Hugging Face's logo

OpenGVLab
/
InternVL3_5-8B

Image-Text-to-Text
Transformers
Safetensors
multilingual
internvl_chat
feature-extraction
internvl
custom_code
conversational
Eval Results
Model card Files
xet
 Community
12

Add MDPBench evaluation results

#12
by Delores-Lin - opened
base: refs/heads/main
←
from: refs/pr/12
Discussion Files changed
+198
-0
Files changed (1) hide show
  1. .eval_results/mdpbench.yaml +198 -0
.eval_results/mdpbench.yaml ADDED
@@ -0,0 +1,198 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: Delores-Lin/MDPBench
3
+ task_id: overall
4
+ value: 42.7
5
+ date: "2026-04-14"
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: 59.7
14
+ date: "2026-04-14"
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: 37.0
23
+ date: "2026-04-14"
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: 53.4
32
+ date: "2026-04-14"
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: 39.8
41
+ date: "2026-04-14"
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: 64.2
50
+ date: "2026-04-14"
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: 47.5
59
+ date: "2026-04-14"
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: 42.7
68
+ date: "2026-04-14"
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: 53.8
77
+ date: "2026-04-14"
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: 60.6
86
+ date: "2026-04-14"
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: 52.2
95
+ date: "2026-04-14"
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: 63.2
104
+ date: "2026-04-14"
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: 57.0
113
+ date: "2026-04-14"
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: 30.6
122
+ date: "2026-04-14"
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: 8.2
131
+ date: "2026-04-14"
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: 9.0
140
+ date: "2026-04-14"
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: 45.6
149
+ date: "2026-04-14"
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: 30.3
158
+ date: "2026-04-14"
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: 26.1
167
+ date: "2026-04-14"
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: 10.8
176
+ date: "2026-04-14"
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: 55.3
185
+ date: "2026-04-14"
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: 59.3
194
+ date: "2026-04-14"
195
+ source:
196
+ url: https://huggingface.co/datasets/Delores-Lin/MDPBench
197
+ name: MDPBench leaderboard
198
+ user: Delores-Lin