CodeGoat24 commited on
Commit
26e558a
·
verified ·
1 Parent(s): 19e2f43

Update leaderboard_data.json

Browse files
Files changed (1) hide show
  1. leaderboard_data.json +451 -0
leaderboard_data.json CHANGED
@@ -1,5 +1,456 @@
1
  {
2
  "leaderboard": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  {
4
  "model": "Z-Image-Turbo",
5
  "link": "https://github.com/Tongyi-MAI/Z-Image",
 
1
  {
2
  "leaderboard": [
3
+ {
4
+ "model": "Z-Image",
5
+ "link": "https://arxiv.org/pdf/2511.22699",
6
+ "hf": "https://huggingface.co/Tongyi-MAI/Z-Image",
7
+ "open_source": true,
8
+ "release_date": "2026-1",
9
+ "Overall": 78.1,
10
+ "Style": 96.8,
11
+ "World Knowledge": 94.46,
12
+ "Attribute-Overall": 82.48,
13
+ "Quantity": 81.25,
14
+ "Expression": 69.87,
15
+ "Material": 91.98,
16
+ "Size": 81.25,
17
+ "Shape": 73.12,
18
+ "Color": 97.5,
19
+ "Action-Overall": 78.9,
20
+ "Hand": 74.36,
21
+ "Full body": 82.61,
22
+ "Animal": 82.35,
23
+ "Non Contact": 77.04,
24
+ "Contact": 71.43,
25
+ "State": 84.43,
26
+ "Relationship-Overall": 80.2,
27
+ "Composition": 84.8,
28
+ "Similarity": 70.0,
29
+ "Inclusion": 86.41,
30
+ "Comparison": 75.0,
31
+ "Compound-Overall": 76.8,
32
+ "Imagination": 82.14,
33
+ "Feature matching": 71.35,
34
+ "Grammar-Overall": 68.98,
35
+ "Pronoun Reference": 80.88,
36
+ "Consistency": 75.0,
37
+ "Negation": 51.54,
38
+ "Layout-Overall": 84.89,
39
+ "2D": 86.76,
40
+ "3D": 82.95,
41
+ "Logical Reasoning": 49.08,
42
+ "Text": 68.39
43
+ },
44
+ {
45
+ "model": "Seedream-4-5-251128",
46
+ "link": "https://seed.bytedance.com/en/seedream4_5",
47
+ "hf": "-",
48
+ "open_source": false,
49
+ "release_date": "2025-11",
50
+ "Overall": 89.7,
51
+ "Style": 99.2,
52
+ "World Knowledge": 96.35,
53
+ "Attribute-Overall": 91.03,
54
+ "Quantity": 87.5,
55
+ "Expression": 87.82,
56
+ "Material": 97.64,
57
+ "Size": 86.81,
58
+ "Shape": 85.62,
59
+ "Color": 100.0,
60
+ "Action-Overall": 88.21,
61
+ "Hand": 80.77,
62
+ "Full body": 90.22,
63
+ "Animal": 91.91,
64
+ "Non Contact": 84.69,
65
+ "Contact": 86.9,
66
+ "State": 93.87,
67
+ "Relationship-Overall": 90.61,
68
+ "Composition": 92.57,
69
+ "Similarity": 85.0,
70
+ "Inclusion": 94.57,
71
+ "Comparison": 88.28,
72
+ "Compound-Overall": 90.08,
73
+ "Imagination": 90.05,
74
+ "Feature matching": 90.1,
75
+ "Grammar-Overall": 84.09,
76
+ "Pronoun Reference": 90.07,
77
+ "Consistency": 85.65,
78
+ "Negation": 76.54,
79
+ "Layout-Overall": 92.54,
80
+ "2D": 91.54,
81
+ "3D": 93.56,
82
+ "Logical Reasoning": 73.17,
83
+ "Text": 91.67
84
+ },
85
+ {
86
+ "model": "LongCat-Image",
87
+ "link": "https://arxiv.org/pdf/2512.07584",
88
+ "hf": "https://huggingface.co/meituan-longcat/LongCat-Image",
89
+ "open_source": true,
90
+ "release_date": "2025-12",
91
+ "Overall": 73.54,
92
+ "Style": 90.7,
93
+ "World Knowledge": 89.72,
94
+ "Attribute-Overall": 80.88,
95
+ "Quantity": 74.31,
96
+ "Expression": 79.49,
97
+ "Material": 87.74,
98
+ "Size": 81.94,
99
+ "Shape": 67.5,
100
+ "Color": 95.0,
101
+ "Action-Overall": 75.48,
102
+ "Hand": 64.1,
103
+ "Full body": 82.61,
104
+ "Animal": 82.35,
105
+ "Non Contact": 71.94,
106
+ "Contact": 72.02,
107
+ "State": 79.25,
108
+ "Relationship-Overall": 75.13,
109
+ "Composition": 75.34,
110
+ "Similarity": 70.56,
111
+ "Inclusion": 83.15,
112
+ "Comparison": 69.53,
113
+ "Compound-Overall": 64.43,
114
+ "Imagination": 68.11,
115
+ "Feature matching": 60.68,
116
+ "Grammar-Overall": 65.78,
117
+ "Pronoun Reference": 76.1,
118
+ "Consistency": 59.72,
119
+ "Negation": 60.0,
120
+ "Layout-Overall": 81.34,
121
+ "2D": 84.93,
122
+ "3D": 77.65,
123
+ "Logical Reasoning": 45.87,
124
+ "Text": 66.09
125
+ },
126
+ {
127
+ "model": "GPT-4o-1.5",
128
+ "link": "https://developers.openai.com/api/docs/models/gpt-image-1.5",
129
+ "hf": "-",
130
+ "open_source": false,
131
+ "release_date": "2025-12",
132
+ "Overall": 95.77,
133
+ "Style": 99.19,
134
+ "World Knowledge": 99.2,
135
+ "Attribute-Overall": 96.33,
136
+ "Quantity": 90.71,
137
+ "Expression": 92.31,
138
+ "Material": 99.03,
139
+ "Size": 97.92,
140
+ "Shape": 97.5,
141
+ "Color": 100.0,
142
+ "Action-Overall": 94.84,
143
+ "Hand": 95.51,
144
+ "Full body": 95.63,
145
+ "Animal": 95.59,
146
+ "Non Contact": 91.15,
147
+ "Contact": 97.02,
148
+ "State": 94.81,
149
+ "Relationship-Overall": 96.94,
150
+ "Composition": 96.96,
151
+ "Similarity": 96.67,
152
+ "Inclusion": 99.44,
153
+ "Comparison": 93.75,
154
+ "Compound-Overall": 98.17,
155
+ "Imagination": 98.45,
156
+ "Feature matching": 97.87,
157
+ "Grammar-Overall": 92.27,
158
+ "Pronoun Reference": 97.77,
159
+ "Consistency": 90.28,
160
+ "Negation": 88.1,
161
+ "Layout-Overall": 94.56,
162
+ "2D": 93.31,
163
+ "3D": 95.83,
164
+ "Logical Reasoning": 88.76,
165
+ "Text": 97.39
166
+ },
167
+ {
168
+ "model": "FLUX.2-klein-base-9b",
169
+ "link": "https://bfl.ai/blog/flux2-klein-towards-interactive-visual-intelligence",
170
+ "hf": "https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B",
171
+ "open_source": true,
172
+ "release_date": "2026-1",
173
+ "Overall": 79.35,
174
+ "Style": 95.8,
175
+ "World Knowledge": 91.13,
176
+ "Attribute-Overall": 82.16,
177
+ "Quantity": 72.92,
178
+ "Expression": 76.28,
179
+ "Material": 89.15,
180
+ "Size": 81.94,
181
+ "Shape": 75.62,
182
+ "Color": 97.5,
183
+ "Action-Overall": 76.78,
184
+ "Hand": 71.15,
185
+ "Full body": 78.8,
186
+ "Animal": 80.15,
187
+ "Non Contact": 78.06,
188
+ "Contact": 68.26,
189
+ "State": 82.55,
190
+ "Relationship-Overall": 86.42,
191
+ "Composition": 88.85,
192
+ "Similarity": 77.78,
193
+ "Inclusion": 92.93,
194
+ "Comparison": 83.59,
195
+ "Compound-Overall": 78.22,
196
+ "Imagination": 79.34,
197
+ "Feature matching": 77.08,
198
+ "Grammar-Overall": 77.51,
199
+ "Pronoun Reference": 85.29,
200
+ "Consistency": 77.67,
201
+ "Negation": 69.23,
202
+ "Layout-Overall": 88.62,
203
+ "2D": 91.54,
204
+ "3D": 85.61,
205
+ "Logical Reasoning": 57.34,
206
+ "Text": 59.48
207
+ },
208
+ {
209
+ "model": "FLUX.2-klein-base-4b",
210
+ "link": "https://bfl.ai/blog/flux2-klein-towards-interactive-visual-intelligence",
211
+ "hf": "https://huggingface.co/black-forest-labs/FLUX.2-klein-base-4B",
212
+ "open_source": true,
213
+ "release_date": "2026-1",
214
+ "Overall": 69.81,
215
+ "Style": 94.6,
216
+ "World Knowledge": 81.65,
217
+ "Attribute-Overall": 78.85,
218
+ "Quantity": 65.97,
219
+ "Expression": 69.87,
220
+ "Material": 84.43,
221
+ "Size": 84.03,
222
+ "Shape": 72.5,
223
+ "Color": 98.33,
224
+ "Action-Overall": 69.96,
225
+ "Hand": 67.31,
226
+ "Full body": 73.37,
227
+ "Animal": 75.74,
228
+ "Non Contact": 66.84,
229
+ "Contact": 60.12,
230
+ "State": 75.94,
231
+ "Relationship-Overall": 80.58,
232
+ "Composition": 84.12,
233
+ "Similarity": 74.44,
234
+ "Inclusion": 83.7,
235
+ "Comparison": 76.56,
236
+ "Compound-Overall": 70.62,
237
+ "Imagination": 74.49,
238
+ "Feature matching": 66.67,
239
+ "Grammar-Overall": 73.8,
240
+ "Pronoun Reference": 78.31,
241
+ "Consistency": 71.3,
242
+ "Negation": 71.15,
243
+ "Layout-Overall": 86.01,
244
+ "2D": 88.6,
245
+ "3D": 83.33,
246
+ "Logical Reasoning": 50.23,
247
+ "Text": 11.78
248
+ },
249
+ {
250
+ "model": "FLUX.2-klein-9b",
251
+ "link": "https://bfl.ai/blog/flux2-klein-towards-interactive-visual-intelligence",
252
+ "hf": "https://huggingface.co/black-forest-labs/FLUX.2-klein-9B",
253
+ "open_source": true,
254
+ "release_date": "2026-1",
255
+ "Overall": 78.28,
256
+ "Style": 97.5,
257
+ "World Knowledge": 93.04,
258
+ "Attribute-Overall": 84.08,
259
+ "Quantity": 75.0,
260
+ "Expression": 83.33,
261
+ "Material": 89.62,
262
+ "Size": 82.64,
263
+ "Shape": 76.88,
264
+ "Color": 97.5,
265
+ "Action-Overall": 80.8,
266
+ "Hand": 78.21,
267
+ "Full body": 85.33,
268
+ "Animal": 83.82,
269
+ "Non Contact": 79.08,
270
+ "Contact": 73.21,
271
+ "State": 84.43,
272
+ "Relationship-Overall": 85.15,
273
+ "Composition": 88.51,
274
+ "Similarity": 72.22,
275
+ "Inclusion": 95.65,
276
+ "Comparison": 80.47,
277
+ "Compound-Overall": 80.03,
278
+ "Imagination": 80.87,
279
+ "Feature matching": 79.17,
280
+ "Grammar-Overall": 73.26,
281
+ "Pronoun Reference": 81.99,
282
+ "Consistency": 76.39,
283
+ "Negation": 61.54,
284
+ "Layout-Overall": 88.81,
285
+ "2D": 90.81,
286
+ "3D": 86.74,
287
+ "Logical Reasoning": 57.34,
288
+ "Text": 42.82
289
+ },
290
+ {
291
+ "model": "FLUX.2-klein-4b",
292
+ "link": "https://bfl.ai/blog/flux2-klein-towards-interactive-visual-intelligence",
293
+ "hf": "https://huggingface.co/black-forest-labs/FLUX.2-klein-4B",
294
+ "open_source": true,
295
+ "release_date": "2026-1",
296
+ "Overall": 72.31,
297
+ "Style": 98.4,
298
+ "World Knowledge": 86.23,
299
+ "Attribute-Overall": 80.45,
300
+ "Quantity": 66.67,
301
+ "Expression": 73.72,
302
+ "Material": 88.21,
303
+ "Size": 84.03,
304
+ "Shape": 72.5,
305
+ "Color": 98.33,
306
+ "Action-Overall": 77.09,
307
+ "Hand": 69.23,
308
+ "Full body": 80.98,
309
+ "Animal": 84.56,
310
+ "Non Contact": 76.53,
311
+ "Contact": 69.64,
312
+ "State": 81.13,
313
+ "Relationship-Overall": 80.2,
314
+ "Composition": 82.43,
315
+ "Similarity": 71.67,
316
+ "Inclusion": 88.59,
317
+ "Comparison": 75.0,
318
+ "Compound-Overall": 75.39,
319
+ "Imagination": 79.59,
320
+ "Feature matching": 71.09,
321
+ "Grammar-Overall": 70.86,
322
+ "Pronoun Reference": 80.88,
323
+ "Consistency": 70.83,
324
+ "Negation": 60.38,
325
+ "Layout-Overall": 85.07,
326
+ "2D": 88.97,
327
+ "3D": 81.06,
328
+ "Logical Reasoning": 56.19,
329
+ "Text": 13.22
330
+ },
331
+ {
332
+ "model": "FLUX-2-pro",
333
+ "link": "https://docs.bfl.ai/flux_2/flux2_text_to_image",
334
+ "hf": "-",
335
+ "open_source": false,
336
+ "release_date": "2025-11",
337
+ "Overall": 88.35,
338
+ "Style": 99.29,
339
+ "World Knowledge": 96.77,
340
+ "Attribute-Overall": 88.79,
341
+ "Quantity": 84.72,
342
+ "Expression": 75.0,
343
+ "Material": 96.23,
344
+ "Size": 90.28,
345
+ "Shape": 86.25,
346
+ "Color": 99.17,
347
+ "Action-Overall": 85.5,
348
+ "Hand": 76.92,
349
+ "Full body": 92.78,
350
+ "Animal": 80.88,
351
+ "Non Contact": 87.76,
352
+ "Contact": 80.36,
353
+ "State": 90.57,
354
+ "Relationship-Overall": 89.41,
355
+ "Composition": 90.88,
356
+ "Similarity": 82.22,
357
+ "Inclusion": 93.33,
358
+ "Comparison": 90.62,
359
+ "Compound-Overall": 89.82,
360
+ "Imagination": 92.86,
361
+ "Feature matching": 86.72,
362
+ "Grammar-Overall": 83.15,
363
+ "Pronoun Reference": 90.38,
364
+ "Consistency": 83.33,
365
+ "Negation": 75.77,
366
+ "Layout-Overall": 94.13,
367
+ "2D": 92.05,
368
+ "3D": 96.21,
369
+ "Logical Reasoning": 74.31,
370
+ "Text": 82.35
371
+ },
372
+ {
373
+ "model": "FLUX-2-max",
374
+ "link": "https://bfl.ai/models/flux-2-max",
375
+ "hf": "-",
376
+ "open_source": false,
377
+ "release_date": "2025-12",
378
+ "Overall": 90.85,
379
+ "Style": 99.09,
380
+ "World Knowledge": 96.77,
381
+ "Attribute-Overall": 90.94,
382
+ "Quantity": 90.28,
383
+ "Expression": 77.7,
384
+ "Material": 97.64,
385
+ "Size": 93.06,
386
+ "Shape": 86.79,
387
+ "Color": 99.17,
388
+ "Action-Overall": 87.3,
389
+ "Hand": 82.69,
390
+ "Full body": 93.3,
391
+ "Animal": 86.03,
392
+ "Non Contact": 85.2,
393
+ "Contact": 84.52,
394
+ "State": 90.57,
395
+ "Relationship-Overall": 92.22,
396
+ "Composition": 94.93,
397
+ "Similarity": 84.44,
398
+ "Inclusion": 95.56,
399
+ "Comparison": 92.19,
400
+ "Compound-Overall": 92.27,
401
+ "Imagination": 95.15,
402
+ "Feature matching": 89.32,
403
+ "Grammar-Overall": 86.82,
404
+ "Pronoun Reference": 90.77,
405
+ "Consistency": 87.5,
406
+ "Negation": 82.31,
407
+ "Layout-Overall": 95.26,
408
+ "2D": 97.35,
409
+ "3D": 93.16,
410
+ "Logical Reasoning": 78.44,
411
+ "Text": 89.38
412
+ },
413
+ {
414
+ "model": "FLUX-2-flex",
415
+ "link": "https://flux2-flex.com/",
416
+ "hf": "-",
417
+ "open_source": false,
418
+ "release_date": "2025-11",
419
+ "Overall": 89.35,
420
+ "Style": 98.59,
421
+ "World Knowledge": 97.1,
422
+ "Attribute-Overall": 90.41,
423
+ "Quantity": 88.19,
424
+ "Expression": 79.05,
425
+ "Material": 95.75,
426
+ "Size": 92.36,
427
+ "Shape": 86.88,
428
+ "Color": 100.0,
429
+ "Action-Overall": 86.74,
430
+ "Hand": 78.21,
431
+ "Full body": 90.0,
432
+ "Animal": 87.5,
433
+ "Non Contact": 83.67,
434
+ "Contact": 84.52,
435
+ "State": 94.34,
436
+ "Relationship-Overall": 92.09,
437
+ "Composition": 92.23,
438
+ "Similarity": 87.22,
439
+ "Inclusion": 96.11,
440
+ "Comparison": 92.97,
441
+ "Compound-Overall": 90.85,
442
+ "Imagination": 92.6,
443
+ "Feature matching": 89.06,
444
+ "Grammar-Overall": 82.47,
445
+ "Pronoun Reference": 90.77,
446
+ "Consistency": 79.17,
447
+ "Negation": 76.92,
448
+ "Layout-Overall": 92.23,
449
+ "2D": 90.15,
450
+ "3D": 94.32,
451
+ "Logical Reasoning": 74.77,
452
+ "Text": 88.24
453
+ },
454
  {
455
  "model": "Z-Image-Turbo",
456
  "link": "https://github.com/Tongyi-MAI/Z-Image",