diff --git a/web/app/components/evaluation/components/metric-selector/use-metric-selector-data.ts b/web/app/components/evaluation/components/metric-selector/use-metric-selector-data.ts
index 46f8e9e740..d2ad11bc12 100644
--- a/web/app/components/evaluation/components/metric-selector/use-metric-selector-data.ts
+++ b/web/app/components/evaluation/components/metric-selector/use-metric-selector-data.ts
@@ -54,9 +54,8 @@ export const useMetricSelectorData = ({
 
   const resolvedMetrics = useMemo(() => {
     const metricsMap = new Map(config.builtinMetrics.map(metric => [metric.id, metric] as const))
-    const defaultGroup = config.builtinMetrics[0]?.group ?? 'other'
 
-    return availableMetricIds.map(metricId => metricsMap.get(metricId) ?? buildMetricOption(metricId, defaultGroup))
+    return availableMetricIds.map(metricId => metricsMap.get(metricId) ?? buildMetricOption(metricId))
   }, [availableMetricIds, config.builtinMetrics])
 
   useEffect(() => {
diff --git a/web/app/components/evaluation/components/metric-selector/utils.ts b/web/app/components/evaluation/components/metric-selector/utils.ts
index 818c4b61da..5ab3f03129 100644
--- a/web/app/components/evaluation/components/metric-selector/utils.ts
+++ b/web/app/components/evaluation/components/metric-selector/utils.ts
@@ -14,12 +14,10 @@ const humanizeMetricId = (metricId: string) => {
     .join(' ')
 }
 
-export const buildMetricOption = (metricId: string, fallbackGroup: string): MetricOption => ({
+export const buildMetricOption = (metricId: string): MetricOption => ({
   id: metricId,
   label: humanizeMetricId(metricId),
   description: '',
-  group: fallbackGroup,
-  badges: ['Built-in'],
 })
 
 export const getMetricVisual = (metricId: string): { icon: string, tone: MetricVisualTone } => {
diff --git a/web/app/components/evaluation/mock.ts b/web/app/components/evaluation/mock.ts
index 317f839b82..362a39d41c 100644
--- a/web/app/components/evaluation/mock.ts
+++ b/web/app/components/evaluation/mock.ts
@@ -29,43 +29,31 @@ const builtinMetrics: MetricOption[] = [
     id: 'answer-correctness',
     label: 'Answer Correctness',
     description: 'Compares the response with the expected answer and scores factual alignment.',
-    group: 'quality',
-    badges: ['LLM', 'Built-in'],
   },
   {
     id: 'faithfulness',
     label: 'Faithfulness',
     description: 'Checks whether the answer stays grounded in the retrieved evidence.',
-    group: 'quality',
-    badges: ['LLM', 'Retrieval'],
   },
   {
     id: 'relevance',
     label: 'Relevance',
     description: 'Evaluates how directly the answer addresses the original request.',
-    group: 'quality',
-    badges: ['LLM'],
   },
   {
     id: 'latency',
     label: 'Latency',
     description: 'Captures runtime responsiveness for the full execution path.',
-    group: 'operations',
-    badges: ['System'],
   },
   {
     id: 'token-usage',
     label: 'Token Usage',
     description: 'Tracks prompt and completion token consumption for the run.',
-    group: 'operations',
-    badges: ['System'],
   },
   {
     id: 'tool-success-rate',
     label: 'Tool Success Rate',
     description: 'Measures whether each required tool invocation finishes without failure.',
-    group: 'operations',
-    badges: ['Workflow'],
   },
 ]
 
@@ -74,22 +62,16 @@ const pipelineBuiltinMetrics: MetricOption[] = [
     id: 'context-precision',
     label: 'Context Precision',
     description: 'Measures whether retrieved chunks stay tightly aligned to the request.',
-    group: 'quality',
-    badges: ['Retrieval'],
   },
   {
     id: 'context-recall',
     label: 'Context Recall',
     description: 'Checks whether the retrieval result includes the evidence needed to answer.',
-    group: 'quality',
-    badges: ['Retrieval'],
   },
   {
     id: 'context-relevance',
     label: 'Context Relevance',
     description: 'Scores how useful the retrieved context is for downstream generation.',
-    group: 'quality',
-    badges: ['Retrieval'],
   },
 ]
 
diff --git a/web/app/components/evaluation/store-utils.ts b/web/app/components/evaluation/store-utils.ts
index ee81a8b06b..be592b4df2 100644
--- a/web/app/components/evaluation/store-utils.ts
+++ b/web/app/components/evaluation/store-utils.ts
@@ -41,8 +41,6 @@ const resolveMetricOption = (resourceType: EvaluationResourceType, metricId: str
     id: metricId,
     label: humanizeMetricId(metricId),
     description: '',
-    group: config.builtinMetrics[0]?.group ?? 'other',
-    badges: ['Built-in'],
   }
 }
 
@@ -225,7 +223,6 @@ export function createBuiltinMetric(
     kind: 'builtin',
     label: metric.label,
     description: metric.description,
-    badges: metric.badges,
     threshold,
     nodeInfoList,
   }
@@ -246,7 +243,6 @@ export function createCustomMetric(): EvaluationMetric {
     kind: 'custom-workflow',
     label: 'Custom Evaluator',
     description: 'Map workflow variables to your evaluation inputs.',
-    badges: ['Workflow'],
     customConfig: {
       workflowId: null,
       workflowAppId: null,
diff --git a/web/app/components/evaluation/types.ts b/web/app/components/evaluation/types.ts
index 411c28d540..c8486f7923 100644
--- a/web/app/components/evaluation/types.ts
+++ b/web/app/components/evaluation/types.ts
@@ -37,8 +37,6 @@ export type MetricOption = {
   id: string
   label: string
   description: string
-  group: string
-  badges: string[]
 }
 
 export type EvaluationWorkflowOption = {
@@ -81,7 +79,6 @@ export type EvaluationMetric = {
   kind: MetricKind
   label: string
   description: string
-  badges: string[]
   threshold?: number
   nodeInfoList?: NodeInfo[]
   customConfig?: CustomMetricConfig