Update app.py

app.py

@@ -52,7 +52,7 @@ except Exception:
 
 
 LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS, BENCHMARK_COLS)
-_test_data = pd.DataFrame({"Score": [54,46,53], "Name": ["MageBench", "MageBench", "MageBench"], "BaseModel": ["GPT-4o", "GPT-4o", "GPT-4o"], "Env.": ["Sokoban", "Sokoban", "Football"],
+_test_data = pd.DataFrame({"Score": [54,46,53], "Name": ["MageBench", "MageBench", "MageBench"], "BaseModel": ["GPT-4o", "GPT-4o", "LLaMA"], "Env.": ["Sokoban", "Sokoban", "Football"],
                           "Target-research": ["Model-Eval-Global", "Model-Eval-Online", "Agent-Eval-Prompt"], "Link": ["xxx", "xxx", "xxx"]})
 
 
@@ -68,8 +68,8 @@ def init_leaderboard(dataframe):
     return Leaderboard(
         value=dataframe,  #dataframe,
         select_columns=SelectColumns(
-            default_selection=["Score", "Name", "BaseModel", "Link", "Env."],
-            cant_deselect=["Score", "Name", "BaseModel", ],
+            default_selection=["Score", "Name", "BaseModel", "Env.", "Target-research"],
+            cant_deselect=["Score", "Name",],
             label="Select Columns to Display:",
         ),
         search_columns=SearchColumns(primary_column="Name", secondary_columns=["BaseModel", "Target-research"],
@@ -78,7 +78,7 @@ def init_leaderboard(dataframe):
         filter_columns=[
             ColumnFilter("Target-research", type="checkboxgroup", label="Comparison settings for target researches (Single Selection)"),
             ColumnFilter("BaseModel", type="dropdown", label="Select The base lmm model that fultill the task."),
-            ColumnFilter("Env.", type="checkbox", label="Environment"),
+            ColumnFilter("Env.", type="checkboxgroup", label="Environment (Single Selection)"),
             # ColumnFilter(AutoEvalColumn.precision.name, type="checkboxgroup", label="Precision"),
             # ColumnFilter(
             #     AutoEvalColumn.params.name,