Update README.md

README.md

@@ -95,12 +95,10 @@ The model is designed for various domains, including:
 
 ---
 
-## Performance Metrics  
+## Limitations 
 
-The model excels in reasoning benchmarks:  
-- **ARC (AI2 Reasoning Challenge):** High accuracy in logical and commonsense tasks.  
-- **GSM8K (Math Reasoning):** Superior results in multi-step problem-solving.  
-- **CommonsenseQA:** Strong comprehension of everyday reasoning tasks.  
+- **Arithmetic Equations** Model might hallucinate in the middle of thinking and using Arithmetic Equations as it wasn't trained on latex equations.
+- **Very Complex problems** Model has a tendency to get side tracked when asked long and complex problems and might answer with uncertainty.
 
 ---