Test commit

src/populate.py

@@ -14,7 +14,7 @@ def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchm
     all_data_json = [v.to_dict() for v in raw_data]
 
     df = pd.DataFrame.from_records(all_data_json)
-    df = df.sort_values(by=[AutoEvalColumn.average.name], ascending=False)
+    df = df.sort_values(by=[AutoEvalColumn.mean_score.name], ascending=False)
     df = df[cols].round(decimals=2)
 
     # filter out if any of the benchmarks have not been produced