Abstract: To precisely identify the different forms of online sexism, we utilize several sentence transformer models such as ALBERT, BERT, RoBERTa, DistilBERT, and XLNet. By combining the predictions from these models, we can generate a more comprehensive and improved result. Each transformer model is trained after pre-processing the data from the training dataset, ensuring that the models are effective at detecting and classifying instances of online sexism. For Task A, the model had to classify the texts as sexist or not sexist. We implemented ALBERT, an NLP-based sentence transformer. For task B, we implemented BERT, RoBERTa, DistilBERT and XLNet and took the mode of predictions for each text as the final prediction for the given text. For task C, we implemented ALBERT, BERT, RoBERTa, DistilBERT and XLNet and took the mode of predictions as the final prediction for the given text.