Fix

src/populate.py

@@ -23,6 +23,7 @@ def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchm
     print(cols)
     if version != "1_correct":
         cols.remove("VCR")
+        benchmark_cols.remove("VCR")
     df = df[cols].round(decimals=2)
 
     # filter out if any of the benchmarks have not been produced