Update README.md

README.md

@@ -121,7 +121,7 @@ The existing Indic benchmarks are not natively in Indian languages, rather, they
 Below are the results from manual evaluation of prompt-response pairs across languages and task categories. Scores are between 1-5 (higher the better). Model names were anonymised during the evaluation.
 
 <img src="images/cumulative_score_category.png" alt="cumulative_score_category" width="600" height="400" />
-<img src="images/cumulative_score_langauge.png" alt="cumulative_score_langauge" width="600" height="400" />
+<img src="images/cumulative_score_language.png" alt="cumulative_score_langauge" width="600" height="400" />
 
 
 ## Usage