diff --git a/benchmark/longmemeval/config_meta_reme.yaml b/benchmark/longmemeval/config_meta_reme.yaml
index 47f5a8ee..db04626a 100644
--- a/benchmark/longmemeval/config_meta_reme.yaml
+++ b/benchmark/longmemeval/config_meta_reme.yaml
@@ -5,59 +5,33 @@ dataset:
   name: "longmemeval"
   source: "benchmark/longmemeval/dataset/longmemeval_s_reme_cleaned.json"
   train_case_ids:  # empty = all cases; or a list of question IDs
-    - "031748ae_abs"
-    - "09ba9854"
-    - "09d032c9"
-    - "0a995998"
-    - "0bb5a684"
-    - "0edc2aef"
-    - "19b5f2b3_abs"
-    - "2788b940"
     - "2a1811e2"
-    - "32260d93"
-    - "35a27287"
-    - "37f165cf"
-    - "38146c39"
-    - "3a704032"
-    - "4d6b87c8"
-    - "57f827a0"
     - "681a1674"
-    - "6b7dfb22"
     - "6d550036"
-    - "7024f17c"
-    - "71017277"
-    - "75832dbd"
-    - "80ec1f4f_abs"
-    - "81507db6"
-    - "830ce83f"
-    - "852ce960"
-    - "88432d0a"
-    - "8c18457d"
-    - "95228167"
-    - "9a707b81"
-    - "9ee3ecd6"
-    - "a2f3aa27"
-    - "a89d7624"
-    - "c4a1ceb8"
-    - "d6233ab6"
-    - "d851d5ba"
-    - "dd2973ad"
     - "e66b632c"
-    - "eace081b"
-    - "eeda8a6d_abs"
+    - "0a995998"
+    - "35a27287"
+    - "19b5f2b3_abs"
+    - "a2f3aa27"
     - "gpt4_0b2f1d21"
-    - "gpt4_2655b836"
-    - "gpt4_2ba83207"
-    - "gpt4_2f8be40d"
-    - "gpt4_59149c78"
     - "gpt4_59c863d7"
-    - "gpt4_7abb270c"
-    - "gpt4_7f6b06db"
+    - "09ba9854"
+    - "830ce83f"
+    - "gpt4_59149c78"
+    - "32260d93"
+    - "95228167"
+    - "8c18457d"
     - "gpt4_85da3956"
-    - "gpt4_93159ced_abs"
-    - "gpt4_a56e767c"
-    - "gpt4_ab202e7f"
-    - "gpt4_c27434e8_abs"
+    - "3a704032"
+    - "d851d5ba"
+    - "7024f17c"
+    - "gpt4_7f6b06db"
+    - "9ee3ecd6"
+    - "0edc2aef"
+    - "eeda8a6d_abs"
+    - "852ce960"
+    - "38146c39"
+    - "gpt4_2655b836"
 
 validation:
   concurrency: 5