Accuracy = 99.76%); and (3) integrating interpretability directly into the prediction workflow based on cooperative game theory to provide global and local explanations that align with petroleum geological knowledge, significantly enhancing the model’s transparency and credibility. Applied to the Xujiahe Formation in the Sichuan Basin, this framework achieves decimeter-level accuracy and demonstrates strong generalization capability. This work proposes a novel framework that enables semi-quantitative gas-bearing property predictions with the potential for basin-scale application, directly identifying sweet spots and offering a more streamlined and interpretable high-accuracy artificial intelligence method for oil and gas resource exploration and development.