This includes a thorough evaluation of the efficacy of a classification model for some plant diseases, which are categorized into multiple classes, including Septoria, which includes Leaf Spot, Bacterial Wilt, Flower Spot, Botrytis is Blight, & Theodore Powdery Mildew. Important metrics like Precision, Memory, F1-Score, Support, Support Proportion, and Overall Accuracy are used to assess the model's prediction accuracy. The recall is the proportion of actual positive experiences that the model correctly estimates, whereas precision is the fraction of correctly predicted positive cases among total predicted positive tests. An equitable evaluation of the model's efficiency is provided by the F1-Score, which is a harmonic average of Precise and Recall. For instance, classifying Botrytis Blight produces outstanding results, with F1-Score, Precision, and Recall all being higher than 98.02%. Additionally, each subclass in the dataset has a certain number of occurrences represented by the Support measure; for example, Botrytis Blight has an Encourage value of 1520. The average number of cases across classes is measured by the Support Proportion, and Botrytis Blight represents 0.0% of the sample, suggesting a potential class imbalance. Furthermore, the model's ability to correctly classify examples across all classes is demonstrated by its overall accuracy of 0.98. All classes' performance indicators are summarized by the Macro Standard, Weighted Standard, or Micro Average, which reveals the model's overall predictive ability. With a remarkable total accuracy of 97.80%, the given model achieves exceptional precision, recall, and F1-Score across several classes. These findings illustrate the classification model's potential for application in agricultural contexts by demonstrating its capacity to consistently identify and distinguish between a variety of plant diseases.