update

app.py

@@ -138,7 +138,7 @@ with demo:
         with gr.TabItem("🏅 LLM Benchmark", elem_id="llm-benchmark-tab-table", id=0):
             leaderboard = init_leaderboard(LEADERBOARD_DF, AutoEvalColumn)
         
-        with gr.TabItem("🏅 Asset Benchmark", elem_id="llm-benchmark-asset-tab-table", id=1):
+        with gr.TabItem("🛠️ Asset Benchmark", elem_id="llm-benchmark-asset-tab-table", id=1):
             leaderboard = init_leaderboard(ASSET_LEADERBOARD_DF, AutoEvalColumnAsset)
 
         with gr.TabItem("📊 Performance Plot", elem_id="llm-benchmark-tab-table", id=2):

src/populate.py

@@ -4,7 +4,7 @@ import os
 import pandas as pd
 
 from src.display.formatting import has_no_nan_values, make_clickable_model
-from src.display.utils import AutoEvalColumn, EvalQueueColumn
+from src.display.utils import AutoEvalColumnAsset, EvalQueueColumn
 from src.leaderboard.read_evals import get_raw_eval_results
 
 
@@ -17,7 +17,7 @@ def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchm
 
     df = pd.DataFrame.from_records(all_data_json)
     print(df)
-    df = df.sort_values(by=[AutoEvalColumn.average.name], ascending=False)
+    df = df.sort_values(by=[AutoEvalColumnAsset.average.name], ascending=False)
     df = df[cols].round(decimals=2)
 
     # filter out if any of the benchmarks have not been produced