Add MDPBench private evaluation result

.eval_results/mdpbench.yaml

@@ -2,7 +2,7 @@
     id: Delores-Lin/MDPBench
     task_id: overall
   value: 52.2
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -11,7 +11,7 @@
     id: Delores-Lin/MDPBench
     task_id: digital
   value: 68.0
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -20,7 +20,7 @@
     id: Delores-Lin/MDPBench
     task_id: photographed
   value: 47.0
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -29,7 +29,7 @@
     id: Delores-Lin/MDPBench
     task_id: latin
   value: 65.1
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -38,7 +38,7 @@
     id: Delores-Lin/MDPBench
     task_id: de
   value: 71.7
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -47,7 +47,7 @@
     id: Delores-Lin/MDPBench
     task_id: en
   value: 77.9
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -56,7 +56,7 @@
     id: Delores-Lin/MDPBench
     task_id: es
   value: 55.9
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -65,7 +65,7 @@
     id: Delores-Lin/MDPBench
     task_id: fr
   value: 62.1
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -74,7 +74,7 @@
     id: Delores-Lin/MDPBench
     task_id: id
   value: 66.2
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -83,7 +83,7 @@
     id: Delores-Lin/MDPBench
     task_id: it
   value: 74.5
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -92,7 +92,7 @@
     id: Delores-Lin/MDPBench
     task_id: nl
   value: 66.3
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -101,7 +101,7 @@
     id: Delores-Lin/MDPBench
     task_id: pt
   value: 71.1
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -110,7 +110,7 @@
     id: Delores-Lin/MDPBench
     task_id: vi
   value: 40.2
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -119,7 +119,7 @@
     id: Delores-Lin/MDPBench
     task_id: non_latin
   value: 37.6
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -128,7 +128,7 @@
     id: Delores-Lin/MDPBench
     task_id: ar
   value: 4.6
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -137,7 +137,7 @@
     id: Delores-Lin/MDPBench
     task_id: hi
   value: 4.2
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -146,7 +146,7 @@
     id: Delores-Lin/MDPBench
     task_id: jp
   value: 55.2
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -155,7 +155,7 @@
     id: Delores-Lin/MDPBench
     task_id: ko
   value: 60.5
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -164,7 +164,7 @@
     id: Delores-Lin/MDPBench
     task_id: ru
   value: 42.6
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -173,7 +173,7 @@
     id: Delores-Lin/MDPBench
     task_id: th
   value: 9.1
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -182,7 +182,7 @@
     id: Delores-Lin/MDPBench
     task_id: zh
   value: 72.2
-  date: "2026-04-14"
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard
@@ -191,7 +191,16 @@
     id: Delores-Lin/MDPBench
     task_id: zh_t
   value: 52.4
-  date: "2026-04-14"
+  date: '2026-07-03'
+  source:
+    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
+    name: MDPBench leaderboard
+    user: Delores-Lin
+- dataset:
+    id: Delores-Lin/MDPBench
+    task_id: private
+  value: 53.6
+  date: '2026-07-03'
   source:
     url: https://huggingface.co/datasets/Delores-Lin/MDPBench
     name: MDPBench leaderboard