Update README.md

README.md

@@ -22,12 +22,18 @@ Training in French also improves the model's overall capabilities.
 
 ### LLM Leaderboard FR
 
-[Updated 2025-04-25]
+[Updated 2025-10-20]
 
 Top 3 all categories on the French Government [Leaderboard LLM FR](https://huggingface.co/spaces/fr-gouv-coordination-ia/llm_leaderboard_fr#/) 
 
 ![image/png](https://github.com/jpacifico/Chocolatine-LLM/blob/main/Assets/Leaderboard_FR_14022025.png?raw=true)  
 
+### COLE Benchmark (Laval University)
+
+[Updated 2025-10-20]
+
+Chocolatine-2-14B-Instruct-v2.0.3 stands out as the *strongest open-weights models* with a Composite Score of **45.05%**  
+[Paper here with benchmark results ](https://arxiv.org/pdf/2510.05046)  
 
 ### MT-Bench-French