diff --git a/dingo/model/llm/compare/llm_html_extract_compare_v3.py b/dingo/model/llm/compare/llm_html_extract_compare_v3.py
index 9abfeee9..202294d6 100644
--- a/dingo/model/llm/compare/llm_html_extract_compare_v3.py
+++ b/dingo/model/llm/compare/llm_html_extract_compare_v3.py
@@ -215,7 +215,7 @@ def process_response(cls, response: str) -> EvalDetail:
             tmp_type = "EXTRACTION_EQUAL"
 
         result.status = response_model.score != 1
-        result.label = [f"{tmp_type}.{response_model.name}"]
+        result.label = [f"{tmp_type}"]
         result.reason = [json.dumps(response_json, ensure_ascii=False)]
 
         return result
diff --git a/test/scripts/model/llm/test_llm_html_extract_compare_v3.py b/test/scripts/model/llm/test_llm_html_extract_compare_v3.py
index b2546ff1..308635aa 100644
--- a/test/scripts/model/llm/test_llm_html_extract_compare_v3.py
+++ b/test/scripts/model/llm/test_llm_html_extract_compare_v3.py
@@ -75,7 +75,7 @@ def test_score_1_prompt_better(self):
         )
         result = LLMHtmlExtractCompareV3.process_response(raw)
         assert result.metric == "LLMHtmlExtractCompareV3"
-        assert result.label == ["PROMPT_BETTER.Error_Content_Coverage"]
+        assert result.label == ["PROMPT_BETTER"]
         assert result.status is False
         parsed = json.loads(result.reason[0])
         assert parsed["score"] == 1
@@ -86,7 +86,7 @@ def test_score_2_content_better(self):
             ensure_ascii=False,
         )
         result = LLMHtmlExtractCompareV3.process_response(raw)
-        assert result.label == ["CONTENT_BETTER.Error_Formula"]
+        assert result.label == ["CONTENT_BETTER"]
         assert result.status is True
 
     def test_score_0_extraction_equal(self):
@@ -95,7 +95,7 @@ def test_score_0_extraction_equal(self):
             ensure_ascii=False,
         )
         result = LLMHtmlExtractCompareV3.process_response(raw)
-        assert result.label == ["EXTRACTION_EQUAL.None"]
+        assert result.label == ["EXTRACTION_EQUAL"]
         assert result.status is True
 
     def test_json_fenced_with_markdown(self):
@@ -111,7 +111,7 @@ def test_redacted_thinking_appended_to_reason(self):
             '{"score": 2, "name": "Error_Table", "reason": "Brief."}'
         )
         result = LLMHtmlExtractCompareV3.process_response(body)
-        assert "CONTENT_BETTER.Error_Table" == result.label[0]
+        assert "CONTENT_BETTER" == result.label[0]
         parsed = json.loads(result.reason[0])
         assert "internal" in parsed["reason"]