The massive use of social networks and the anonymity that this provides has made possible not only the immediate communication between users, but also the spread of hate speech against certain groups of our society in the form of offensive messages to them, this has led to a serious social problem, which remains a topic of current research along with NLP. The purpose of the present work is to make a comparison of our "HateCheck" recognition model against the author's results, using the same database as them. To do so, we will make use of the main metrics such as: precision, recall and F1.