Selecting the right crop for a particular land condition is one of the significant challenges in the agricultural sector. Each crop type has specific needs related to environmental factors such as soil type, pH, humidity, rainfall, and temperature. Mistakes in determining the appropriate crop type can result in decreased production, wastage of resources, and losses for farmers. This paper aims to determine the best model for use as a knowledge base to choose suitable plants for soil conditions. Machine learning algorithms were used to identify patterns of relationships between land conditions and the success of certain crop types to assist in selecting suitable crops and then made a knowledge-based decision support system. Algorithms such as Decision Tree, Random Forest, Support Vector Machine (SVM), and k-Nearest Neighbor (k-NN) have been applied to solve this problem. In this paper, 30 experiments were conducted to test the stability of the model in determining suitable crops based on land conditions. The results of the experiments showed that the Support Vector Machine (SVM) has a more stable performance than other algorithms, with accuracy values of mean and standard deviation of 1 and 0, respectively.