Hugging Face's logo

tiiuae
/
Falcon-OCR

Image-to-Text
Transformers
Safetensors
falcon_ocr
text-generation
falcon
ocr
vision-language
document-understanding
custom_code
Eval Results
Model card Files
xet
 Community
14

Add MDPBench private evaluation result

#14
by Delores-Lin - opened
base: refs/heads/main
←
from: refs/pr/14
Discussion Files changed
+31
-43
Files changed (1) hide show
  1. .eval_results/mdpbench.yaml +31 -43
.eval_results/mdpbench.yaml CHANGED
@@ -2,217 +2,205 @@
2
  id: Delores-Lin/MDPBench
3
  task_id: overall
4
  value: 56.3
5
- date: "2026-06-08"
6
  source:
7
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
8
  name: MDPBench leaderboard
9
  user: Delores-Lin
10
-
11
  - dataset:
12
  id: Delores-Lin/MDPBench
13
  task_id: digital
14
  value: 72.4
15
- date: "2026-06-08"
16
  source:
17
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
18
  name: MDPBench leaderboard
19
  user: Delores-Lin
20
-
21
  - dataset:
22
  id: Delores-Lin/MDPBench
23
  task_id: photographed
24
  value: 51.1
25
- date: "2026-06-08"
26
  source:
27
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
28
  name: MDPBench leaderboard
29
  user: Delores-Lin
30
-
31
  - dataset:
32
  id: Delores-Lin/MDPBench
33
  task_id: latin
34
  value: 69.3
35
- date: "2026-06-08"
36
  source:
37
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
38
  name: MDPBench leaderboard
39
  user: Delores-Lin
40
-
41
  - dataset:
42
  id: Delores-Lin/MDPBench
43
  task_id: de
44
  value: 72.4
45
- date: "2026-06-08"
46
  source:
47
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
48
  name: MDPBench leaderboard
49
  user: Delores-Lin
50
-
51
  - dataset:
52
  id: Delores-Lin/MDPBench
53
  task_id: en
54
  value: 75.0
55
- date: "2026-06-08"
56
  source:
57
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
58
  name: MDPBench leaderboard
59
  user: Delores-Lin
60
-
61
  - dataset:
62
  id: Delores-Lin/MDPBench
63
  task_id: es
64
  value: 60.9
65
- date: "2026-06-08"
66
  source:
67
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
68
  name: MDPBench leaderboard
69
  user: Delores-Lin
70
-
71
  - dataset:
72
  id: Delores-Lin/MDPBench
73
  task_id: fr
74
  value: 61.8
75
- date: "2026-06-08"
76
  source:
77
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
78
  name: MDPBench leaderboard
79
  user: Delores-Lin
80
-
81
  - dataset:
82
  id: Delores-Lin/MDPBench
83
  task_id: id
84
  value: 69.6
85
- date: "2026-06-08"
86
  source:
87
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
88
  name: MDPBench leaderboard
89
  user: Delores-Lin
90
-
91
  - dataset:
92
  id: Delores-Lin/MDPBench
93
  task_id: it
94
  value: 74.7
95
- date: "2026-06-08"
96
  source:
97
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
98
  name: MDPBench leaderboard
99
  user: Delores-Lin
100
-
101
  - dataset:
102
  id: Delores-Lin/MDPBench
103
  task_id: nl
104
  value: 71.6
105
- date: "2026-06-08"
106
  source:
107
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
108
  name: MDPBench leaderboard
109
  user: Delores-Lin
110
-
111
  - dataset:
112
  id: Delores-Lin/MDPBench
113
  task_id: pt
114
  value: 70.3
115
- date: "2026-06-08"
116
  source:
117
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
118
  name: MDPBench leaderboard
119
  user: Delores-Lin
120
-
121
  - dataset:
122
  id: Delores-Lin/MDPBench
123
  task_id: vi
124
  value: 67.8
125
- date: "2026-06-08"
126
  source:
127
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
128
  name: MDPBench leaderboard
129
  user: Delores-Lin
130
-
131
  - dataset:
132
  id: Delores-Lin/MDPBench
133
  task_id: non_latin
134
  value: 41.6
135
- date: "2026-06-08"
136
  source:
137
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
138
  name: MDPBench leaderboard
139
  user: Delores-Lin
140
-
141
  - dataset:
142
  id: Delores-Lin/MDPBench
143
  task_id: ar
144
  value: 37.9
145
- date: "2026-06-08"
146
  source:
147
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
148
  name: MDPBench leaderboard
149
  user: Delores-Lin
150
-
151
  - dataset:
152
  id: Delores-Lin/MDPBench
153
  task_id: hi
154
  value: 61.3
155
- date: "2026-06-08"
156
  source:
157
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
158
  name: MDPBench leaderboard
159
  user: Delores-Lin
160
-
161
  - dataset:
162
  id: Delores-Lin/MDPBench
163
  task_id: jp
164
  value: 39.6
165
- date: "2026-06-08"
166
  source:
167
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
168
  name: MDPBench leaderboard
169
  user: Delores-Lin
170
-
171
  - dataset:
172
  id: Delores-Lin/MDPBench
173
  task_id: ko
174
  value: 29.6
175
- date: "2026-06-08"
176
  source:
177
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
178
  name: MDPBench leaderboard
179
  user: Delores-Lin
180
-
181
  - dataset:
182
  id: Delores-Lin/MDPBench
183
  task_id: ru
184
  value: 54.0
185
- date: "2026-06-08"
186
  source:
187
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
188
  name: MDPBench leaderboard
189
  user: Delores-Lin
190
-
191
  - dataset:
192
  id: Delores-Lin/MDPBench
193
  task_id: th
194
  value: 24.8
195
- date: "2026-06-08"
196
  source:
197
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
198
  name: MDPBench leaderboard
199
  user: Delores-Lin
200
-
201
  - dataset:
202
  id: Delores-Lin/MDPBench
203
  task_id: zh
204
  value: 39.7
205
- date: "2026-06-08"
206
  source:
207
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
208
  name: MDPBench leaderboard
209
  user: Delores-Lin
210
-
211
  - dataset:
212
  id: Delores-Lin/MDPBench
213
  task_id: zh_t
214
  value: 45.6
215
- date: "2026-06-08"
 
 
 
 
 
 
 
 
 
216
  source:
217
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
218
  name: MDPBench leaderboard
 
2
  id: Delores-Lin/MDPBench
3
  task_id: overall
4
  value: 56.3
5
+ date: '2026-07-03'
6
  source:
7
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
8
  name: MDPBench leaderboard
9
  user: Delores-Lin
 
10
  - dataset:
11
  id: Delores-Lin/MDPBench
12
  task_id: digital
13
  value: 72.4
14
+ date: '2026-07-03'
15
  source:
16
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
17
  name: MDPBench leaderboard
18
  user: Delores-Lin
 
19
  - dataset:
20
  id: Delores-Lin/MDPBench
21
  task_id: photographed
22
  value: 51.1
23
+ date: '2026-07-03'
24
  source:
25
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
26
  name: MDPBench leaderboard
27
  user: Delores-Lin
 
28
  - dataset:
29
  id: Delores-Lin/MDPBench
30
  task_id: latin
31
  value: 69.3
32
+ date: '2026-07-03'
33
  source:
34
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
35
  name: MDPBench leaderboard
36
  user: Delores-Lin
 
37
  - dataset:
38
  id: Delores-Lin/MDPBench
39
  task_id: de
40
  value: 72.4
41
+ date: '2026-07-03'
42
  source:
43
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
44
  name: MDPBench leaderboard
45
  user: Delores-Lin
 
46
  - dataset:
47
  id: Delores-Lin/MDPBench
48
  task_id: en
49
  value: 75.0
50
+ date: '2026-07-03'
51
  source:
52
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
53
  name: MDPBench leaderboard
54
  user: Delores-Lin
 
55
  - dataset:
56
  id: Delores-Lin/MDPBench
57
  task_id: es
58
  value: 60.9
59
+ date: '2026-07-03'
60
  source:
61
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
62
  name: MDPBench leaderboard
63
  user: Delores-Lin
 
64
  - dataset:
65
  id: Delores-Lin/MDPBench
66
  task_id: fr
67
  value: 61.8
68
+ date: '2026-07-03'
69
  source:
70
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
71
  name: MDPBench leaderboard
72
  user: Delores-Lin
 
73
  - dataset:
74
  id: Delores-Lin/MDPBench
75
  task_id: id
76
  value: 69.6
77
+ date: '2026-07-03'
78
  source:
79
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
80
  name: MDPBench leaderboard
81
  user: Delores-Lin
 
82
  - dataset:
83
  id: Delores-Lin/MDPBench
84
  task_id: it
85
  value: 74.7
86
+ date: '2026-07-03'
87
  source:
88
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
89
  name: MDPBench leaderboard
90
  user: Delores-Lin
 
91
  - dataset:
92
  id: Delores-Lin/MDPBench
93
  task_id: nl
94
  value: 71.6
95
+ date: '2026-07-03'
96
  source:
97
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
98
  name: MDPBench leaderboard
99
  user: Delores-Lin
 
100
  - dataset:
101
  id: Delores-Lin/MDPBench
102
  task_id: pt
103
  value: 70.3
104
+ date: '2026-07-03'
105
  source:
106
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
107
  name: MDPBench leaderboard
108
  user: Delores-Lin
 
109
  - dataset:
110
  id: Delores-Lin/MDPBench
111
  task_id: vi
112
  value: 67.8
113
+ date: '2026-07-03'
114
  source:
115
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
116
  name: MDPBench leaderboard
117
  user: Delores-Lin
 
118
  - dataset:
119
  id: Delores-Lin/MDPBench
120
  task_id: non_latin
121
  value: 41.6
122
+ date: '2026-07-03'
123
  source:
124
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
125
  name: MDPBench leaderboard
126
  user: Delores-Lin
 
127
  - dataset:
128
  id: Delores-Lin/MDPBench
129
  task_id: ar
130
  value: 37.9
131
+ date: '2026-07-03'
132
  source:
133
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
134
  name: MDPBench leaderboard
135
  user: Delores-Lin
 
136
  - dataset:
137
  id: Delores-Lin/MDPBench
138
  task_id: hi
139
  value: 61.3
140
+ date: '2026-07-03'
141
  source:
142
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
143
  name: MDPBench leaderboard
144
  user: Delores-Lin
 
145
  - dataset:
146
  id: Delores-Lin/MDPBench
147
  task_id: jp
148
  value: 39.6
149
+ date: '2026-07-03'
150
  source:
151
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
152
  name: MDPBench leaderboard
153
  user: Delores-Lin
 
154
  - dataset:
155
  id: Delores-Lin/MDPBench
156
  task_id: ko
157
  value: 29.6
158
+ date: '2026-07-03'
159
  source:
160
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
161
  name: MDPBench leaderboard
162
  user: Delores-Lin
 
163
  - dataset:
164
  id: Delores-Lin/MDPBench
165
  task_id: ru
166
  value: 54.0
167
+ date: '2026-07-03'
168
  source:
169
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
170
  name: MDPBench leaderboard
171
  user: Delores-Lin
 
172
  - dataset:
173
  id: Delores-Lin/MDPBench
174
  task_id: th
175
  value: 24.8
176
+ date: '2026-07-03'
177
  source:
178
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
179
  name: MDPBench leaderboard
180
  user: Delores-Lin
 
181
  - dataset:
182
  id: Delores-Lin/MDPBench
183
  task_id: zh
184
  value: 39.7
185
+ date: '2026-07-03'
186
  source:
187
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
188
  name: MDPBench leaderboard
189
  user: Delores-Lin
 
190
  - dataset:
191
  id: Delores-Lin/MDPBench
192
  task_id: zh_t
193
  value: 45.6
194
+ date: '2026-07-03'
195
+ source:
196
+ url: https://huggingface.co/datasets/Delores-Lin/MDPBench
197
+ name: MDPBench leaderboard
198
+ user: Delores-Lin
199
+ - dataset:
200
+ id: Delores-Lin/MDPBench
201
+ task_id: private
202
+ value: 58.5
203
+ date: '2026-07-03'
204
  source:
205
  url: https://huggingface.co/datasets/Delores-Lin/MDPBench
206
  name: MDPBench leaderboard