add a remark about benchmarking

README.md

@@ -91,6 +91,7 @@ prob_label_is_true = probs[:,1]
 ```
 
 ### Benchmarking
+Below, you can see the F1 score on several text classification datasets. All tested models were not fine-tuned on those datasets and were tested in a zero-shot setting.
 | Model                       | IMDB | AG_NEWS | Emotions |
 |-----------------------------|------|---------|----------|
 | [Bart-large-mnli (407 M)](https://huggingface.co/facebook/bart-large-mnli)      | 0.89 | 0.6887  | 0.3765   |