style: Run linter on benchmark script

benchmark/problem_stats.py

@@ -1,9 +1,11 @@
 #!/usr/bin/env python
 
-import yaml
-from pathlib import Path
-from collections import defaultdict
 import json
+from collections import defaultdict
+from pathlib import Path
+
+import yaml
+
 
 def load_results(dirname):
     """Load all result files from a benchmark directory"""
@@ -22,6 +24,7 @@ def load_results(dirname):
             continue
     return all_results
 
+
 def analyze_exercise_solutions():
     # Load the leaderboard data
     with open("aider/website/_data/edit_leaderboard.yml") as f:
@@ -54,15 +57,11 @@ def analyze_exercise_solutions():
     print("-" * 40)
 
     # Sort by number of models that solved each exercise
-    sorted_exercises = sorted(
-        exercise_solutions.items(),
-        key=lambda x: len(x[1]),
-        reverse=True
-    )
+    sorted_exercises = sorted(exercise_solutions.items(), key=lambda x: len(x[1]), reverse=True)
 
     for testcase, models in sorted_exercises:
         print(f"{testcase}: solved by {len(models)} models")
-        #print(f"  Models: {', '.join(models)}")
+        # print(f"  Models: {', '.join(models)}")
 
     print("\nSummary:")
     print(f"Total exercises solved at least once: {len(exercise_solutions)}")
@@ -78,5 +77,6 @@ def analyze_exercise_solutions():
     for count in sorted(solved_by_counts.keys()):
         print(f"Solved by {count} models: {solved_by_counts[count]} exercises")
 
+
 if __name__ == "__main__":
     analyze_exercise_solutions()