diff --git a/test/integration/scheduler_perf/README.md b/test/integration/scheduler_perf/README.md
index 5ca8474fb33..46d7423cad3 100644
--- a/test/integration/scheduler_perf/README.md
+++ b/test/integration/scheduler_perf/README.md
@@ -158,7 +158,7 @@ the ci-benchmark-scheduler-perf periodic job will fail with an error log such as
 ```
 --- FAIL: BenchmarkPerfScheduling/SchedulingBasic/5000Nodes_10000Pods
     ...
-    scheduler_perf.go:1098: ERROR: op 2: expected SchedulingThroughput Average to be higher: got 256.12, want 270
+    scheduler_perf.go:1098: ERROR: op 2: SchedulingBasic/5000Nodes_10000Pods/namespace-2: expected SchedulingThroughput Average to be higher: got 256.12, want 270
 ```
 
 This allows to analyze which workload failed. Make sure that the failure is not an outlier 
diff --git a/test/integration/scheduler_perf/config/performance-config.yaml b/test/integration/scheduler_perf/config/performance-config.yaml
index 8285b17ba27..a04055a438a 100644
--- a/test/integration/scheduler_perf/config/performance-config.yaml
+++ b/test/integration/scheduler_perf/config/performance-config.yaml
@@ -818,7 +818,7 @@
       measurePods: 1000
   - name: 5000Nodes_2000Pods
     labels: [performance]
-    threshold: 35
+    threshold: 24
     params:
       initNodes: 6000
       initPodsPerNamespace: 40
@@ -1070,7 +1070,6 @@
       measurePods: 10
       maxClaimsPerNode: 10
   - name: 2000pods_100nodes
-    labels: [performance, fast]
     params:
       # In this testcase, the number of nodes is smaller
       # than the limit for the PodScheduling slices.
@@ -1214,7 +1213,6 @@
       measurePods: 10
       maxClaimsPerNode: 10
   - name: 2000pods_100nodes
-    labels: [performance, fast]
     params:
       nodesWithDRA: 100
       nodesWithoutDRA: 0
@@ -1289,7 +1287,6 @@
       measureClaims: 2 # must be measurePods / 5
       maxClaimsPerNode: 2
   - name: 2000pods_100nodes
-    labels: [performance, fast]
     params:
       nodesWithDRA: 100
       nodesWithoutDRA: 0
diff --git a/test/integration/scheduler_perf/scheduler_perf.go b/test/integration/scheduler_perf/scheduler_perf.go
index c87ad55cec9..af571b21b0f 100644
--- a/test/integration/scheduler_perf/scheduler_perf.go
+++ b/test/integration/scheduler_perf/scheduler_perf.go
@@ -939,9 +939,9 @@ func compareMetricWithThreshold(items []DataItem, threshold float64, metricSelec
 	for _, item := range items {
 		if item.Labels["Metric"] == metricSelector.Name && labelsMatch(item.Labels, metricSelector.Labels) && !valueWithinThreshold(item.Data["Average"], threshold, metricSelector.ExpectLower) {
 			if metricSelector.ExpectLower {
-				return fmt.Errorf("expected %s Average to be lower: got %f, want %f", metricSelector.Name, item.Data["Average"], threshold)
+				return fmt.Errorf("%s: expected %s Average to be lower: got %f, want %f", item.Labels["Name"], metricSelector.Name, item.Data["Average"], threshold)
 			}
-			return fmt.Errorf("expected %s Average to be higher: got %f, want %f", metricSelector.Name, item.Data["Average"], threshold)
+			return fmt.Errorf("%s: expected %s Average to be higher: got %f, want %f", item.Labels["Name"], metricSelector.Name, item.Data["Average"], threshold)
 		}
 	}
 	return nil