Spaces:
Sleeping
Sleeping
Valentin Buchner
commited on
Commit
·
b0fe459
1
Parent(s):
b3dbb25
add leaderboard backup
Browse files- Leaderboard.md +163 -0
Leaderboard.md
ADDED
@@ -0,0 +1,163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# 🔥🏅️GenCeption Leaderboard 🏅️🔥
|
2 |
+
|
3 |
+
Evaluated MLLMs: [ChatGPT-4V](https://cdn.openai.com/papers/GPTV_System_Card.pdf), [mPLUG-Owl2](https://arxiv.org/pdf/2311.04257.pdf), [LLaVA-13B](https://arxiv.org/pdf/2304.08485.pdf), [LLaVA-7B](https://arxiv.org/pdf/2304.08485.pdf)
|
4 |
+
|
5 |
+
<table>
|
6 |
+
<tr><th>Existence </th><th>Count</th></tr>
|
7 |
+
<tr><td>
|
8 |
+
|
9 |
+
| Model | GC@3|
|
10 |
+
|--|--|
|
11 |
+
| ChatGPT-4V|0.422 |
|
12 |
+
| mPLUG-Owl2|0.323 |
|
13 |
+
| LLaVA-7B|0.308 |
|
14 |
+
| LLaVA-13B|0.305 |
|
15 |
+
|
16 |
+
</td><td>
|
17 |
+
|
18 |
+
| Model | GC@3|
|
19 |
+
|--|--|
|
20 |
+
| ChatGPT-4V|0.404 |
|
21 |
+
| mPLUG-Owl2|0.299 |
|
22 |
+
| LLaVA-13B|0.294 |
|
23 |
+
| LLaVA-7B|0.353 |
|
24 |
+
|
25 |
+
</td></tr> </table>
|
26 |
+
|
27 |
+
|
28 |
+
<table>
|
29 |
+
<tr><th>Position </th><th>Color</th></tr>
|
30 |
+
<tr><td>
|
31 |
+
|
32 |
+
| Model | GC@3|
|
33 |
+
|--|--|
|
34 |
+
| ChatGPT-4V|0.408|
|
35 |
+
| mPLUG-Owl2|0.306 |
|
36 |
+
| LLaVA-7B|0.285 |
|
37 |
+
| LLaVA-13B|0.255 |
|
38 |
+
|
39 |
+
</td><td>
|
40 |
+
|
41 |
+
| Model | GC@3|
|
42 |
+
|--|--|
|
43 |
+
| ChatGPT-4V|0.403 |
|
44 |
+
| LLaVA-13B|0.300 |
|
45 |
+
| mPLUG-Owl2|0.290 |
|
46 |
+
| LLaVA-7B|0.284 |
|
47 |
+
|
48 |
+
</td></tr> </table>
|
49 |
+
|
50 |
+
|
51 |
+
<table>
|
52 |
+
<tr><th>Poster </th><th>Celebrity</th></tr>
|
53 |
+
<tr><td>
|
54 |
+
|
55 |
+
| Model | GC@3|
|
56 |
+
|--|--|
|
57 |
+
| ChatGPT-4V|0.324|
|
58 |
+
| mPLUG-Owl2|0.243 |
|
59 |
+
| LLaVA-13B|0.215 |
|
60 |
+
| LLaVA-7B|0.214 |
|
61 |
+
|
62 |
+
</td><td>
|
63 |
+
|
64 |
+
| Model | GC@3|
|
65 |
+
|--|--|
|
66 |
+
| ChatGPT-4V|0.332 |
|
67 |
+
| mPLUG-Owl2|0.232 |
|
68 |
+
| LLaVA-13B|0.206 |
|
69 |
+
| LLaVA-7B|0.188 |
|
70 |
+
|
71 |
+
</td></tr> </table>
|
72 |
+
|
73 |
+
|
74 |
+
<table>
|
75 |
+
<tr><th>Scene </th><th>Landmark</th></tr>
|
76 |
+
<tr><td>
|
77 |
+
|
78 |
+
| Model | GC@3|
|
79 |
+
|--|--|
|
80 |
+
| ChatGPT-4V|0.393|
|
81 |
+
| mPLUG-Owl2|0.299 |
|
82 |
+
| LLaVA-13B|0.277 |
|
83 |
+
| LLaVA-7B|0.266 |
|
84 |
+
|
85 |
+
</td><td>
|
86 |
+
|
87 |
+
| Model | GC@3|
|
88 |
+
|--|--|
|
89 |
+
| ChatGPT-4V|0.353 |
|
90 |
+
| mPLUG-Owl2|0.275 |
|
91 |
+
| LLaVA-7B|0.252 |
|
92 |
+
| LLaVA-13B|0.242 |
|
93 |
+
|
94 |
+
</td></tr> </table>
|
95 |
+
|
96 |
+
|
97 |
+
<table>
|
98 |
+
<tr><th>Artwork </th><th>Commonsense Reasoning</th></tr>
|
99 |
+
<tr><td>
|
100 |
+
|
101 |
+
| Model | GC@3|
|
102 |
+
|--|--|
|
103 |
+
| ChatGPT-4V|0.421|
|
104 |
+
| mPLUG-Owl2|0.252 |
|
105 |
+
| LLaVA-13B|0.212 |
|
106 |
+
| LLaVA-7B|0.210 |
|
107 |
+
|
108 |
+
</td><td>
|
109 |
+
|
110 |
+
| Model | GC@3|
|
111 |
+
|--|--|
|
112 |
+
| ChatGPT-4V|0.471 |
|
113 |
+
| mPLUG-Owl2|0.353 |
|
114 |
+
| LLaVA-13B|0.334 |
|
115 |
+
| LLaVA-7B|0.294 |
|
116 |
+
|
117 |
+
</td></tr> </table>
|
118 |
+
|
119 |
+
|
120 |
+
<table>
|
121 |
+
<tr><th>Code Reasoning </th><th>Numerical Calculation</th></tr>
|
122 |
+
<tr><td>
|
123 |
+
|
124 |
+
| Model | GC@3|
|
125 |
+
|--|--|
|
126 |
+
| ChatGPT-4V|0.193|
|
127 |
+
| mPLUG-Owl2|0.176 |
|
128 |
+
| LLaVA-13B|0.144 |
|
129 |
+
| LLaVA-7B|0.107 |
|
130 |
+
|
131 |
+
</td><td>
|
132 |
+
|
133 |
+
| Model | GC@3|
|
134 |
+
|--|--|
|
135 |
+
| ChatGPT-4V|0.240 |
|
136 |
+
| LLaVA-13B|0.195 |
|
137 |
+
| mPLUG-Owl2|0.192 |
|
138 |
+
| LLaVA-7B|0.155 |
|
139 |
+
|
140 |
+
</td></tr> </table>
|
141 |
+
|
142 |
+
|
143 |
+
<table>
|
144 |
+
<tr><th>Text Translation </th><th>OCR</th></tr>
|
145 |
+
<tr><td>
|
146 |
+
|
147 |
+
| Model | GC@3|
|
148 |
+
|--|--|
|
149 |
+
| ChatGPT-4V|0.157|
|
150 |
+
| LLaVA-13B|0.116 |
|
151 |
+
| LLaVA-7B|0.111 |
|
152 |
+
| mPLUG-Owl2|0.081 |
|
153 |
+
|
154 |
+
</td><td>
|
155 |
+
|
156 |
+
| Model | GC@3|
|
157 |
+
|--|--|
|
158 |
+
| ChatGPT-4V|0.393 |
|
159 |
+
| mPLUG-Owl2|0.276 |
|
160 |
+
| LLaVA-13B|0.239 |
|
161 |
+
| LLaVA-7B|0.222 |
|
162 |
+
|
163 |
+
</td></tr> </table>
|