Fix

src/leaderboard/read_evals.py

@@ -9,7 +9,7 @@ import numpy as np
 
 from src.display.formatting import make_clickable_model
 from src.display.utils import AutoEvalColumn, ModelType, Precision, WeightType
-from src.about import Tasks, N_Tasks
+from src.about import Detail_Tasks, Tasks, N_Tasks
 from src.submission.check_validity import is_model_on_hub
 
 
@@ -177,7 +177,7 @@ def get_raw_eval_results(results_path: str, requests_path: str) -> list[EvalResu
     
     version = results_path.split("/")[-1]
     print(version)
-    tasks = N_Tasks if "n_" in version else Tasks
+    tasks = list(N_Tasks) + list(Detail_Tasks) if "n_" in version else Tasks
     print(tasks)
 
     eval_results = {}

src/populate.py

@@ -6,13 +6,13 @@ 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.leaderboard.read_evals import get_raw_eval_results
-from src.about import Tasks, N_Tasks
+from src.about import Tasks, N_Tasks, Detail_Tasks
 
 
 def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchmark_cols: list, version="1_correct") -> pd.DataFrame:
     """Creates a dataframe from all the individual experiment results"""
     raw_data = get_raw_eval_results(results_path+"/"+version, requests_path)
-    tasks = Tasks if version == "1_correct" else N_Tasks
+    tasks = Tasks if version == "1_correct" else list(N_Tasks) + list(Detail_Tasks)
     all_data_json = [v.to_dict(tasks) for v in raw_data]
 
     print(all_data_json)