diff --git a/docs/en/advanced_guides/objective_judgelm_evaluation.md b/docs/en/advanced_guides/objective_judgelm_evaluation.md
index 670881f29..6850e276f 100644
--- a/docs/en/advanced_guides/objective_judgelm_evaluation.md
+++ b/docs/en/advanced_guides/objective_judgelm_evaluation.md
@@ -27,7 +27,7 @@ from mmengine.config import read_base
 with read_base():
     from .models.hf_llama.hf_llama3_8b_instruct import models as hf_llama3_8b_instruct_model # noqa: F401, F403
     from .models.hf_llama.hf_llama3_70b_instruct import models as hf_llama3_70b_instruct_model  # noqa: F401, F403
-    from .datasets.math.math_llm_judge import math_datasets  # noqa: F401, F403
+    from .datasets.math.math_llm_judge_gen import math_datasets  # noqa: F401, F403
 from opencompass.datasets import math_judement_preprocess
 from opencompass.partitioners import NaivePartitioner, SizePartitioner
 from opencompass.partitioners.sub_naive import SubjectiveNaivePartitioner
diff --git a/docs/zh_cn/advanced_guides/objective_judgelm_evaluation.md b/docs/zh_cn/advanced_guides/objective_judgelm_evaluation.md
index fb3865497..9364e61c1 100644
--- a/docs/zh_cn/advanced_guides/objective_judgelm_evaluation.md
+++ b/docs/zh_cn/advanced_guides/objective_judgelm_evaluation.md
@@ -27,7 +27,7 @@ from mmengine.config import read_base
 with read_base():
     from .models.hf_llama.hf_llama3_8b_instruct import models as hf_llama3_8b_instruct_model # noqa: F401, F403
     from .models.hf_llama.hf_llama3_70b_instruct import models as hf_llama3_70b_instruct_model  # noqa: F401, F403
-    from .datasets.math.math_llm_judge import math_datasets  # noqa: F401, F403
+    from .datasets.math.math_llm_judge_gen import math_datasets  # noqa: F401, F403
 from opencompass.datasets import math_judement_preprocess
 from opencompass.partitioners import NaivePartitioner, SizePartitioner
 from opencompass.partitioners.sub_naive import SubjectiveNaivePartitioner
diff --git a/examples/eval_math_llm_judge.py b/examples/eval_math_llm_judge.py
index 5e1ebdb40..4d4de6519 100644
--- a/examples/eval_math_llm_judge.py
+++ b/examples/eval_math_llm_judge.py
@@ -4,7 +4,7 @@
 with read_base():
     from opencompass.configs.models.hf_llama.hf_llama3_8b_instruct import models as hf_llama3_8b_instruct_model  # noqa: F401, F403
     from opencompass.configs.models.hf_llama.hf_llama3_70b_instruct import models as hf_llama3_70b_instruct_model  # noqa: F401, F403
-    from opencompass.configs.datasets.math.math_llm_judge import math_datasets  # noqa: F401, F403
+    from opencompass.configs.datasets.math.math_llm_judge_gen import math_datasets  # noqa: F401, F403
 
 from opencompass.datasets import math_judement_preprocess
 from opencompass.openicl.icl_evaluator import LMEvaluator