Update MDPBench private evaluation result

#3
Files changed (1) hide show
  1. .eval_results/mdpbench.yaml +31 -22
.eval_results/mdpbench.yaml CHANGED
@@ -2,7 +2,7 @@
2
  id: Delores-Lin/MDPBench
3
  task_id: overall
4
  value: 82.5
5
- date: '2026-07-15'
6
  source:
7
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
8
  name: MDPBench leaderboard
@@ -11,7 +11,7 @@
11
  id: Delores-Lin/MDPBench
12
  task_id: digital
13
  value: 87.9
14
- date: '2026-07-15'
15
  source:
16
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
17
  name: MDPBench leaderboard
@@ -20,7 +20,7 @@
20
  id: Delores-Lin/MDPBench
21
  task_id: photographed
22
  value: 80.7
23
- date: '2026-07-15'
24
  source:
25
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
26
  name: MDPBench leaderboard
@@ -29,7 +29,7 @@
29
  id: Delores-Lin/MDPBench
30
  task_id: latin
31
  value: 83.2
32
- date: '2026-07-15'
33
  source:
34
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
35
  name: MDPBench leaderboard
@@ -38,7 +38,7 @@
38
  id: Delores-Lin/MDPBench
39
  task_id: de
40
  value: 87.3
41
- date: '2026-07-15'
42
  source:
43
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
44
  name: MDPBench leaderboard
@@ -47,7 +47,7 @@
47
  id: Delores-Lin/MDPBench
48
  task_id: en
49
  value: 83.6
50
- date: '2026-07-15'
51
  source:
52
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
53
  name: MDPBench leaderboard
@@ -56,7 +56,7 @@
56
  id: Delores-Lin/MDPBench
57
  task_id: es
58
  value: 76.8
59
- date: '2026-07-15'
60
  source:
61
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
62
  name: MDPBench leaderboard
@@ -65,7 +65,7 @@
65
  id: Delores-Lin/MDPBench
66
  task_id: fr
67
  value: 73.6
68
- date: '2026-07-15'
69
  source:
70
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
71
  name: MDPBench leaderboard
@@ -74,7 +74,7 @@
74
  id: Delores-Lin/MDPBench
75
  task_id: id
76
  value: 85.4
77
- date: '2026-07-15'
78
  source:
79
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
80
  name: MDPBench leaderboard
@@ -83,7 +83,7 @@
83
  id: Delores-Lin/MDPBench
84
  task_id: it
85
  value: 87.2
86
- date: '2026-07-15'
87
  source:
88
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
89
  name: MDPBench leaderboard
@@ -92,7 +92,7 @@
92
  id: Delores-Lin/MDPBench
93
  task_id: nl
94
  value: 85.5
95
- date: '2026-07-15'
96
  source:
97
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
98
  name: MDPBench leaderboard
@@ -101,7 +101,7 @@
101
  id: Delores-Lin/MDPBench
102
  task_id: pt
103
  value: 87.4
104
- date: '2026-07-15'
105
  source:
106
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
107
  name: MDPBench leaderboard
@@ -110,7 +110,7 @@
110
  id: Delores-Lin/MDPBench
111
  task_id: vi
112
  value: 81.9
113
- date: '2026-07-15'
114
  source:
115
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
116
  name: MDPBench leaderboard
@@ -119,7 +119,7 @@
119
  id: Delores-Lin/MDPBench
120
  task_id: non_latin
121
  value: 81.7
122
- date: '2026-07-15'
123
  source:
124
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
125
  name: MDPBench leaderboard
@@ -128,7 +128,7 @@
128
  id: Delores-Lin/MDPBench
129
  task_id: ar
130
  value: 91.2
131
- date: '2026-07-15'
132
  source:
133
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
134
  name: MDPBench leaderboard
@@ -137,7 +137,7 @@
137
  id: Delores-Lin/MDPBench
138
  task_id: hi
139
  value: 87.1
140
- date: '2026-07-15'
141
  source:
142
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
143
  name: MDPBench leaderboard
@@ -146,7 +146,7 @@
146
  id: Delores-Lin/MDPBench
147
  task_id: jp
148
  value: 69.9
149
- date: '2026-07-15'
150
  source:
151
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
152
  name: MDPBench leaderboard
@@ -155,7 +155,7 @@
155
  id: Delores-Lin/MDPBench
156
  task_id: ko
157
  value: 88.7
158
- date: '2026-07-15'
159
  source:
160
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
161
  name: MDPBench leaderboard
@@ -164,7 +164,7 @@
164
  id: Delores-Lin/MDPBench
165
  task_id: ru
166
  value: 78.0
167
- date: '2026-07-15'
168
  source:
169
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
170
  name: MDPBench leaderboard
@@ -173,7 +173,7 @@
173
  id: Delores-Lin/MDPBench
174
  task_id: th
175
  value: 79.8
176
- date: '2026-07-15'
177
  source:
178
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
179
  name: MDPBench leaderboard
@@ -182,7 +182,7 @@
182
  id: Delores-Lin/MDPBench
183
  task_id: zh
184
  value: 84.4
185
- date: '2026-07-15'
186
  source:
187
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
188
  name: MDPBench leaderboard
@@ -191,7 +191,16 @@
191
  id: Delores-Lin/MDPBench
192
  task_id: zh_t
193
  value: 74.7
194
- date: '2026-07-15'
 
 
 
 
 
 
 
 
 
195
  source:
196
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
197
  name: MDPBench leaderboard
 
2
  id: Delores-Lin/MDPBench
3
  task_id: overall
4
  value: 82.5
5
+ date: '2026-07-17'
6
  source:
7
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
8
  name: MDPBench leaderboard
 
11
  id: Delores-Lin/MDPBench
12
  task_id: digital
13
  value: 87.9
14
+ date: '2026-07-17'
15
  source:
16
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
17
  name: MDPBench leaderboard
 
20
  id: Delores-Lin/MDPBench
21
  task_id: photographed
22
  value: 80.7
23
+ date: '2026-07-17'
24
  source:
25
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
26
  name: MDPBench leaderboard
 
29
  id: Delores-Lin/MDPBench
30
  task_id: latin
31
  value: 83.2
32
+ date: '2026-07-17'
33
  source:
34
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
35
  name: MDPBench leaderboard
 
38
  id: Delores-Lin/MDPBench
39
  task_id: de
40
  value: 87.3
41
+ date: '2026-07-17'
42
  source:
43
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
44
  name: MDPBench leaderboard
 
47
  id: Delores-Lin/MDPBench
48
  task_id: en
49
  value: 83.6
50
+ date: '2026-07-17'
51
  source:
52
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
53
  name: MDPBench leaderboard
 
56
  id: Delores-Lin/MDPBench
57
  task_id: es
58
  value: 76.8
59
+ date: '2026-07-17'
60
  source:
61
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
62
  name: MDPBench leaderboard
 
65
  id: Delores-Lin/MDPBench
66
  task_id: fr
67
  value: 73.6
68
+ date: '2026-07-17'
69
  source:
70
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
71
  name: MDPBench leaderboard
 
74
  id: Delores-Lin/MDPBench
75
  task_id: id
76
  value: 85.4
77
+ date: '2026-07-17'
78
  source:
79
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
80
  name: MDPBench leaderboard
 
83
  id: Delores-Lin/MDPBench
84
  task_id: it
85
  value: 87.2
86
+ date: '2026-07-17'
87
  source:
88
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
89
  name: MDPBench leaderboard
 
92
  id: Delores-Lin/MDPBench
93
  task_id: nl
94
  value: 85.5
95
+ date: '2026-07-17'
96
  source:
97
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
98
  name: MDPBench leaderboard
 
101
  id: Delores-Lin/MDPBench
102
  task_id: pt
103
  value: 87.4
104
+ date: '2026-07-17'
105
  source:
106
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
107
  name: MDPBench leaderboard
 
110
  id: Delores-Lin/MDPBench
111
  task_id: vi
112
  value: 81.9
113
+ date: '2026-07-17'
114
  source:
115
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
116
  name: MDPBench leaderboard
 
119
  id: Delores-Lin/MDPBench
120
  task_id: non_latin
121
  value: 81.7
122
+ date: '2026-07-17'
123
  source:
124
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
125
  name: MDPBench leaderboard
 
128
  id: Delores-Lin/MDPBench
129
  task_id: ar
130
  value: 91.2
131
+ date: '2026-07-17'
132
  source:
133
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
134
  name: MDPBench leaderboard
 
137
  id: Delores-Lin/MDPBench
138
  task_id: hi
139
  value: 87.1
140
+ date: '2026-07-17'
141
  source:
142
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
143
  name: MDPBench leaderboard
 
146
  id: Delores-Lin/MDPBench
147
  task_id: jp
148
  value: 69.9
149
+ date: '2026-07-17'
150
  source:
151
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
152
  name: MDPBench leaderboard
 
155
  id: Delores-Lin/MDPBench
156
  task_id: ko
157
  value: 88.7
158
+ date: '2026-07-17'
159
  source:
160
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
161
  name: MDPBench leaderboard
 
164
  id: Delores-Lin/MDPBench
165
  task_id: ru
166
  value: 78.0
167
+ date: '2026-07-17'
168
  source:
169
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
170
  name: MDPBench leaderboard
 
173
  id: Delores-Lin/MDPBench
174
  task_id: th
175
  value: 79.8
176
+ date: '2026-07-17'
177
  source:
178
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
179
  name: MDPBench leaderboard
 
182
  id: Delores-Lin/MDPBench
183
  task_id: zh
184
  value: 84.4
185
+ date: '2026-07-17'
186
  source:
187
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
188
  name: MDPBench leaderboard
 
191
  id: Delores-Lin/MDPBench
192
  task_id: zh_t
193
  value: 74.7
194
+ date: '2026-07-17'
195
+ source:
196
+ url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
197
+ name: MDPBench leaderboard
198
+ user: Delores-Lin
199
+ - dataset:
200
+ id: Delores-Lin/MDPBench
201
+ task_id: private
202
+ value: 84.0
203
+ date: '2026-07-17'
204
  source:
205
  url: https://huggingface.co/zenosai/MonkeyOCRv2-S-Parsing
206
  name: MDPBench leaderboard