Update leaderboard_data.json
Browse files- 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": "FLUX-2-flex",
|
| 5 |
+
"link": "https://flux2-flex.com/",
|
| 6 |
+
"hf": "-",
|
| 7 |
+
"open_source": false,
|
| 8 |
+
"release_date": "2025-11",
|
| 9 |
+
"Overall": 87.62,
|
| 10 |
+
"Style": 98.09,
|
| 11 |
+
"World Knowledge": 95.99,
|
| 12 |
+
"Attribute-Overall": 90.76,
|
| 13 |
+
"Quantity": 87.5,
|
| 14 |
+
"Expression": 80.26,
|
| 15 |
+
"Material": 95.28,
|
| 16 |
+
"Size": 93.06,
|
| 17 |
+
"Shape": 88.68,
|
| 18 |
+
"Color": 100.0,
|
| 19 |
+
"Action-Overall": 89.67,
|
| 20 |
+
"Hand": 89.74,
|
| 21 |
+
"Full body": 92.18,
|
| 22 |
+
"Animal": 88.24,
|
| 23 |
+
"Non Contact": 87.76,
|
| 24 |
+
"Contact": 82.63,
|
| 25 |
+
"State": 95.73,
|
| 26 |
+
"Relationship-Overall": 91.57,
|
| 27 |
+
"Composition": 93.58,
|
| 28 |
+
"Similarity": 86.59,
|
| 29 |
+
"Inclusion": 94.44,
|
| 30 |
+
"Comparison": 89.84,
|
| 31 |
+
"Compound-Overall": 92.09,
|
| 32 |
+
"Imagination": 94.9,
|
| 33 |
+
"Feature matching": 89.18,
|
| 34 |
+
"Grammar-Overall": 85.68,
|
| 35 |
+
"Pronoun Reference": 94.32,
|
| 36 |
+
"Consistency": 85.65,
|
| 37 |
+
"Negation": 76.92,
|
| 38 |
+
"Layout-Overall": 94.54,
|
| 39 |
+
"2D": 94.4,
|
| 40 |
+
"3D": 94.68,
|
| 41 |
+
"Logical Reasoning": 77.08,
|
| 42 |
+
"Text": 60.77
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"model": "FLUX-2-max",
|
| 46 |
+
"link": "https://bfl.ai/models/flux-2-max",
|
| 47 |
+
"hf": "-",
|
| 48 |
+
"open_source": false,
|
| 49 |
+
"release_date": "2025-12",
|
| 50 |
+
"Overall": 88.14,
|
| 51 |
+
"Style": 99.1,
|
| 52 |
+
"World Knowledge": 97.28,
|
| 53 |
+
"Attribute-Overall": 92.26,
|
| 54 |
+
"Quantity": 90.28,
|
| 55 |
+
"Expression": 80.26,
|
| 56 |
+
"Material": 97.64,
|
| 57 |
+
"Size": 95.14,
|
| 58 |
+
"Shape": 90.0,
|
| 59 |
+
"Color": 100.0,
|
| 60 |
+
"Action-Overall": 90.55,
|
| 61 |
+
"Hand": 89.1,
|
| 62 |
+
"Full body": 94.44,
|
| 63 |
+
"Animal": 90.44,
|
| 64 |
+
"Non Contact": 89.8,
|
| 65 |
+
"Contact": 85.71,
|
| 66 |
+
"State": 92.92,
|
| 67 |
+
"Relationship-Overall": 94.26,
|
| 68 |
+
"Composition": 95.95,
|
| 69 |
+
"Similarity": 88.89,
|
| 70 |
+
"Inclusion": 98.89,
|
| 71 |
+
"Comparison": 91.41,
|
| 72 |
+
"Compound-Overall": 93.65,
|
| 73 |
+
"Imagination": 95.41,
|
| 74 |
+
"Feature matching": 91.84,
|
| 75 |
+
"Grammar-Overall": 87.57,
|
| 76 |
+
"Pronoun Reference": 94.32,
|
| 77 |
+
"Consistency": 88.89,
|
| 78 |
+
"Negation": 79.62,
|
| 79 |
+
"Layout-Overall": 94.92,
|
| 80 |
+
"2D": 96.64,
|
| 81 |
+
"3D": 93.18,
|
| 82 |
+
"Logical Reasoning": 80.0,
|
| 83 |
+
"Text": 51.76
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"model": "FLUX-2-pro",
|
| 87 |
+
"link": "https://docs.bfl.ai/flux_2/flux2_text_to_image",
|
| 88 |
+
"hf": "-",
|
| 89 |
+
"open_source": false,
|
| 90 |
+
"release_date": "2025-11",
|
| 91 |
+
"Overall": 85.4,
|
| 92 |
+
"Style": 99.2,
|
| 93 |
+
"World Knowledge": 96.47,
|
| 94 |
+
"Attribute-Overall": 89.69,
|
| 95 |
+
"Quantity": 84.72,
|
| 96 |
+
"Expression": 77.63,
|
| 97 |
+
"Material": 97.17,
|
| 98 |
+
"Size": 89.58,
|
| 99 |
+
"Shape": 88.12,
|
| 100 |
+
"Color": 100.0,
|
| 101 |
+
"Action-Overall": 87.5,
|
| 102 |
+
"Hand": 83.33,
|
| 103 |
+
"Full body": 90.56,
|
| 104 |
+
"Animal": 88.97,
|
| 105 |
+
"Non Contact": 88.27,
|
| 106 |
+
"Contact": 80.95,
|
| 107 |
+
"State": 91.51,
|
| 108 |
+
"Relationship-Overall": 90.69,
|
| 109 |
+
"Composition": 91.89,
|
| 110 |
+
"Similarity": 82.22,
|
| 111 |
+
"Inclusion": 96.67,
|
| 112 |
+
"Comparison": 91.41,
|
| 113 |
+
"Compound-Overall": 89.13,
|
| 114 |
+
"Imagination": 92.35,
|
| 115 |
+
"Feature matching": 85.83,
|
| 116 |
+
"Grammar-Overall": 82.84,
|
| 117 |
+
"Pronoun Reference": 91.29,
|
| 118 |
+
"Consistency": 84.72,
|
| 119 |
+
"Negation": 72.69,
|
| 120 |
+
"Layout-Overall": 93.98,
|
| 121 |
+
"2D": 93.28,
|
| 122 |
+
"3D": 94.7,
|
| 123 |
+
"Logical Reasoning": 75.93,
|
| 124 |
+
"Text": 48.53
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"model": "FLUX.2-klein-4b",
|
| 128 |
+
"link": "https://bfl.ai/blog/flux2-klein-towards-interactive-visual-intelligence",
|
| 129 |
+
"hf": "https://huggingface.co/black-forest-labs/FLUX.2-klein-4B",
|
| 130 |
+
"open_source": true,
|
| 131 |
+
"release_date": "2026-1",
|
| 132 |
+
"Overall": 71.8,
|
| 133 |
+
"Style": 97.1,
|
| 134 |
+
"World Knowledge": 87.34,
|
| 135 |
+
"Attribute-Overall": 83.87,
|
| 136 |
+
"Quantity": 64.58,
|
| 137 |
+
"Expression": 83.33,
|
| 138 |
+
"Material": 91.98,
|
| 139 |
+
"Size": 83.33,
|
| 140 |
+
"Shape": 79.38,
|
| 141 |
+
"Color": 100.0,
|
| 142 |
+
"Action-Overall": 78.42,
|
| 143 |
+
"Hand": 73.08,
|
| 144 |
+
"Full body": 80.43,
|
| 145 |
+
"Animal": 81.62,
|
| 146 |
+
"Non Contact": 76.02,
|
| 147 |
+
"Contact": 73.81,
|
| 148 |
+
"State": 84.43,
|
| 149 |
+
"Relationship-Overall": 80.84,
|
| 150 |
+
"Composition": 85.81,
|
| 151 |
+
"Similarity": 65.56,
|
| 152 |
+
"Inclusion": 91.3,
|
| 153 |
+
"Comparison": 75.78,
|
| 154 |
+
"Compound-Overall": 76.03,
|
| 155 |
+
"Imagination": 82.14,
|
| 156 |
+
"Feature matching": 69.79,
|
| 157 |
+
"Grammar-Overall": 74.87,
|
| 158 |
+
"Pronoun Reference": 84.19,
|
| 159 |
+
"Consistency": 76.85,
|
| 160 |
+
"Negation": 63.46,
|
| 161 |
+
"Layout-Overall": 82.65,
|
| 162 |
+
"2D": 86.03,
|
| 163 |
+
"3D": 79.17,
|
| 164 |
+
"Logical Reasoning": 56.88,
|
| 165 |
+
"Text": 0.0
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"model": "FLUX.2-klein-9b",
|
| 169 |
+
"link": "https://bfl.ai/blog/flux2-klein-towards-interactive-visual-intelligence",
|
| 170 |
+
"hf": "https://huggingface.co/black-forest-labs/FLUX.2-klein-9B",
|
| 171 |
+
"open_source": true,
|
| 172 |
+
"release_date": "2026-1",
|
| 173 |
+
"Overall": 75.19,
|
| 174 |
+
"Style": 98.6,
|
| 175 |
+
"World Knowledge": 93.67,
|
| 176 |
+
"Attribute-Overall": 86.11,
|
| 177 |
+
"Quantity": 75.69,
|
| 178 |
+
"Expression": 81.41,
|
| 179 |
+
"Material": 93.4,
|
| 180 |
+
"Size": 86.11,
|
| 181 |
+
"Shape": 80.0,
|
| 182 |
+
"Color": 100.0,
|
| 183 |
+
"Action-Overall": 83.08,
|
| 184 |
+
"Hand": 76.28,
|
| 185 |
+
"Full body": 86.41,
|
| 186 |
+
"Animal": 88.97,
|
| 187 |
+
"Non Contact": 78.57,
|
| 188 |
+
"Contact": 80.36,
|
| 189 |
+
"State": 87.74,
|
| 190 |
+
"Relationship-Overall": 86.68,
|
| 191 |
+
"Composition": 90.88,
|
| 192 |
+
"Similarity": 75.56,
|
| 193 |
+
"Inclusion": 92.93,
|
| 194 |
+
"Comparison": 83.59,
|
| 195 |
+
"Compound-Overall": 82.35,
|
| 196 |
+
"Imagination": 87.24,
|
| 197 |
+
"Feature matching": 77.34,
|
| 198 |
+
"Grammar-Overall": 77.01,
|
| 199 |
+
"Pronoun Reference": 86.76,
|
| 200 |
+
"Consistency": 79.17,
|
| 201 |
+
"Negation": 65.0,
|
| 202 |
+
"Layout-Overall": 84.89,
|
| 203 |
+
"2D": 88.6,
|
| 204 |
+
"3D": 81.06,
|
| 205 |
+
"Logical Reasoning": 58.03,
|
| 206 |
+
"Text": 1.44
|
| 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": 69.45,
|
| 215 |
+
"Style": 96.9,
|
| 216 |
+
"World Knowledge": 84.34,
|
| 217 |
+
"Attribute-Overall": 80.77,
|
| 218 |
+
"Quantity": 70.14,
|
| 219 |
+
"Expression": 71.15,
|
| 220 |
+
"Material": 90.09,
|
| 221 |
+
"Size": 81.25,
|
| 222 |
+
"Shape": 73.12,
|
| 223 |
+
"Color": 99.17,
|
| 224 |
+
"Action-Overall": 71.39,
|
| 225 |
+
"Hand": 69.87,
|
| 226 |
+
"Full body": 73.91,
|
| 227 |
+
"Animal": 73.53,
|
| 228 |
+
"Non Contact": 66.33,
|
| 229 |
+
"Contact": 64.88,
|
| 230 |
+
"State": 78.77,
|
| 231 |
+
"Relationship-Overall": 79.57,
|
| 232 |
+
"Composition": 83.45,
|
| 233 |
+
"Similarity": 70.56,
|
| 234 |
+
"Inclusion": 83.15,
|
| 235 |
+
"Comparison": 78.12,
|
| 236 |
+
"Compound-Overall": 70.49,
|
| 237 |
+
"Imagination": 77.3,
|
| 238 |
+
"Feature matching": 63.54,
|
| 239 |
+
"Grammar-Overall": 75.27,
|
| 240 |
+
"Pronoun Reference": 81.25,
|
| 241 |
+
"Consistency": 74.54,
|
| 242 |
+
"Negation": 69.62,
|
| 243 |
+
"Layout-Overall": 80.04,
|
| 244 |
+
"2D": 84.93,
|
| 245 |
+
"3D": 75.0,
|
| 246 |
+
"Logical Reasoning": 55.73,
|
| 247 |
+
"Text": 0.0
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"model": "FLUX.2-klein-base-9b",
|
| 251 |
+
"link": "https://bfl.ai/blog/flux2-klein-towards-interactive-visual-intelligence",
|
| 252 |
+
"hf": "https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B",
|
| 253 |
+
"open_source": true,
|
| 254 |
+
"release_date": "2026-1",
|
| 255 |
+
"Overall": 73.81,
|
| 256 |
+
"Style": 96.7,
|
| 257 |
+
"World Knowledge": 88.77,
|
| 258 |
+
"Attribute-Overall": 85.79,
|
| 259 |
+
"Quantity": 75.0,
|
| 260 |
+
"Expression": 79.49,
|
| 261 |
+
"Material": 91.51,
|
| 262 |
+
"Size": 87.5,
|
| 263 |
+
"Shape": 81.88,
|
| 264 |
+
"Color": 100.0,
|
| 265 |
+
"Action-Overall": 78.99,
|
| 266 |
+
"Hand": 72.44,
|
| 267 |
+
"Full body": 82.07,
|
| 268 |
+
"Animal": 88.97,
|
| 269 |
+
"Non Contact": 70.92,
|
| 270 |
+
"Contact": 77.38,
|
| 271 |
+
"State": 83.49,
|
| 272 |
+
"Relationship-Overall": 84.9,
|
| 273 |
+
"Composition": 88.85,
|
| 274 |
+
"Similarity": 79.44,
|
| 275 |
+
"Inclusion": 88.04,
|
| 276 |
+
"Comparison": 78.91,
|
| 277 |
+
"Compound-Overall": 78.09,
|
| 278 |
+
"Imagination": 83.67,
|
| 279 |
+
"Feature matching": 72.4,
|
| 280 |
+
"Grammar-Overall": 77.94,
|
| 281 |
+
"Pronoun Reference": 84.56,
|
| 282 |
+
"Consistency": 81.02,
|
| 283 |
+
"Negation": 68.46,
|
| 284 |
+
"Layout-Overall": 83.96,
|
| 285 |
+
"2D": 88.24,
|
| 286 |
+
"3D": 79.55,
|
| 287 |
+
"Logical Reasoning": 60.09,
|
| 288 |
+
"Text": 2.87
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"model": "GPT-4o-1.5",
|
| 292 |
+
"link": "https://developers.openai.com/api/docs/models/gpt-image-1.5",
|
| 293 |
+
"hf": "-",
|
| 294 |
+
"open_source": false,
|
| 295 |
+
"release_date": "2025-12",
|
| 296 |
+
"Overall": 95.62,
|
| 297 |
+
"Style": 99.49,
|
| 298 |
+
"World Knowledge": 99.68,
|
| 299 |
+
"Attribute-Overall": 96.55,
|
| 300 |
+
"Quantity": 92.14,
|
| 301 |
+
"Expression": 94.23,
|
| 302 |
+
"Material": 98.08,
|
| 303 |
+
"Size": 99.31,
|
| 304 |
+
"Shape": 95.62,
|
| 305 |
+
"Color": 100.0,
|
| 306 |
+
"Action-Overall": 95.52,
|
| 307 |
+
"Hand": 96.15,
|
| 308 |
+
"Full body": 98.91,
|
| 309 |
+
"Animal": 96.32,
|
| 310 |
+
"Non Contact": 93.81,
|
| 311 |
+
"Contact": 92.86,
|
| 312 |
+
"State": 95.28,
|
| 313 |
+
"Relationship-Overall": 97.83,
|
| 314 |
+
"Composition": 97.97,
|
| 315 |
+
"Similarity": 97.22,
|
| 316 |
+
"Inclusion": 100.0,
|
| 317 |
+
"Comparison": 95.31,
|
| 318 |
+
"Compound-Overall": 97.13,
|
| 319 |
+
"Imagination": 99.23,
|
| 320 |
+
"Feature matching": 94.95,
|
| 321 |
+
"Grammar-Overall": 91.98,
|
| 322 |
+
"Pronoun Reference": 95.9,
|
| 323 |
+
"Consistency": 92.13,
|
| 324 |
+
"Negation": 87.7,
|
| 325 |
+
"Layout-Overall": 93.8,
|
| 326 |
+
"2D": 93.28,
|
| 327 |
+
"3D": 94.32,
|
| 328 |
+
"Logical Reasoning": 90.6,
|
| 329 |
+
"Text": 93.6
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"model": "LongCat-Image",
|
| 333 |
+
"link": "https://arxiv.org/pdf/2512.07584",
|
| 334 |
+
"hf": "https://huggingface.co/meituan-longcat/LongCat-Image",
|
| 335 |
+
"open_source": true,
|
| 336 |
+
"release_date": "2025-12",
|
| 337 |
+
"Overall": 75.97,
|
| 338 |
+
"Style": 87.6,
|
| 339 |
+
"World Knowledge": 92.09,
|
| 340 |
+
"Attribute-Overall": 79.17,
|
| 341 |
+
"Quantity": 71.53,
|
| 342 |
+
"Expression": 77.56,
|
| 343 |
+
"Material": 88.21,
|
| 344 |
+
"Size": 77.78,
|
| 345 |
+
"Shape": 63.75,
|
| 346 |
+
"Color": 96.67,
|
| 347 |
+
"Action-Overall": 77.0,
|
| 348 |
+
"Hand": 76.92,
|
| 349 |
+
"Full body": 78.8,
|
| 350 |
+
"Animal": 85.29,
|
| 351 |
+
"Non Contact": 71.43,
|
| 352 |
+
"Contact": 67.26,
|
| 353 |
+
"State": 83.02,
|
| 354 |
+
"Relationship-Overall": 79.95,
|
| 355 |
+
"Composition": 80.41,
|
| 356 |
+
"Similarity": 70.56,
|
| 357 |
+
"Inclusion": 86.96,
|
| 358 |
+
"Comparison": 82.03,
|
| 359 |
+
"Compound-Overall": 66.62,
|
| 360 |
+
"Imagination": 69.13,
|
| 361 |
+
"Feature matching": 64.06,
|
| 362 |
+
"Grammar-Overall": 65.64,
|
| 363 |
+
"Pronoun Reference": 79.78,
|
| 364 |
+
"Consistency": 63.43,
|
| 365 |
+
"Negation": 52.69,
|
| 366 |
+
"Layout-Overall": 79.29,
|
| 367 |
+
"2D": 78.31,
|
| 368 |
+
"3D": 80.3,
|
| 369 |
+
"Logical Reasoning": 49.31,
|
| 370 |
+
"Text": 83.05
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"model": "Seedream-4-5-251128",
|
| 374 |
+
"link": "https://seed.bytedance.com/en/seedream4_5",
|
| 375 |
+
"hf": "-",
|
| 376 |
+
"open_source": false,
|
| 377 |
+
"release_date": "2025-11",
|
| 378 |
+
"Overall": 89.58,
|
| 379 |
+
"Style": 98.9,
|
| 380 |
+
"World Knowledge": 96.2,
|
| 381 |
+
"Attribute-Overall": 92.31,
|
| 382 |
+
"Quantity": 87.5,
|
| 383 |
+
"Expression": 87.82,
|
| 384 |
+
"Material": 99.53,
|
| 385 |
+
"Size": 89.58,
|
| 386 |
+
"Shape": 88.12,
|
| 387 |
+
"Color": 100.0,
|
| 388 |
+
"Action-Overall": 89.54,
|
| 389 |
+
"Hand": 85.26,
|
| 390 |
+
"Full body": 94.02,
|
| 391 |
+
"Animal": 91.91,
|
| 392 |
+
"Non Contact": 82.14,
|
| 393 |
+
"Contact": 86.31,
|
| 394 |
+
"State": 96.7,
|
| 395 |
+
"Relationship-Overall": 90.48,
|
| 396 |
+
"Composition": 88.85,
|
| 397 |
+
"Similarity": 89.44,
|
| 398 |
+
"Inclusion": 94.02,
|
| 399 |
+
"Comparison": 90.62,
|
| 400 |
+
"Compound-Overall": 88.66,
|
| 401 |
+
"Imagination": 91.84,
|
| 402 |
+
"Feature matching": 85.42,
|
| 403 |
+
"Grammar-Overall": 84.22,
|
| 404 |
+
"Pronoun Reference": 90.81,
|
| 405 |
+
"Consistency": 84.26,
|
| 406 |
+
"Negation": 77.31,
|
| 407 |
+
"Layout-Overall": 91.04,
|
| 408 |
+
"2D": 91.54,
|
| 409 |
+
"3D": 90.53,
|
| 410 |
+
"Logical Reasoning": 71.1,
|
| 411 |
+
"Text": 93.39
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"model": "Z-Image",
|
| 415 |
+
"link": "https://arxiv.org/pdf/2511.22699",
|
| 416 |
+
"hf": "https://huggingface.co/Tongyi-MAI/Z-Image",
|
| 417 |
+
"open_source": true,
|
| 418 |
+
"release_date": "2026-1",
|
| 419 |
+
"Overall": 81.69,
|
| 420 |
+
"Style": 96.3,
|
| 421 |
+
"World Knowledge": 94.62,
|
| 422 |
+
"Attribute-Overall": 86.11,
|
| 423 |
+
"Quantity": 83.33,
|
| 424 |
+
"Expression": 74.36,
|
| 425 |
+
"Material": 95.28,
|
| 426 |
+
"Size": 85.42,
|
| 427 |
+
"Shape": 79.38,
|
| 428 |
+
"Color": 98.33,
|
| 429 |
+
"Action-Overall": 82.6,
|
| 430 |
+
"Hand": 81.41,
|
| 431 |
+
"Full body": 85.33,
|
| 432 |
+
"Animal": 83.82,
|
| 433 |
+
"Non Contact": 81.63,
|
| 434 |
+
"Contact": 76.19,
|
| 435 |
+
"State": 86.32,
|
| 436 |
+
"Relationship-Overall": 84.64,
|
| 437 |
+
"Composition": 88.51,
|
| 438 |
+
"Similarity": 75.0,
|
| 439 |
+
"Inclusion": 90.22,
|
| 440 |
+
"Comparison": 81.25,
|
| 441 |
+
"Compound-Overall": 79.51,
|
| 442 |
+
"Imagination": 83.16,
|
| 443 |
+
"Feature matching": 75.78,
|
| 444 |
+
"Grammar-Overall": 71.26,
|
| 445 |
+
"Pronoun Reference": 84.19,
|
| 446 |
+
"Consistency": 73.61,
|
| 447 |
+
"Negation": 55.77,
|
| 448 |
+
"Layout-Overall": 86.57,
|
| 449 |
+
"2D": 86.76,
|
| 450 |
+
"3D": 86.36,
|
| 451 |
+
"Logical Reasoning": 54.82,
|
| 452 |
+
"Text": 80.46
|
| 453 |
+
},
|
| 454 |
{
|
| 455 |
"model": "Z-Image-Turbo",
|
| 456 |
"link": "https://github.com/Tongyi-MAI/Z-Image",
|