Spaces:
Running
Running
自良
commited on
Commit
·
512e3dd
1
Parent(s):
6ce1f2f
update leaderboard
Browse files- arena_elo/cut_off_date.txt +1 -1
- arena_elo/elo_rating/__pycache__/__init__.cpython-310.pyc +0 -0
- arena_elo/elo_rating/__pycache__/basic_stats.cpython-310.pyc +0 -0
- arena_elo/elo_rating/__pycache__/clean_battle_data.cpython-310.pyc +0 -0
- arena_elo/elo_rating/__pycache__/elo_analysis.cpython-310.pyc +0 -0
- arena_elo/elo_rating/__pycache__/generate_leaderboard.cpython-310.pyc +0 -0
- arena_elo/elo_rating/__pycache__/model_registry.cpython-310.pyc +0 -0
- arena_elo/elo_rating/__pycache__/utils.cpython-310.pyc +0 -0
- arena_elo/results/20250108/clean_battle.json +634 -0
- arena_elo/results/20250108/elo_results.pkl +3 -0
- arena_elo/results/20250108/leaderboard.csv +8 -0
- arena_elo/results/latest/clean_battle.json +105 -33
- arena_elo/results/latest/elo_results.pkl +2 -2
- arena_elo/results/latest/leaderboard.csv +7 -8
arena_elo/cut_off_date.txt
CHANGED
@@ -1 +1 @@
|
|
1 |
-
|
|
|
1 |
+
20250108
|
arena_elo/elo_rating/__pycache__/__init__.cpython-310.pyc
CHANGED
Binary files a/arena_elo/elo_rating/__pycache__/__init__.cpython-310.pyc and b/arena_elo/elo_rating/__pycache__/__init__.cpython-310.pyc differ
|
|
arena_elo/elo_rating/__pycache__/basic_stats.cpython-310.pyc
CHANGED
Binary files a/arena_elo/elo_rating/__pycache__/basic_stats.cpython-310.pyc and b/arena_elo/elo_rating/__pycache__/basic_stats.cpython-310.pyc differ
|
|
arena_elo/elo_rating/__pycache__/clean_battle_data.cpython-310.pyc
CHANGED
Binary files a/arena_elo/elo_rating/__pycache__/clean_battle_data.cpython-310.pyc and b/arena_elo/elo_rating/__pycache__/clean_battle_data.cpython-310.pyc differ
|
|
arena_elo/elo_rating/__pycache__/elo_analysis.cpython-310.pyc
CHANGED
Binary files a/arena_elo/elo_rating/__pycache__/elo_analysis.cpython-310.pyc and b/arena_elo/elo_rating/__pycache__/elo_analysis.cpython-310.pyc differ
|
|
arena_elo/elo_rating/__pycache__/generate_leaderboard.cpython-310.pyc
CHANGED
Binary files a/arena_elo/elo_rating/__pycache__/generate_leaderboard.cpython-310.pyc and b/arena_elo/elo_rating/__pycache__/generate_leaderboard.cpython-310.pyc differ
|
|
arena_elo/elo_rating/__pycache__/model_registry.cpython-310.pyc
CHANGED
Binary files a/arena_elo/elo_rating/__pycache__/model_registry.cpython-310.pyc and b/arena_elo/elo_rating/__pycache__/model_registry.cpython-310.pyc differ
|
|
arena_elo/elo_rating/__pycache__/utils.cpython-310.pyc
CHANGED
Binary files a/arena_elo/elo_rating/__pycache__/utils.cpython-310.pyc and b/arena_elo/elo_rating/__pycache__/utils.cpython-310.pyc differ
|
|
arena_elo/results/20250108/clean_battle.json
ADDED
@@ -0,0 +1,634 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
4 |
+
"model_b": "ChatDiT",
|
5 |
+
"winner": "model_b",
|
6 |
+
"judge": "arena_user_127.0.0.1",
|
7 |
+
"anony": true,
|
8 |
+
"tstamp": 1735030427.6669
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
12 |
+
"model_b": "ChatDiT",
|
13 |
+
"winner": "model_a",
|
14 |
+
"judge": "arena_user_127.0.0.1",
|
15 |
+
"anony": true,
|
16 |
+
"tstamp": 1735030452.0238
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"model_a": "ChatDiT",
|
20 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
21 |
+
"winner": "model_a",
|
22 |
+
"judge": "arena_user_127.0.0.1",
|
23 |
+
"anony": true,
|
24 |
+
"tstamp": 1735030464.2602
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"model_a": "ChatDiT",
|
28 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
29 |
+
"winner": "model_a",
|
30 |
+
"judge": "arena_user_127.0.0.1",
|
31 |
+
"anony": true,
|
32 |
+
"tstamp": 1735030476.2328
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
36 |
+
"model_b": "ChatDiT",
|
37 |
+
"winner": "tie (bothbad)",
|
38 |
+
"judge": "arena_user_127.0.0.1",
|
39 |
+
"anony": true,
|
40 |
+
"tstamp": 1735030495.2955
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"model_a": "ChatDiT",
|
44 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
45 |
+
"winner": "tie (bothbad)",
|
46 |
+
"judge": "arena_user_127.0.0.1",
|
47 |
+
"anony": true,
|
48 |
+
"tstamp": 1735030503.418
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"model_a": "ChatDiT",
|
52 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
53 |
+
"winner": "model_a",
|
54 |
+
"judge": "arena_user_127.0.0.1",
|
55 |
+
"anony": true,
|
56 |
+
"tstamp": 1735030511.3926
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"model_a": "ChatDiT",
|
60 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
61 |
+
"winner": "tie (bothbad)",
|
62 |
+
"judge": "arena_user_127.0.0.1",
|
63 |
+
"anony": true,
|
64 |
+
"tstamp": 1735034259.9984
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"model_a": "ChatDiT",
|
68 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
69 |
+
"winner": "model_a",
|
70 |
+
"judge": "arena_user_127.0.0.1",
|
71 |
+
"anony": true,
|
72 |
+
"tstamp": 1735034275.6871
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"model_a": "ChatDiT",
|
76 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
77 |
+
"winner": "model_a",
|
78 |
+
"judge": "arena_user_127.0.0.1",
|
79 |
+
"anony": true,
|
80 |
+
"tstamp": 1735034284.7354
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
84 |
+
"model_b": "ChatDiT",
|
85 |
+
"winner": "model_a",
|
86 |
+
"judge": "arena_user_127.0.0.1",
|
87 |
+
"anony": true,
|
88 |
+
"tstamp": 1735034293.468
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"model_a": "ChatDiT",
|
92 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
93 |
+
"winner": "model_b",
|
94 |
+
"judge": "arena_user_127.0.0.1",
|
95 |
+
"anony": true,
|
96 |
+
"tstamp": 1735034303.2042
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"model_a": "ChatDiT",
|
100 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
101 |
+
"winner": "model_a",
|
102 |
+
"judge": "arena_user_127.0.0.1",
|
103 |
+
"anony": true,
|
104 |
+
"tstamp": 1735034314.1941
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
108 |
+
"model_b": "ChatDiT",
|
109 |
+
"winner": "model_a",
|
110 |
+
"judge": "arena_user_127.0.0.1",
|
111 |
+
"anony": true,
|
112 |
+
"tstamp": 1735034326.5092
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
116 |
+
"model_b": "ChatDiT",
|
117 |
+
"winner": "model_b",
|
118 |
+
"judge": "arena_user_127.0.0.1",
|
119 |
+
"anony": true,
|
120 |
+
"tstamp": 1735034331.6963
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
124 |
+
"model_b": "ChatDiT",
|
125 |
+
"winner": "tie (bothbad)",
|
126 |
+
"judge": "arena_user_127.0.0.1",
|
127 |
+
"anony": true,
|
128 |
+
"tstamp": 1735034336.5346
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"model_a": "ChatDiT",
|
132 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
133 |
+
"winner": "model_b",
|
134 |
+
"judge": "arena_user_127.0.0.1",
|
135 |
+
"anony": true,
|
136 |
+
"tstamp": 1735034351.9521
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
140 |
+
"model_b": "ChatDiT",
|
141 |
+
"winner": "model_b",
|
142 |
+
"judge": "arena_user_127.0.0.1",
|
143 |
+
"anony": true,
|
144 |
+
"tstamp": 1735034366.1775
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
148 |
+
"model_b": "ChatDiT",
|
149 |
+
"winner": "model_a",
|
150 |
+
"judge": "arena_user_127.0.0.1",
|
151 |
+
"anony": true,
|
152 |
+
"tstamp": 1735034380.5877
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"model_a": "ChatDiT",
|
156 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
157 |
+
"winner": "model_b",
|
158 |
+
"judge": "arena_user_127.0.0.1",
|
159 |
+
"anony": true,
|
160 |
+
"tstamp": 1735034384.3087
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
164 |
+
"model_b": "ChatDiT",
|
165 |
+
"winner": "model_a",
|
166 |
+
"judge": "arena_user_127.0.0.1",
|
167 |
+
"anony": true,
|
168 |
+
"tstamp": 1735034389.1583
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
172 |
+
"model_b": "ChatDiT",
|
173 |
+
"winner": "model_b",
|
174 |
+
"judge": "arena_user_127.0.0.1",
|
175 |
+
"anony": true,
|
176 |
+
"tstamp": 1735034405.9359
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
180 |
+
"model_b": "ChatDiT",
|
181 |
+
"winner": "model_b",
|
182 |
+
"judge": "arena_user_127.0.0.1",
|
183 |
+
"anony": true,
|
184 |
+
"tstamp": 1735034412.3533
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
188 |
+
"model_b": "ChatDiT",
|
189 |
+
"winner": "model_a",
|
190 |
+
"judge": "arena_user_127.0.0.1",
|
191 |
+
"anony": true,
|
192 |
+
"tstamp": 1735034419.0118
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
196 |
+
"model_b": "ChatDiT",
|
197 |
+
"winner": "model_b",
|
198 |
+
"judge": "arena_user_127.0.0.1",
|
199 |
+
"anony": true,
|
200 |
+
"tstamp": 1735034425.6972
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
204 |
+
"model_b": "ChatDiT",
|
205 |
+
"winner": "model_b",
|
206 |
+
"judge": "arena_user_127.0.0.1",
|
207 |
+
"anony": true,
|
208 |
+
"tstamp": 1735034432.5891
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"model_a": "ChatDiT",
|
212 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
213 |
+
"winner": "model_a",
|
214 |
+
"judge": "arena_user_127.0.0.1",
|
215 |
+
"anony": true,
|
216 |
+
"tstamp": 1735092762.0
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
220 |
+
"model_b": "ChatDiT",
|
221 |
+
"winner": "tie (bothbad)",
|
222 |
+
"judge": "arena_user_127.0.0.1",
|
223 |
+
"anony": true,
|
224 |
+
"tstamp": 1735092774.618
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
228 |
+
"model_b": "ChatDiT",
|
229 |
+
"winner": "model_a",
|
230 |
+
"judge": "arena_user_127.0.0.1",
|
231 |
+
"anony": true,
|
232 |
+
"tstamp": 1735092797.2067
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
236 |
+
"model_b": "ChatDiT",
|
237 |
+
"winner": "model_b",
|
238 |
+
"judge": "arena_user_127.0.0.1",
|
239 |
+
"anony": true,
|
240 |
+
"tstamp": 1735092804.6699
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
244 |
+
"model_b": "ChatDiT",
|
245 |
+
"winner": "model_a",
|
246 |
+
"judge": "arena_user_127.0.0.1",
|
247 |
+
"anony": true,
|
248 |
+
"tstamp": 1735092810.2635
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
252 |
+
"model_b": "ChatDiT",
|
253 |
+
"winner": "model_b",
|
254 |
+
"judge": "arena_user_127.0.0.1",
|
255 |
+
"anony": true,
|
256 |
+
"tstamp": 1735093113.5724
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"model_a": "ChatDiT",
|
260 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
261 |
+
"winner": "tie (bothbad)",
|
262 |
+
"judge": "arena_user_127.0.0.1",
|
263 |
+
"anony": true,
|
264 |
+
"tstamp": 1735093133.2436
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"model_a": "GPT-4o + Stable Diffusion 3 Medium",
|
268 |
+
"model_b": "GPT-4o + OmniGen",
|
269 |
+
"winner": "model_a",
|
270 |
+
"judge": "arena_user_127.0.0.1",
|
271 |
+
"anony": true,
|
272 |
+
"tstamp": 1735187628.4881
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"model_a": "GPT-4o + Stable Diffusion 3 Medium",
|
276 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
277 |
+
"winner": "model_b",
|
278 |
+
"judge": "arena_user_127.0.0.1",
|
279 |
+
"anony": true,
|
280 |
+
"tstamp": 1735187649.4872
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"model_a": "GPT-4o + Emu2",
|
284 |
+
"model_b": "ChatDiT",
|
285 |
+
"winner": "model_a",
|
286 |
+
"judge": "arena_user_127.0.0.1",
|
287 |
+
"anony": true,
|
288 |
+
"tstamp": 1735197562.2637
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
292 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
293 |
+
"winner": "model_a",
|
294 |
+
"judge": "arena_user_127.0.0.1",
|
295 |
+
"anony": true,
|
296 |
+
"tstamp": 1735197586.8438
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"model_a": "ChatDiT",
|
300 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
301 |
+
"winner": "model_a",
|
302 |
+
"judge": "arena_user_127.0.0.1",
|
303 |
+
"anony": false,
|
304 |
+
"tstamp": 1735201758.7145
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"model_a": "GPT-4o + DALLE-3",
|
308 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
309 |
+
"winner": "model_b",
|
310 |
+
"judge": "arena_user_127.0.0.1",
|
311 |
+
"anony": false,
|
312 |
+
"tstamp": 1735202083.631
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"model_a": "GPT-4o + DALLE-3",
|
316 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
317 |
+
"winner": "model_a",
|
318 |
+
"judge": "arena_user_127.0.0.1",
|
319 |
+
"anony": false,
|
320 |
+
"tstamp": 1735202099.4377
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"model_a": "GPT-4o + OmniGen",
|
324 |
+
"model_b": "ChatDiT",
|
325 |
+
"winner": "model_b",
|
326 |
+
"judge": "arena_user_127.0.0.1",
|
327 |
+
"anony": true,
|
328 |
+
"tstamp": 1735202132.8592
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"model_a": "GPT-4o + DALLE-3",
|
332 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
333 |
+
"winner": "model_b",
|
334 |
+
"judge": "arena_user_127.0.0.1",
|
335 |
+
"anony": false,
|
336 |
+
"tstamp": 1735202545.8694
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"model_a": "GPT-4o + DALLE-3",
|
340 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
341 |
+
"winner": "model_a",
|
342 |
+
"judge": "arena_user_127.0.0.1",
|
343 |
+
"anony": false,
|
344 |
+
"tstamp": 1735202565.5723
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"model_a": "GPT-4o + DALLE-3",
|
348 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
349 |
+
"winner": "tie (bothbad)",
|
350 |
+
"judge": "arena_user_127.0.0.1",
|
351 |
+
"anony": false,
|
352 |
+
"tstamp": 1735202573.0118
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"model_a": "GPT-4o + DALLE-3",
|
356 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
357 |
+
"winner": "tie (bothbad)",
|
358 |
+
"judge": "arena_user_127.0.0.1",
|
359 |
+
"anony": false,
|
360 |
+
"tstamp": 1735203523.809
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"model_a": "GPT-4o + OmniGen",
|
364 |
+
"model_b": "GPT-4o + DALLE-3",
|
365 |
+
"winner": "model_b",
|
366 |
+
"judge": "arena_user_127.0.0.1",
|
367 |
+
"anony": true,
|
368 |
+
"tstamp": 1735205600.7414
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"model_a": "ChatDiT",
|
372 |
+
"model_b": "GPT-4o + DALLE-3",
|
373 |
+
"winner": "model_a",
|
374 |
+
"judge": "arena_user_127.0.0.1",
|
375 |
+
"anony": true,
|
376 |
+
"tstamp": 1735207454.8251
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"model_a": "GPT-4o + OmniGen",
|
380 |
+
"model_b": "GPT-4o + Stable Diffusion 3 Medium",
|
381 |
+
"winner": "model_b",
|
382 |
+
"judge": "arena_user_127.0.0.1",
|
383 |
+
"anony": true,
|
384 |
+
"tstamp": 1735207466.0131
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"model_a": "GPT-4o + DALLE-3",
|
388 |
+
"model_b": "GPT-4o + Emu2",
|
389 |
+
"winner": "model_b",
|
390 |
+
"judge": "arena_user_127.0.0.1",
|
391 |
+
"anony": true,
|
392 |
+
"tstamp": 1735215923.1589
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"model_a": "GPT-4o + PixArt-Sigma",
|
396 |
+
"model_b": "GPT-4o + DALLE-3",
|
397 |
+
"winner": "model_a",
|
398 |
+
"judge": "arena_user_127.0.0.1",
|
399 |
+
"anony": true,
|
400 |
+
"tstamp": 1735215935.7597
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"model_a": "GPT-4o + OmniGen",
|
404 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
405 |
+
"winner": "tie (bothbad)",
|
406 |
+
"judge": "arena_user_127.0.0.1",
|
407 |
+
"anony": true,
|
408 |
+
"tstamp": 1735215942.7093
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"model_a": "GPT-4o + PixArt-Sigma",
|
412 |
+
"model_b": "GPT-4o + OmniGen",
|
413 |
+
"winner": "model_a",
|
414 |
+
"judge": "arena_user_127.0.0.1",
|
415 |
+
"anony": true,
|
416 |
+
"tstamp": 1735215949.7965
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"model_a": "GPT-4o + DALLE-3",
|
420 |
+
"model_b": "ChatDiT",
|
421 |
+
"winner": "model_b",
|
422 |
+
"judge": "arena_user_127.0.0.1",
|
423 |
+
"anony": true,
|
424 |
+
"tstamp": 1735215962.6898
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"model_a": "GPT-4o + Stable Diffusion 3 Medium",
|
428 |
+
"model_b": "GPT-4o + DALLE-3",
|
429 |
+
"winner": "tie (bothbad)",
|
430 |
+
"judge": "arena_user_127.0.0.1",
|
431 |
+
"anony": true,
|
432 |
+
"tstamp": 1735215968.9052
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
436 |
+
"model_b": "GPT-4o + Stable Diffusion 3 Medium",
|
437 |
+
"winner": "tie (bothbad)",
|
438 |
+
"judge": "arena_user_127.0.0.1",
|
439 |
+
"anony": true,
|
440 |
+
"tstamp": 1735215976.5079
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"model_a": "GPT-4o + Emu2",
|
444 |
+
"model_b": "GPT-4o + Stable Diffusion 3 Medium",
|
445 |
+
"winner": "model_b",
|
446 |
+
"judge": "arena_user_127.0.0.1",
|
447 |
+
"anony": true,
|
448 |
+
"tstamp": 1735215982.9709
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"model_a": "ChatDiT",
|
452 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
453 |
+
"winner": "model_a",
|
454 |
+
"judge": "arena_user_127.0.0.1",
|
455 |
+
"anony": true,
|
456 |
+
"tstamp": 1735215993.2305
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"model_a": "GPT-4o + Stable Diffusion 3 Medium",
|
460 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
461 |
+
"winner": "tie (bothbad)",
|
462 |
+
"judge": "arena_user_127.0.0.1",
|
463 |
+
"anony": true,
|
464 |
+
"tstamp": 1735215999.8713
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"model_a": "GPT-4o + PixArt-Sigma",
|
468 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
469 |
+
"winner": "model_b",
|
470 |
+
"judge": "arena_user_127.0.0.1",
|
471 |
+
"anony": true,
|
472 |
+
"tstamp": 1735216012.8216
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"model_a": "ChatDiT",
|
476 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
477 |
+
"winner": "model_a",
|
478 |
+
"judge": "arena_user_127.0.0.1",
|
479 |
+
"anony": true,
|
480 |
+
"tstamp": 1735216021.653
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"model_a": "GPT-4o + PixArt-Sigma",
|
484 |
+
"model_b": "GPT-4o + OmniGen",
|
485 |
+
"winner": "model_b",
|
486 |
+
"judge": "arena_user_127.0.0.1",
|
487 |
+
"anony": true,
|
488 |
+
"tstamp": 1735286354.5764
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"model_a": "GPT-4o + Stable Diffusion 3 Medium",
|
492 |
+
"model_b": "ChatDiT",
|
493 |
+
"winner": "tie (bothbad)",
|
494 |
+
"judge": "arena_user_127.0.0.1",
|
495 |
+
"anony": true,
|
496 |
+
"tstamp": 1735286365.2329
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"model_a": "GPT-4o + Emu2",
|
500 |
+
"model_b": "ChatDiT",
|
501 |
+
"winner": "model_a",
|
502 |
+
"judge": "arena_user_127.0.0.1",
|
503 |
+
"anony": true,
|
504 |
+
"tstamp": 1735286374.6751
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
508 |
+
"model_b": "GPT-4o + Emu2",
|
509 |
+
"winner": "model_a",
|
510 |
+
"judge": "arena_user_127.0.0.1",
|
511 |
+
"anony": true,
|
512 |
+
"tstamp": 1735286382.1211
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"model_a": "GPT-4o + PixArt-Sigma",
|
516 |
+
"model_b": "GPT-4o + OmniGen",
|
517 |
+
"winner": "model_a",
|
518 |
+
"judge": "arena_user_127.0.0.1",
|
519 |
+
"anony": true,
|
520 |
+
"tstamp": 1735288723.7052
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
524 |
+
"model_b": "GPT-4o + DALLE-3",
|
525 |
+
"winner": "model_a",
|
526 |
+
"judge": "arena_user_127.0.0.1",
|
527 |
+
"anony": true,
|
528 |
+
"tstamp": 1735288729.3576
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"model_a": "GPT-4o + PixArt-Sigma",
|
532 |
+
"model_b": "GPT-4o + OmniGen",
|
533 |
+
"winner": "model_a",
|
534 |
+
"judge": "arena_user_127.0.0.1",
|
535 |
+
"anony": true,
|
536 |
+
"tstamp": 1735288749.1708
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
540 |
+
"model_b": "GPT-4o + Stable Diffusion 3 Medium",
|
541 |
+
"winner": "model_a",
|
542 |
+
"judge": "arena_user_127.0.0.1",
|
543 |
+
"anony": true,
|
544 |
+
"tstamp": 1736305459.7554
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"model_a": "GPT-4o + Emu2",
|
548 |
+
"model_b": "GPT-4o + DALLE-3",
|
549 |
+
"winner": "model_b",
|
550 |
+
"judge": "arena_user_127.0.0.1",
|
551 |
+
"anony": true,
|
552 |
+
"tstamp": 1736305568.3703
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"model_a": "GPT-4o + Emu2",
|
556 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
557 |
+
"winner": "model_b",
|
558 |
+
"judge": "arena_user_127.0.0.1",
|
559 |
+
"anony": true,
|
560 |
+
"tstamp": 1736305578.3648
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"model_a": "GPT-4o + OmniGen",
|
564 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
565 |
+
"winner": "model_b",
|
566 |
+
"judge": "arena_user_10.16.39.228",
|
567 |
+
"anony": true,
|
568 |
+
"tstamp": 1736316463.4086
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"model_a": "GPT-4o + OmniGen",
|
572 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
573 |
+
"winner": "model_a",
|
574 |
+
"judge": "arena_user_10.16.30.109",
|
575 |
+
"anony": true,
|
576 |
+
"tstamp": 1736316525.3474
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"model_a": "GPT-4o + Stable Diffusion 3 Medium",
|
580 |
+
"model_b": "GPT-4o + DALLE-3",
|
581 |
+
"winner": "tie (bothbad)",
|
582 |
+
"judge": "arena_user_10.16.9.166",
|
583 |
+
"anony": false,
|
584 |
+
"tstamp": 1736317079.2219
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"model_a": "GPT-4o + Stable Diffusion 3 Medium",
|
588 |
+
"model_b": "GPT-4o + OmniGen",
|
589 |
+
"winner": "model_a",
|
590 |
+
"judge": "arena_user_10.16.39.228",
|
591 |
+
"anony": true,
|
592 |
+
"tstamp": 1736317103.5229
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"model_a": "ChatDiT",
|
596 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
597 |
+
"winner": "model_b",
|
598 |
+
"judge": "arena_user_10.16.9.166",
|
599 |
+
"anony": true,
|
600 |
+
"tstamp": 1736317151.2313
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"model_a": "GPT-4o + Emu2",
|
604 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
605 |
+
"winner": "model_b",
|
606 |
+
"judge": "arena_user_10.16.24.150",
|
607 |
+
"anony": true,
|
608 |
+
"tstamp": 1736317260.068
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"model_a": "GPT-4o + PixArt-Sigma",
|
612 |
+
"model_b": "GPT-4o + OmniGen",
|
613 |
+
"winner": "model_b",
|
614 |
+
"judge": "arena_user_172.18.13.178",
|
615 |
+
"anony": true,
|
616 |
+
"tstamp": 1736320695.0812
|
617 |
+
},
|
618 |
+
{
|
619 |
+
"model_a": "ChatDiT",
|
620 |
+
"model_b": "GPT-4o + Stable Diffusion 3 Medium",
|
621 |
+
"winner": "model_a",
|
622 |
+
"judge": "arena_user_10.16.43.67",
|
623 |
+
"anony": true,
|
624 |
+
"tstamp": 1736321735.4094
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"model_a": "GPT-4o + PixArt-Sigma",
|
628 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
629 |
+
"winner": "model_a",
|
630 |
+
"judge": "arena_user_10.16.24.150",
|
631 |
+
"anony": true,
|
632 |
+
"tstamp": 1736335598.6764
|
633 |
+
}
|
634 |
+
]
|
arena_elo/results/20250108/elo_results.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bcf8ae6947143cd90ff0649dfa15dbfb465397de67be4e0b39ff34e0f705df3
|
3 |
+
size 57457
|
arena_elo/results/20250108/leaderboard.csv
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
key,Model,Arena Elo rating (anony),Arena Elo rating (full),license,creator,link
|
2 |
+
ChatDiT,ChatDiT,1141.9082940955832,1141.3534939692347,MIT License,Tongyi Lab,https://github.com/ali-vilab/ChatDiT
|
3 |
+
GPT-4o + FLUX.1 [dev],GPT-4o + FLUX.1 [dev],1106.4413262289752,1096.9228824729828,FLUX.1 [dev] Non-Commercial License,Black Forest Labs,https://huggingface.co/black-forest-labs/FLUX.1-dev
|
4 |
+
GPT-4o + Stable Diffusion 3 Medium,GPT-4o + Stable Diffusion 3 Medium,1037.4899722855018,1026.2775791477911,Stability AI Community License,Stability AI,https://huggingface.co/stabilityai/stable-diffusion-3-medium
|
5 |
+
GPT-4o + PixArt-Sigma,GPT-4o + PixArt-Sigma,1030.2322549298108,1003.2938185806802,CreativeML Open RAIL++-M License,Huawei Noah's Ark Lab,https://huggingface.co/PixArt-alpha/PixArt-Sigma-XL-2-1024-MS
|
6 |
+
GPT-4o + Emu2,GPT-4o + Emu2,941.1199462147184,946.5946854676025,Apache License 2.0,BAAI,https://huggingface.co/BAAI/Emu2
|
7 |
+
GPT-4o + DALLE-3,GPT-4o + DALLE-3,884.7999841743839,941.2186221773824,OpenAI Terms of Use,OpenAI,https://openai.com/index/dall-e-3/
|
8 |
+
GPT-4o + OmniGen,GPT-4o + OmniGen,858.0082220710267,844.3389181843263,MIT License,BAAI,https://huggingface.co/spaces/Shitao/OmniGen
|
arena_elo/results/latest/clean_battle.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
[
|
2 |
{
|
3 |
-
"model_a": "FLUX
|
4 |
"model_b": "ChatDiT",
|
5 |
"winner": "model_b",
|
6 |
"judge": "arena_user_127.0.0.1",
|
@@ -8,7 +8,7 @@
|
|
8 |
"tstamp": 1735030427.6669
|
9 |
},
|
10 |
{
|
11 |
-
"model_a": "FLUX
|
12 |
"model_b": "ChatDiT",
|
13 |
"winner": "model_a",
|
14 |
"judge": "arena_user_127.0.0.1",
|
@@ -17,7 +17,7 @@
|
|
17 |
},
|
18 |
{
|
19 |
"model_a": "ChatDiT",
|
20 |
-
"model_b": "FLUX
|
21 |
"winner": "model_a",
|
22 |
"judge": "arena_user_127.0.0.1",
|
23 |
"anony": true,
|
@@ -25,14 +25,14 @@
|
|
25 |
},
|
26 |
{
|
27 |
"model_a": "ChatDiT",
|
28 |
-
"model_b": "FLUX
|
29 |
"winner": "model_a",
|
30 |
"judge": "arena_user_127.0.0.1",
|
31 |
"anony": true,
|
32 |
"tstamp": 1735030476.2328
|
33 |
},
|
34 |
{
|
35 |
-
"model_a": "FLUX
|
36 |
"model_b": "ChatDiT",
|
37 |
"winner": "tie (bothbad)",
|
38 |
"judge": "arena_user_127.0.0.1",
|
@@ -41,7 +41,7 @@
|
|
41 |
},
|
42 |
{
|
43 |
"model_a": "ChatDiT",
|
44 |
-
"model_b": "FLUX
|
45 |
"winner": "tie (bothbad)",
|
46 |
"judge": "arena_user_127.0.0.1",
|
47 |
"anony": true,
|
@@ -49,7 +49,7 @@
|
|
49 |
},
|
50 |
{
|
51 |
"model_a": "ChatDiT",
|
52 |
-
"model_b": "FLUX
|
53 |
"winner": "model_a",
|
54 |
"judge": "arena_user_127.0.0.1",
|
55 |
"anony": true,
|
@@ -57,7 +57,7 @@
|
|
57 |
},
|
58 |
{
|
59 |
"model_a": "ChatDiT",
|
60 |
-
"model_b": "FLUX
|
61 |
"winner": "tie (bothbad)",
|
62 |
"judge": "arena_user_127.0.0.1",
|
63 |
"anony": true,
|
@@ -65,7 +65,7 @@
|
|
65 |
},
|
66 |
{
|
67 |
"model_a": "ChatDiT",
|
68 |
-
"model_b": "FLUX
|
69 |
"winner": "model_a",
|
70 |
"judge": "arena_user_127.0.0.1",
|
71 |
"anony": true,
|
@@ -73,14 +73,14 @@
|
|
73 |
},
|
74 |
{
|
75 |
"model_a": "ChatDiT",
|
76 |
-
"model_b": "FLUX
|
77 |
"winner": "model_a",
|
78 |
"judge": "arena_user_127.0.0.1",
|
79 |
"anony": true,
|
80 |
"tstamp": 1735034284.7354
|
81 |
},
|
82 |
{
|
83 |
-
"model_a": "FLUX
|
84 |
"model_b": "ChatDiT",
|
85 |
"winner": "model_a",
|
86 |
"judge": "arena_user_127.0.0.1",
|
@@ -89,7 +89,7 @@
|
|
89 |
},
|
90 |
{
|
91 |
"model_a": "ChatDiT",
|
92 |
-
"model_b": "FLUX
|
93 |
"winner": "model_b",
|
94 |
"judge": "arena_user_127.0.0.1",
|
95 |
"anony": true,
|
@@ -97,14 +97,14 @@
|
|
97 |
},
|
98 |
{
|
99 |
"model_a": "ChatDiT",
|
100 |
-
"model_b": "FLUX
|
101 |
"winner": "model_a",
|
102 |
"judge": "arena_user_127.0.0.1",
|
103 |
"anony": true,
|
104 |
"tstamp": 1735034314.1941
|
105 |
},
|
106 |
{
|
107 |
-
"model_a": "FLUX
|
108 |
"model_b": "ChatDiT",
|
109 |
"winner": "model_a",
|
110 |
"judge": "arena_user_127.0.0.1",
|
@@ -112,7 +112,7 @@
|
|
112 |
"tstamp": 1735034326.5092
|
113 |
},
|
114 |
{
|
115 |
-
"model_a": "FLUX
|
116 |
"model_b": "ChatDiT",
|
117 |
"winner": "model_b",
|
118 |
"judge": "arena_user_127.0.0.1",
|
@@ -120,7 +120,7 @@
|
|
120 |
"tstamp": 1735034331.6963
|
121 |
},
|
122 |
{
|
123 |
-
"model_a": "FLUX
|
124 |
"model_b": "ChatDiT",
|
125 |
"winner": "tie (bothbad)",
|
126 |
"judge": "arena_user_127.0.0.1",
|
@@ -129,14 +129,14 @@
|
|
129 |
},
|
130 |
{
|
131 |
"model_a": "ChatDiT",
|
132 |
-
"model_b": "FLUX
|
133 |
"winner": "model_b",
|
134 |
"judge": "arena_user_127.0.0.1",
|
135 |
"anony": true,
|
136 |
"tstamp": 1735034351.9521
|
137 |
},
|
138 |
{
|
139 |
-
"model_a": "FLUX
|
140 |
"model_b": "ChatDiT",
|
141 |
"winner": "model_b",
|
142 |
"judge": "arena_user_127.0.0.1",
|
@@ -144,7 +144,7 @@
|
|
144 |
"tstamp": 1735034366.1775
|
145 |
},
|
146 |
{
|
147 |
-
"model_a": "FLUX
|
148 |
"model_b": "ChatDiT",
|
149 |
"winner": "model_a",
|
150 |
"judge": "arena_user_127.0.0.1",
|
@@ -153,14 +153,14 @@
|
|
153 |
},
|
154 |
{
|
155 |
"model_a": "ChatDiT",
|
156 |
-
"model_b": "FLUX
|
157 |
"winner": "model_b",
|
158 |
"judge": "arena_user_127.0.0.1",
|
159 |
"anony": true,
|
160 |
"tstamp": 1735034384.3087
|
161 |
},
|
162 |
{
|
163 |
-
"model_a": "FLUX
|
164 |
"model_b": "ChatDiT",
|
165 |
"winner": "model_a",
|
166 |
"judge": "arena_user_127.0.0.1",
|
@@ -168,7 +168,7 @@
|
|
168 |
"tstamp": 1735034389.1583
|
169 |
},
|
170 |
{
|
171 |
-
"model_a": "FLUX
|
172 |
"model_b": "ChatDiT",
|
173 |
"winner": "model_b",
|
174 |
"judge": "arena_user_127.0.0.1",
|
@@ -176,7 +176,7 @@
|
|
176 |
"tstamp": 1735034405.9359
|
177 |
},
|
178 |
{
|
179 |
-
"model_a": "FLUX
|
180 |
"model_b": "ChatDiT",
|
181 |
"winner": "model_b",
|
182 |
"judge": "arena_user_127.0.0.1",
|
@@ -184,7 +184,7 @@
|
|
184 |
"tstamp": 1735034412.3533
|
185 |
},
|
186 |
{
|
187 |
-
"model_a": "FLUX
|
188 |
"model_b": "ChatDiT",
|
189 |
"winner": "model_a",
|
190 |
"judge": "arena_user_127.0.0.1",
|
@@ -192,7 +192,7 @@
|
|
192 |
"tstamp": 1735034419.0118
|
193 |
},
|
194 |
{
|
195 |
-
"model_a": "FLUX
|
196 |
"model_b": "ChatDiT",
|
197 |
"winner": "model_b",
|
198 |
"judge": "arena_user_127.0.0.1",
|
@@ -200,7 +200,7 @@
|
|
200 |
"tstamp": 1735034425.6972
|
201 |
},
|
202 |
{
|
203 |
-
"model_a": "FLUX
|
204 |
"model_b": "ChatDiT",
|
205 |
"winner": "model_b",
|
206 |
"judge": "arena_user_127.0.0.1",
|
@@ -209,14 +209,14 @@
|
|
209 |
},
|
210 |
{
|
211 |
"model_a": "ChatDiT",
|
212 |
-
"model_b": "FLUX
|
213 |
"winner": "model_a",
|
214 |
"judge": "arena_user_127.0.0.1",
|
215 |
"anony": true,
|
216 |
"tstamp": 1735092762.0
|
217 |
},
|
218 |
{
|
219 |
-
"model_a": "FLUX
|
220 |
"model_b": "ChatDiT",
|
221 |
"winner": "tie (bothbad)",
|
222 |
"judge": "arena_user_127.0.0.1",
|
@@ -224,7 +224,7 @@
|
|
224 |
"tstamp": 1735092774.618
|
225 |
},
|
226 |
{
|
227 |
-
"model_a": "FLUX
|
228 |
"model_b": "ChatDiT",
|
229 |
"winner": "model_a",
|
230 |
"judge": "arena_user_127.0.0.1",
|
@@ -232,7 +232,7 @@
|
|
232 |
"tstamp": 1735092797.2067
|
233 |
},
|
234 |
{
|
235 |
-
"model_a": "FLUX
|
236 |
"model_b": "ChatDiT",
|
237 |
"winner": "model_b",
|
238 |
"judge": "arena_user_127.0.0.1",
|
@@ -240,7 +240,7 @@
|
|
240 |
"tstamp": 1735092804.6699
|
241 |
},
|
242 |
{
|
243 |
-
"model_a": "FLUX
|
244 |
"model_b": "ChatDiT",
|
245 |
"winner": "model_a",
|
246 |
"judge": "arena_user_127.0.0.1",
|
@@ -248,7 +248,7 @@
|
|
248 |
"tstamp": 1735092810.2635
|
249 |
},
|
250 |
{
|
251 |
-
"model_a": "FLUX
|
252 |
"model_b": "ChatDiT",
|
253 |
"winner": "model_b",
|
254 |
"judge": "arena_user_127.0.0.1",
|
@@ -257,7 +257,7 @@
|
|
257 |
},
|
258 |
{
|
259 |
"model_a": "ChatDiT",
|
260 |
-
"model_b": "FLUX
|
261 |
"winner": "tie (bothbad)",
|
262 |
"judge": "arena_user_127.0.0.1",
|
263 |
"anony": true,
|
@@ -558,5 +558,77 @@
|
|
558 |
"judge": "arena_user_127.0.0.1",
|
559 |
"anony": true,
|
560 |
"tstamp": 1736305578.3648
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
561 |
}
|
562 |
]
|
|
|
1 |
[
|
2 |
{
|
3 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
4 |
"model_b": "ChatDiT",
|
5 |
"winner": "model_b",
|
6 |
"judge": "arena_user_127.0.0.1",
|
|
|
8 |
"tstamp": 1735030427.6669
|
9 |
},
|
10 |
{
|
11 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
12 |
"model_b": "ChatDiT",
|
13 |
"winner": "model_a",
|
14 |
"judge": "arena_user_127.0.0.1",
|
|
|
17 |
},
|
18 |
{
|
19 |
"model_a": "ChatDiT",
|
20 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
21 |
"winner": "model_a",
|
22 |
"judge": "arena_user_127.0.0.1",
|
23 |
"anony": true,
|
|
|
25 |
},
|
26 |
{
|
27 |
"model_a": "ChatDiT",
|
28 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
29 |
"winner": "model_a",
|
30 |
"judge": "arena_user_127.0.0.1",
|
31 |
"anony": true,
|
32 |
"tstamp": 1735030476.2328
|
33 |
},
|
34 |
{
|
35 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
36 |
"model_b": "ChatDiT",
|
37 |
"winner": "tie (bothbad)",
|
38 |
"judge": "arena_user_127.0.0.1",
|
|
|
41 |
},
|
42 |
{
|
43 |
"model_a": "ChatDiT",
|
44 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
45 |
"winner": "tie (bothbad)",
|
46 |
"judge": "arena_user_127.0.0.1",
|
47 |
"anony": true,
|
|
|
49 |
},
|
50 |
{
|
51 |
"model_a": "ChatDiT",
|
52 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
53 |
"winner": "model_a",
|
54 |
"judge": "arena_user_127.0.0.1",
|
55 |
"anony": true,
|
|
|
57 |
},
|
58 |
{
|
59 |
"model_a": "ChatDiT",
|
60 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
61 |
"winner": "tie (bothbad)",
|
62 |
"judge": "arena_user_127.0.0.1",
|
63 |
"anony": true,
|
|
|
65 |
},
|
66 |
{
|
67 |
"model_a": "ChatDiT",
|
68 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
69 |
"winner": "model_a",
|
70 |
"judge": "arena_user_127.0.0.1",
|
71 |
"anony": true,
|
|
|
73 |
},
|
74 |
{
|
75 |
"model_a": "ChatDiT",
|
76 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
77 |
"winner": "model_a",
|
78 |
"judge": "arena_user_127.0.0.1",
|
79 |
"anony": true,
|
80 |
"tstamp": 1735034284.7354
|
81 |
},
|
82 |
{
|
83 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
84 |
"model_b": "ChatDiT",
|
85 |
"winner": "model_a",
|
86 |
"judge": "arena_user_127.0.0.1",
|
|
|
89 |
},
|
90 |
{
|
91 |
"model_a": "ChatDiT",
|
92 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
93 |
"winner": "model_b",
|
94 |
"judge": "arena_user_127.0.0.1",
|
95 |
"anony": true,
|
|
|
97 |
},
|
98 |
{
|
99 |
"model_a": "ChatDiT",
|
100 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
101 |
"winner": "model_a",
|
102 |
"judge": "arena_user_127.0.0.1",
|
103 |
"anony": true,
|
104 |
"tstamp": 1735034314.1941
|
105 |
},
|
106 |
{
|
107 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
108 |
"model_b": "ChatDiT",
|
109 |
"winner": "model_a",
|
110 |
"judge": "arena_user_127.0.0.1",
|
|
|
112 |
"tstamp": 1735034326.5092
|
113 |
},
|
114 |
{
|
115 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
116 |
"model_b": "ChatDiT",
|
117 |
"winner": "model_b",
|
118 |
"judge": "arena_user_127.0.0.1",
|
|
|
120 |
"tstamp": 1735034331.6963
|
121 |
},
|
122 |
{
|
123 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
124 |
"model_b": "ChatDiT",
|
125 |
"winner": "tie (bothbad)",
|
126 |
"judge": "arena_user_127.0.0.1",
|
|
|
129 |
},
|
130 |
{
|
131 |
"model_a": "ChatDiT",
|
132 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
133 |
"winner": "model_b",
|
134 |
"judge": "arena_user_127.0.0.1",
|
135 |
"anony": true,
|
136 |
"tstamp": 1735034351.9521
|
137 |
},
|
138 |
{
|
139 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
140 |
"model_b": "ChatDiT",
|
141 |
"winner": "model_b",
|
142 |
"judge": "arena_user_127.0.0.1",
|
|
|
144 |
"tstamp": 1735034366.1775
|
145 |
},
|
146 |
{
|
147 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
148 |
"model_b": "ChatDiT",
|
149 |
"winner": "model_a",
|
150 |
"judge": "arena_user_127.0.0.1",
|
|
|
153 |
},
|
154 |
{
|
155 |
"model_a": "ChatDiT",
|
156 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
157 |
"winner": "model_b",
|
158 |
"judge": "arena_user_127.0.0.1",
|
159 |
"anony": true,
|
160 |
"tstamp": 1735034384.3087
|
161 |
},
|
162 |
{
|
163 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
164 |
"model_b": "ChatDiT",
|
165 |
"winner": "model_a",
|
166 |
"judge": "arena_user_127.0.0.1",
|
|
|
168 |
"tstamp": 1735034389.1583
|
169 |
},
|
170 |
{
|
171 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
172 |
"model_b": "ChatDiT",
|
173 |
"winner": "model_b",
|
174 |
"judge": "arena_user_127.0.0.1",
|
|
|
176 |
"tstamp": 1735034405.9359
|
177 |
},
|
178 |
{
|
179 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
180 |
"model_b": "ChatDiT",
|
181 |
"winner": "model_b",
|
182 |
"judge": "arena_user_127.0.0.1",
|
|
|
184 |
"tstamp": 1735034412.3533
|
185 |
},
|
186 |
{
|
187 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
188 |
"model_b": "ChatDiT",
|
189 |
"winner": "model_a",
|
190 |
"judge": "arena_user_127.0.0.1",
|
|
|
192 |
"tstamp": 1735034419.0118
|
193 |
},
|
194 |
{
|
195 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
196 |
"model_b": "ChatDiT",
|
197 |
"winner": "model_b",
|
198 |
"judge": "arena_user_127.0.0.1",
|
|
|
200 |
"tstamp": 1735034425.6972
|
201 |
},
|
202 |
{
|
203 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
204 |
"model_b": "ChatDiT",
|
205 |
"winner": "model_b",
|
206 |
"judge": "arena_user_127.0.0.1",
|
|
|
209 |
},
|
210 |
{
|
211 |
"model_a": "ChatDiT",
|
212 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
213 |
"winner": "model_a",
|
214 |
"judge": "arena_user_127.0.0.1",
|
215 |
"anony": true,
|
216 |
"tstamp": 1735092762.0
|
217 |
},
|
218 |
{
|
219 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
220 |
"model_b": "ChatDiT",
|
221 |
"winner": "tie (bothbad)",
|
222 |
"judge": "arena_user_127.0.0.1",
|
|
|
224 |
"tstamp": 1735092774.618
|
225 |
},
|
226 |
{
|
227 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
228 |
"model_b": "ChatDiT",
|
229 |
"winner": "model_a",
|
230 |
"judge": "arena_user_127.0.0.1",
|
|
|
232 |
"tstamp": 1735092797.2067
|
233 |
},
|
234 |
{
|
235 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
236 |
"model_b": "ChatDiT",
|
237 |
"winner": "model_b",
|
238 |
"judge": "arena_user_127.0.0.1",
|
|
|
240 |
"tstamp": 1735092804.6699
|
241 |
},
|
242 |
{
|
243 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
244 |
"model_b": "ChatDiT",
|
245 |
"winner": "model_a",
|
246 |
"judge": "arena_user_127.0.0.1",
|
|
|
248 |
"tstamp": 1735092810.2635
|
249 |
},
|
250 |
{
|
251 |
+
"model_a": "GPT-4o + FLUX.1 [dev]",
|
252 |
"model_b": "ChatDiT",
|
253 |
"winner": "model_b",
|
254 |
"judge": "arena_user_127.0.0.1",
|
|
|
257 |
},
|
258 |
{
|
259 |
"model_a": "ChatDiT",
|
260 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
261 |
"winner": "tie (bothbad)",
|
262 |
"judge": "arena_user_127.0.0.1",
|
263 |
"anony": true,
|
|
|
558 |
"judge": "arena_user_127.0.0.1",
|
559 |
"anony": true,
|
560 |
"tstamp": 1736305578.3648
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"model_a": "GPT-4o + OmniGen",
|
564 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
565 |
+
"winner": "model_b",
|
566 |
+
"judge": "arena_user_10.16.39.228",
|
567 |
+
"anony": true,
|
568 |
+
"tstamp": 1736316463.4086
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"model_a": "GPT-4o + OmniGen",
|
572 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
573 |
+
"winner": "model_a",
|
574 |
+
"judge": "arena_user_10.16.30.109",
|
575 |
+
"anony": true,
|
576 |
+
"tstamp": 1736316525.3474
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"model_a": "GPT-4o + Stable Diffusion 3 Medium",
|
580 |
+
"model_b": "GPT-4o + DALLE-3",
|
581 |
+
"winner": "tie (bothbad)",
|
582 |
+
"judge": "arena_user_10.16.9.166",
|
583 |
+
"anony": false,
|
584 |
+
"tstamp": 1736317079.2219
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"model_a": "GPT-4o + Stable Diffusion 3 Medium",
|
588 |
+
"model_b": "GPT-4o + OmniGen",
|
589 |
+
"winner": "model_a",
|
590 |
+
"judge": "arena_user_10.16.39.228",
|
591 |
+
"anony": true,
|
592 |
+
"tstamp": 1736317103.5229
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"model_a": "ChatDiT",
|
596 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
597 |
+
"winner": "model_b",
|
598 |
+
"judge": "arena_user_10.16.9.166",
|
599 |
+
"anony": true,
|
600 |
+
"tstamp": 1736317151.2313
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"model_a": "GPT-4o + Emu2",
|
604 |
+
"model_b": "GPT-4o + PixArt-Sigma",
|
605 |
+
"winner": "model_b",
|
606 |
+
"judge": "arena_user_10.16.24.150",
|
607 |
+
"anony": true,
|
608 |
+
"tstamp": 1736317260.068
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"model_a": "GPT-4o + PixArt-Sigma",
|
612 |
+
"model_b": "GPT-4o + OmniGen",
|
613 |
+
"winner": "model_b",
|
614 |
+
"judge": "arena_user_172.18.13.178",
|
615 |
+
"anony": true,
|
616 |
+
"tstamp": 1736320695.0812
|
617 |
+
},
|
618 |
+
{
|
619 |
+
"model_a": "ChatDiT",
|
620 |
+
"model_b": "GPT-4o + Stable Diffusion 3 Medium",
|
621 |
+
"winner": "model_a",
|
622 |
+
"judge": "arena_user_10.16.43.67",
|
623 |
+
"anony": true,
|
624 |
+
"tstamp": 1736321735.4094
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"model_a": "GPT-4o + PixArt-Sigma",
|
628 |
+
"model_b": "GPT-4o + FLUX.1 [dev]",
|
629 |
+
"winner": "model_a",
|
630 |
+
"judge": "arena_user_10.16.24.150",
|
631 |
+
"anony": true,
|
632 |
+
"tstamp": 1736335598.6764
|
633 |
}
|
634 |
]
|
arena_elo/results/latest/elo_results.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bcf8ae6947143cd90ff0649dfa15dbfb465397de67be4e0b39ff34e0f705df3
|
3 |
+
size 57457
|
arena_elo/results/latest/leaderboard.csv
CHANGED
@@ -1,9 +1,8 @@
|
|
1 |
key,Model,Arena Elo rating (anony),Arena Elo rating (full),license,creator,link
|
2 |
-
|
3 |
-
GPT-4o +
|
4 |
-
|
5 |
-
|
6 |
-
GPT-4o + Emu2,GPT-4o + Emu2,
|
7 |
-
GPT-4o +
|
8 |
-
GPT-4o +
|
9 |
-
GPT-4o + OmniGen,GPT-4o + OmniGen,727.5684009612476,717.0935607561696,MIT License,BAAI,https://huggingface.co/spaces/Shitao/OmniGen
|
|
|
1 |
key,Model,Arena Elo rating (anony),Arena Elo rating (full),license,creator,link
|
2 |
+
ChatDiT,ChatDiT,1141.9082940955832,1141.3534939692347,MIT License,Tongyi Lab,https://github.com/ali-vilab/ChatDiT
|
3 |
+
GPT-4o + FLUX.1 [dev],GPT-4o + FLUX.1 [dev],1106.4413262289752,1096.9228824729828,FLUX.1 [dev] Non-Commercial License,Black Forest Labs,https://huggingface.co/black-forest-labs/FLUX.1-dev
|
4 |
+
GPT-4o + Stable Diffusion 3 Medium,GPT-4o + Stable Diffusion 3 Medium,1037.4899722855018,1026.2775791477911,Stability AI Community License,Stability AI,https://huggingface.co/stabilityai/stable-diffusion-3-medium
|
5 |
+
GPT-4o + PixArt-Sigma,GPT-4o + PixArt-Sigma,1030.2322549298108,1003.2938185806802,CreativeML Open RAIL++-M License,Huawei Noah's Ark Lab,https://huggingface.co/PixArt-alpha/PixArt-Sigma-XL-2-1024-MS
|
6 |
+
GPT-4o + Emu2,GPT-4o + Emu2,941.1199462147184,946.5946854676025,Apache License 2.0,BAAI,https://huggingface.co/BAAI/Emu2
|
7 |
+
GPT-4o + DALLE-3,GPT-4o + DALLE-3,884.7999841743839,941.2186221773824,OpenAI Terms of Use,OpenAI,https://openai.com/index/dall-e-3/
|
8 |
+
GPT-4o + OmniGen,GPT-4o + OmniGen,858.0082220710267,844.3389181843263,MIT License,BAAI,https://huggingface.co/spaces/Shitao/OmniGen
|
|