diff --git a/configs/eval_corebench_2409_base_objective.py b/configs/eval_corebench_2409_base_objective.py
index 9c904365..d5d7a387 100644
--- a/configs/eval_corebench_2409_base_objective.py
+++ b/configs/eval_corebench_2409_base_objective.py
@@ -81,7 +81,7 @@ core_summary_groups = [
             ['drop', 'accuracy'],
             ['math', 'accuracy'],
             ['gsm8k', 'accuracy'],
-            ['mathbench-t (average)', 'naive_average']
+            ['mathbench-t (average)', 'naive_average'],
             ['GPQA_diamond', 'accuracy'],
             ['openai_humaneval', 'humaneval_pass@1'],
             ['IFEval', 'Prompt-level-strict-accuracy'],
@@ -101,7 +101,7 @@ summarizer = dict(
         ['drop', 'accuracy'],
         ['math', 'accuracy'],
         ['gsm8k', 'accuracy'],
-        ['mathbench-t (average)', 'naive_average']
+        ['mathbench-t (average)', 'naive_average'],
         ['GPQA_diamond', 'accuracy'],
         ['openai_humaneval', 'humaneval_pass@1'],
         ['IFEval', 'Prompt-level-strict-accuracy'],
@@ -185,4 +185,4 @@ eval = dict(
 #                      PART 5  Utils Configuaration                   #
 #######################################################################
 base_exp_dir = 'outputs/corebench_2409_objective/'
-work_dir = osp.join(base_exp_dir, 'chat_objective')
+work_dir = osp.join(base_exp_dir, 'base_objective')
diff --git a/opencompass/models/bailing_api_oc.py b/opencompass/models/bailing_api_oc.py
index 54e0d502..d4368a36 100644
--- a/opencompass/models/bailing_api_oc.py
+++ b/opencompass/models/bailing_api_oc.py
@@ -13,7 +13,6 @@ try:
     from retrying import retry
 except ImportError:
     retry = None
-    print('please install retrying by `pip install retrying`')
 
 from opencompass.utils.prompt import PromptList
 
diff --git a/opencompass/models/openai_api.py b/opencompass/models/openai_api.py
index 4a07dee3..aff2579a 100644
--- a/opencompass/models/openai_api.py
+++ b/opencompass/models/openai_api.py
@@ -601,6 +601,10 @@ class OpenAISDK(OpenAI):
                 if self.verbose:
                     self.logger.info(
                         'Successfully get response from OpenAI API')
+                    try:
+                        self.logger.info(responses)
+                    except Exception as e:  # noqa F841
+                        pass
                 return responses.choices[0].message.content
             except Exception as e:
                 self.logger.error(e)