Update README.md

README.md

@@ -273,16 +273,44 @@ from [mteb/scripts/task_selection/europe_tasks.csv at main · embeddings-benchma
 
 
 #### Evaluations on cross-lingual capabilities 
-There are important use cases where one wants to retrieve multiple documents on a topic or answering questions that are formulated in a 
-different language than the query. This increases recall and information retrieval coverage. For testing on cross-lingual capabilities 
-evaluated Pharia-1-Embedding-4608-control and GritLM on the MLQA-V1 datasets (Facebook) for German/English and English/Spanish language pairings. 
-For German/French we used the CLSD-WMT19 dataset providing correct and adversarial translations of a sentence in the corresponding pair language.
-
-|Model Name                     |MLQA-V1 Ger/Eng (2000 samples)| MLQA-V1 Eng/Esp (2000 samples)| CLSD-WMT19 Ger/Fra (2900 samples)|
-|:-----------------------------:|:----------------------------:|:-----------------------------:|:--------------------------------:|
-|Pharia-1-Embedding-4608-control|79.5%                         |78.5%                          |95.1%                             |
-|GritLM-7B                      |73.4%                         |73.9%                          |94.2%                             |
-|Nvidia-Embed-v2                |69.4%                         |70.7%                          |93.4%                             |
+There are important use cases where one wants to retrieve multiple documents on a topic or answering questions that are formulated in a
+different language than the query. This increases recall and information retrieval coverage. For testing on cross-lingual capabilities
+we evaluated Pharia-1-Embedding-4608-control, GritLM and Nvidia-Embed-v2 on the MLQA-V1 datasets (Facebook) for German/English and 
+English/Spanish language pairings. For German/French we used the CLSD-WMT19 dataset providing correct and adversarial translations 
+of a sentence in the corresponding pair language. In order to check quality over a larger range of sample size we did the accuracy 
+computations for varying number of samples taken from the MLQA-V1 dataset. For the CLSD-WMT19 evaluation we employed the 
+full set of data (2900 samples available).
+  
+
+#### MLQA-V1 Ger/Eng cross-lingual accuracies for the considered models
+ 
+|# of samples|Pharia4608|GritLM|Nvidia-Embed-v2|
+|:---:|:---:|:---:|:---:|
+|1000|86.0%|82.5%|77.0%|
+|2000|79.5%|73.4%|69.4%|
+|4000|65.3%|59.2%|56.0%|
+|6000|54.3%|48.6%|45.6%|
+|10000|38.6%|32.8%|32.8%|
+
+
+#### MLQA-V1 Eng/Esp cross-lingual accuracies for the considered models
+
+|# samples|Pharia4608|GritLM|NV-Embed-v2|
+|:---:|:---:|:---:|:---:|
+|1000|87.5%|82.0%|81.5%|
+|2000|78.5%|73.9%|70.7%|
+|4000|65.5%|59.3%|56.9%|
+|6000|55.3%|49.2%|46.2%|
+|10000|41.7%|35.5%|33.2%|
+
+#### CLSD-WMT19 Ger/Fra (2900 samples) cross-lingual evaluation for the considered models
+
+
+|Model Name                     | accuracy |
+|:-----------------------------:|:--------------------------------:|
+|Pharia-1-Embedding-4608-control|95.1%                             |
+|GritLM-7B                      |94.2%                             |
+|Nvidia-Embed-v2                |93.4%                             |
 
 
 ## Training Details