diff --git a/aider/website/_data/edit_leaderboard.yml b/aider/website/_data/edit_leaderboard.yml
index 61f9f62cc..4b538e798 100644
--- a/aider/website/_data/edit_leaderboard.yml
+++ b/aider/website/_data/edit_leaderboard.yml
@@ -1201,26 +1201,26 @@
   versions: 0.56.0
   seconds_per_case: 9.3
   total_cost: 0.0000
-
-- dirname: 2024-09-20-20-07-27--qwen-2.5-72b-instruct
+  
+- dirname: 2024-09-20-20-20-19--qwen-2.5-72b-instruct-diff
   test_cases: 133
   model: qwen-2.5-72b-instruct (bf16)
-  edit_format: whole
-  commit_hash: d7051ce
-  pass_rate_1: 52.6
-  pass_rate_2: 64.7
-  percent_cases_well_formed: 100.0
-  error_outputs: 0
-  num_malformed_responses: 0
-  num_with_malformed_responses: 0
-  user_asks: 2
+  edit_format: diff
+  commit_hash: 5139594
+  pass_rate_1: 53.4
+  pass_rate_2: 65.4
+  percent_cases_well_formed: 96.2
+  error_outputs: 9
+  num_malformed_responses: 9
+  num_with_malformed_responses: 5
+  user_asks: 3
   lazy_comments: 0
-  syntax_errors: 0
-  indentation_errors: 0
+  syntax_errors: 2
+  indentation_errors: 1
   exhausted_context_windows: 0
-  test_timeouts: 0
+  test_timeouts: 3
   command: aider --model openrouter/qwen/qwen-2.5-72b-instruct
   date: 2024-09-20
   versions: 0.56.1.dev
-  seconds_per_case: 53.9
+  seconds_per_case: 39.8
   total_cost: 0.0000
\ No newline at end of file
diff --git a/benchmark/benchmark.py b/benchmark/benchmark.py
index 3d559b9be..360e0705c 100755
--- a/benchmark/benchmark.py
+++ b/benchmark/benchmark.py
@@ -549,7 +549,7 @@ def run_test_real(
         chat_history_file=history_fname,
     )
 
-    main_model = models.Model(model_name)
+    main_model = models.Model(model_name, weak_model=model_name)
     edit_format = edit_format or main_model.edit_format
 
     dump(main_model)