diff --git a/dingo/model/llm/rag/llm_rag_answer_relevancy.py b/dingo/model/llm/rag/llm_rag_answer_relevancy.py
index 24c7f6e0..498a9537 100644
--- a/dingo/model/llm/rag/llm_rag_answer_relevancy.py
+++ b/dingo/model/llm/rag/llm_rag_answer_relevancy.py
@@ -265,10 +265,10 @@ def eval(cls, input_data: Data) -> ModelRes:
             result = ModelRes()
             result.score = score
 
-            # 根据分数判断是否通过（默认阈值5，满分10分）
-            threshold = 5
+            # 根据分数判断是否通过
+            threshold = None
             if hasattr(cls, 'dynamic_config') and cls.dynamic_config.parameters:
-                threshold = cls.dynamic_config.parameters.get('threshold', 5)
+                threshold = cls.dynamic_config.parameters.get('threshold')
                 # 检查是否有自定义的strictness参数
                 cls.strictness = cls.dynamic_config.parameters.get('strictness', 3)
 
@@ -277,7 +277,7 @@ def eval(cls, input_data: Data) -> ModelRes:
                 if embedding_model_name:
                     cls.init_embedding_model(embedding_model_name)
 
-            if score >= threshold:
+            if threshold is None or score >= threshold:
                 result.eval_status = False
                 result.eval_details = {
                     "label": ["QUALITY_GOOD.ANSWER_RELEVANCY_PASS"],
diff --git a/dingo/model/llm/rag/llm_rag_context_precision.py b/dingo/model/llm/rag/llm_rag_context_precision.py
index 05dd4f0f..a7255ebf 100644
--- a/dingo/model/llm/rag/llm_rag_context_precision.py
+++ b/dingo/model/llm/rag/llm_rag_context_precision.py
@@ -254,12 +254,12 @@ def process_response(cls, responses: List[str]) -> ModelRes:
         result = ModelRes()
         result.score = score
 
-        # 根据分数判断是否通过（默认阈值5，满分10分）
-        threshold = 5
+        # 根据分数判断是否通过
+        threshold = None
         if hasattr(cls, 'dynamic_config') and cls.dynamic_config.parameters:
-            threshold = cls.dynamic_config.parameters.get('threshold', 5)
+            threshold = cls.dynamic_config.parameters.get('threshold')
 
-        if score >= threshold:
+        if threshold is None or score >= threshold:
             result.eval_status = False
             result.eval_details = {
                 "label": ["QUALITY_GOOD.CONTEXT_PRECISION_PASS"],
diff --git a/dingo/model/llm/rag/llm_rag_context_recall.py b/dingo/model/llm/rag/llm_rag_context_recall.py
index bd2e1842..ba8e7e8c 100644
--- a/dingo/model/llm/rag/llm_rag_context_recall.py
+++ b/dingo/model/llm/rag/llm_rag_context_recall.py
@@ -200,12 +200,12 @@ def process_response(cls, response: str) -> ModelRes:
         result = ModelRes()
         result.score = score
 
-        # 根据分数判断是否通过（默认阈值5，满分10分）
-        threshold = 5
+        # 根据分数判断是否通过
+        threshold = None
         if hasattr(cls, 'dynamic_config') and cls.dynamic_config.parameters:
-            threshold = cls.dynamic_config.parameters.get('threshold', 5)
+            threshold = cls.dynamic_config.parameters.get('threshold')
 
-        if score >= threshold:
+        if threshold is None or score >= threshold:
             result.eval_status = False
             result.eval_details = {
                 "label": ["QUALITY_GOOD.CONTEXT_RECALL_PASS"],
diff --git a/dingo/model/llm/rag/llm_rag_context_relevancy.py b/dingo/model/llm/rag/llm_rag_context_relevancy.py
index 4e481add..ca5c36fa 100644
--- a/dingo/model/llm/rag/llm_rag_context_relevancy.py
+++ b/dingo/model/llm/rag/llm_rag_context_relevancy.py
@@ -200,12 +200,12 @@ def process_response(cls, response: str) -> ModelRes:
         result = ModelRes()
         result.score = score
 
-        # 根据分数判断是否通过（默认阈值5，满分10分）
-        threshold = 5
+        # 根据分数判断是否通过
+        threshold = None
         if hasattr(cls, 'dynamic_config') and cls.dynamic_config.parameters:
-            threshold = cls.dynamic_config.parameters.get('threshold', 5)
+            threshold = cls.dynamic_config.parameters.get('threshold')
 
-        if score >= threshold:
+        if threshold is None or score >= threshold:
             result.eval_status = False
             result.eval_details = {
                 "label": ["QUALITY_GOOD.CONTEXT_RELEVANCY_PASS"],
diff --git a/dingo/model/llm/rag/llm_rag_faithfulness.py b/dingo/model/llm/rag/llm_rag_faithfulness.py
index 2ded8fac..f5fc70b0 100644
--- a/dingo/model/llm/rag/llm_rag_faithfulness.py
+++ b/dingo/model/llm/rag/llm_rag_faithfulness.py
@@ -284,12 +284,12 @@ def process_response(cls, response: str) -> ModelRes:
         result = ModelRes()
         result.score = score
 
-        # 根据分数判断是否通过（默认阈值5，满分10分）
-        threshold = 5
+        # 根据分数判断是否通过
+        threshold = None
         if hasattr(cls, 'dynamic_config') and cls.dynamic_config.parameters:
-            threshold = cls.dynamic_config.parameters.get('threshold', 5)
+            threshold = cls.dynamic_config.parameters.get('threshold')
 
-        if score >= threshold:
+        if threshold is None or score >= threshold:
             result.eval_status = False
             result.eval_details = {
                 "label": ["QUALITY_GOOD.FAITHFULNESS_PASS"],