look the appending of task names

src/leaderboard/read_evals.py

@@ -198,10 +198,10 @@ def get_raw_eval_results(results_path: str, requests_path: str) -> list[EvalResu
 
     results = []
     for v in eval_results.values():
-        #try:
-        v.to_dict() # we test if the dict version is complete
-        results.append(v)
-        #except KeyError:  # not all eval values present
-        #    continue
+        try:
+            v.to_dict() # we test if the dict version is complete
+            results.append(v)
+        except KeyError:  # not all eval values present
+            continue
 
     return results