Conservation agriculture (CA) is being promoted as a set of management practices that can sustain crop production while providing positive environmental externalities. However, its impact on crop productivity is still hotly debated, and how this productivity will be affected by climate change remains uncertain. Here we compared the productivity of CA vs. conventional tillage (CT) systems under current and future climate conditions using a probabilistic machine-learning approach at the global scale. We reveal large differences in the probability of yield gains with CA across crop types, climate zones, and geographical regions. We show that, for most crops, CA performed better in continental, arid and temperate regions than in tropical ones. Under future climate conditions, the relative productive performance of CA is expected to increase for maize in almost all cropping areas within the tropical band, thus improving the competitiveness of CA for this major crop.