Update README.md

README.md

@@ -46,7 +46,7 @@ If you are a German speaker you may also have a look at our Blog post about this
 
 We evaluated our model for the nli task using the TEST set of the German part of the [xnli](https://huggingface.co/datasets/xnli) dataset.
 
-XNLI TEST-Set Accuracy: 86% 
+XNLI TEST-Set Accuracy: 85.6% 
 
 
 ### Zeroshot Text Classification Task Benchmark 
@@ -58,7 +58,7 @@ The next table shows the results as well as a comparison with other German langu
 
 | Model               | Accuracy |
 |:-------------------:|:------:|
-| Svalabs/gbert-large-zeroshot-nli     | 0.79 |
+| Svalabs/gbert-large-zeroshot-nli     | 0.81 |
 | Sahajtomar/German_Zeroshot | 0.76 |
 | Symanto/xlm-roberta-base-snli-mnli-anli-xnli | 0.16 |
 | Deepset/gbert-base | 0.65 |