Update

src/display/utils.py

@@ -26,7 +26,7 @@ auto_eval_column_dict = []
 auto_eval_column_dict.append(
     ["method_name", ColumnContent, ColumnContent("Method", "markdown", True, never_hidden=True)]
 )
-auto_eval_column_dict.append(["model_name", ColumnContent, ColumnContent("Model", "markdown", True)])
+auto_eval_column_dict.append(["model_name", ColumnContent, ColumnContent("Base Model", "markdown", True)])
 # Scores
 auto_eval_column_dict.append(["full_pass_count", ColumnContent, ColumnContent("Repaired ⬆️", "number", True)])
 auto_eval_column_dict.append(["fast_pass_count", ColumnContent, ColumnContent("Repaired (Fast)", "number", True)])

src/leaderboard/read_evals.py

@@ -31,8 +31,8 @@ class EvalResult:
 
         method_name = data.get("method_name", "")
         method_url = data.get("method_url", "")
-        model_name = data.get("model_name", "")
-        model_url = data.get("model_url", "")
+        model_name = data.get("base_model_name", "")
+        model_url = data.get("base_model_url", "")
         with_hint = data.get("with_hint", False)
         fixes = data.get("fixes", [])
         attempts = len(fixes)

src/populate.py

@@ -13,7 +13,6 @@ def get_leaderboard_df(requests_path: str, cols: list) -> pd.DataFrame:
     all_data_json = [v.to_dict() for v in raw_data]
 
     df = pd.DataFrame.from_records(all_data_json)
-    print(df)
     df = df.sort_values(by=[AutoEvalColumn.full_pass_count.name], ascending=False)
     df = df[cols].round(decimals=2)
     return df