Update app.py

app.py

@@ -53,7 +53,7 @@ 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", "LLaMA"], "Env.": ["Sokoban", "Sokoban", "Football"],
-                          "Target-research": ["Model-Eval-Global", "Model-Eval-Online", "Agent-Eval-Prompt"], "Link": ["xxx", "xxx", "xxx"]})
+                          "Target-research": ["Model-Eval-Global", "Model-Eval-Online", "Agent-Eval-Prompt"], "Subset": ["mini", "all", "mini"],  "Link": ["xxx", "xxx", "xxx"]})
 
 
 (
@@ -79,6 +79,7 @@ def init_leaderboard(dataframe):
             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="checkboxgroup", label="Environment (Single Selection)"),
+            ColumnFilter("Subset", type="checkboxgroup", label="Subset (Single Selection)"),
             # ColumnFilter(AutoEvalColumn.precision.name, type="checkboxgroup", label="Precision"),
             # ColumnFilter(
             #     AutoEvalColumn.params.name,