Update README.md

README.md

@@ -60,11 +60,15 @@ The **roberta-base-ca-cased-tc** is a Text Classification (TC) model for the Cat
 We used the QA dataset in Catalan called [TeCla](https://huggingface.co/datasets/projecte-aina/viquiquad) for training and evaluation.
 
 ## Evaluation and results
-Below, the evaluation result on the TeCla test set:
+We evaluated the _roberta-base-ca-cased-tc_ on the TeCla test set against standard multilingual and monolingual baselines:
 
-| Task        | TeCla (accuracy) | 
-| ------------|:----|
+| Model        | TeCla (accuracy) | 
+| ------------|:-------------|
 | BERTa       | **74.04** |
+| mBERT       |  70.56 | 
+| XLM-RoBERTa | 71.68 | 
+| WikiBERT-ca |  73.22 | 
+
 For more details, check the fine-tuning and evaluation scripts in the official [GitHub repository](https://github.com/projecte-aina/berta).
 
 ## Citing