diff --git a/packages/ai/evals/golden-dataset/golden.eval.ts b/packages/ai/evals/golden-dataset/golden.eval.ts
index cf5ee63ae..ebb102f00 100644
--- a/packages/ai/evals/golden-dataset/golden.eval.ts
+++ b/packages/ai/evals/golden-dataset/golden.eval.ts
@@ -60,7 +60,7 @@ Eval('development', {
   experimentName: 'Golden-Dataset-Run',
   data: initDataset({
     project: 'development',
-    dataset: 'Golden-Dataset-Temp',
+    dataset: 'Golden-Dataset',
   }),
   task: getMetricCreation,
   scores: basicSuite.concat(basicLLMSuite).concat(expectedSuite).concat(formatSuite),