Being able to predict the outcome of a game is useful in many aspects. Such as, to aid designers in the process of understanding how the game is played by the players, as well as how to be able to balance the elements within the game are two of those aspects. If one could predict the outcome of games with certainty the design process could possibly be evolved into more of an experiment based approach where one can observe cause and effect to some degree. It has previously been shown that it is possible to predict outcomes of games to varying degrees of success. However, there is a lack of research which compares and evaluates several different models on the same domain with common aims. To narrow this identified gap an experiment is conducted to compare and analyze seven different classifiers within the same domain. The classifiers are then ranked on accuracy against each other with help of appropriate statistical methods. The classifiers compete on the task of predicting which team will win or lose in a match of the game Blood Bowl 2. For nuance three different datasets are made for the models to be trained on. While the results vary between the models of the various datasets the general consensus has an identifiable pattern of rejections. The results also indicate a strong accuracy for Support Vector Machine and Logistic Regression across all the datasets.