CodeGoat24 commited on
Commit
19e2f43
·
verified ·
1 Parent(s): adfb6fc

Update leaderboard_data.json

Browse files
Files changed (1) hide show
  1. leaderboard_data.json +460 -460
leaderboard_data.json CHANGED
@@ -703,7 +703,7 @@
703
  "hf": "-",
704
  "open_source": false,
705
  "release_date": "2025-09",
706
- "Overall": 87.34,
707
  "Style": 98.8,
708
  "World Knowledge": 95.41,
709
  "Attribute-Overall": 88.57,
@@ -785,40 +785,40 @@
785
  "hf": "-",
786
  "open_source": false,
787
  "release_date": "2024-11",
788
- "Overall": 69.55,
789
- "Style": 93.85,
790
  "World Knowledge": 90.36,
791
- "Attribute-Overall": 74.68,
792
- "Quantity": 73.57,
793
- "Expression": 56.58,
794
- "Material": 87.5,
795
- "Size": 69.44,
796
- "Shape": 66.25,
797
- "Color": 94.17,
798
- "Action-Overall": 70.11,
799
- "Hand": 58.33,
800
- "Full body": 78.8,
801
- "Animal": 79.41,
802
- "Non Contact": 67.19,
803
- "Contact": 62.2,
804
- "State": 74.06,
805
- "Relationship-Overall": 71.54,
806
- "Composition": 73.99,
807
- "Similarity": 61.11,
808
- "Inclusion": 76.7,
809
- "Comparison": 73.44,
810
- "Compound-Overall": 66.58,
811
- "Imagination": 70.36,
812
- "Feature matching": 62.63,
813
- "Grammar-Overall": 70.9,
814
  "Pronoun Reference": 71.21,
815
- "Consistency": 68.06,
816
- "Negation": 73.02,
817
- "Layout-Overall": 75.38,
818
- "2D": 75.0,
819
- "3D": 75.77,
820
- "Logical Reasoning": 48.39,
821
- "Text": 33.72
822
  },
823
  {
824
  "model": "Nano Banana",
@@ -867,40 +867,40 @@
867
  "hf": "-",
868
  "open_source": false,
869
  "release_date": "2024-06",
870
- "Overall": 61.98,
871
- "Style": 86.9,
872
- "World Knowledge": 87.5,
873
- "Attribute-Overall": 66.99,
874
  "Quantity": 67.36,
875
- "Expression": 49.36,
876
- "Material": 63.21,
877
  "Size": 69.44,
878
- "Shape": 68.12,
879
  "Color": 91.67,
880
- "Action-Overall": 58.46,
881
- "Hand": 55.13,
882
- "Full body": 60.33,
883
- "Animal": 64.71,
884
- "Non Contact": 54.08,
885
  "Contact": 51.79,
886
- "State": 64.62,
887
- "Relationship-Overall": 69.29,
888
- "Composition": 74.32,
889
  "Similarity": 66.67,
890
- "Inclusion": 69.02,
891
- "Comparison": 61.72,
892
- "Compound-Overall": 54.38,
893
- "Imagination": 61.99,
894
- "Feature matching": 46.61,
895
- "Grammar-Overall": 60.16,
896
- "Pronoun Reference": 77.21,
897
- "Consistency": 56.48,
898
- "Negation": 45.38,
899
- "Layout-Overall": 65.3,
900
- "2D": 69.12,
901
- "3D": 61.36,
902
- "Logical Reasoning": 30.91,
903
- "Text": 39.94
904
  },
905
  {
906
  "model": "HiDream_v2L",
@@ -908,39 +908,39 @@
908
  "hf": "-",
909
  "open_source": false,
910
  "release_date": "2025-07",
911
- "Overall": 61.38,
912
- "Style": 87.29,
913
  "World Knowledge": 89.62,
914
- "Attribute-Overall": 63.4,
915
- "Quantity": 67.14,
916
- "Expression": 42.95,
917
  "Material": 57.82,
918
  "Size": 74.26,
919
- "Shape": 57.32,
920
- "Color": 91.53,
921
- "Action-Overall": 60.36,
922
- "Hand": 54.49,
923
- "Full body": 59.12,
924
- "Animal": 72.06,
925
- "Non Contact": 60.94,
926
- "Contact": 52.73,
927
- "State": 63.68,
928
- "Relationship-Overall": 66.75,
929
- "Composition": 72.26,
930
  "Similarity": 64.2,
931
  "Inclusion": 65.93,
932
- "Comparison": 58.73,
933
  "Compound-Overall": 49.28,
934
  "Imagination": 53.75,
935
  "Feature matching": 44.76,
936
- "Grammar-Overall": 60.08,
937
- "Pronoun Reference": 74.62,
938
- "Consistency": 60.48,
939
- "Negation": 45.0,
940
- "Layout-Overall": 67.36,
941
- "2D": 68.91,
942
- "3D": 65.78,
943
- "Logical Reasoning": 25.35,
944
  "Text": 44.31
945
  },
946
  {
@@ -949,40 +949,40 @@
949
  "hf": "-",
950
  "open_source": false,
951
  "release_date": "2025-01",
952
- "Overall": 77.37,
953
- "Style": 92.7,
954
- "World Knowledge": 94.94,
955
- "Attribute-Overall": 83.23,
956
  "Quantity": 77.08,
957
- "Expression": 73.08,
958
- "Material": 85.38,
959
  "Size": 89.58,
960
- "Shape": 79.38,
961
- "Color": 97.5,
962
- "Action-Overall": 79.85,
963
- "Hand": 74.36,
964
- "Full body": 85.33,
965
- "Animal": 85.29,
966
  "Non Contact": 76.02,
967
  "Contact": 75.6,
968
- "State": 82.55,
969
- "Relationship-Overall": 80.96,
970
- "Composition": 82.09,
971
- "Similarity": 73.33,
972
  "Inclusion": 87.5,
973
- "Comparison": 79.69,
974
- "Compound-Overall": 72.94,
975
- "Imagination": 78.06,
976
- "Feature matching": 67.71,
977
  "Grammar-Overall": 76.87,
978
- "Pronoun Reference": 83.09,
979
- "Consistency": 78.24,
980
  "Negation": 69.23,
981
- "Layout-Overall": 86.38,
982
- "2D": 87.87,
983
- "3D": 84.85,
984
- "Logical Reasoning": 54.09,
985
- "Text": 51.72
986
  },
987
  {
988
  "model": "Recraft",
@@ -990,40 +990,40 @@
990
  "hf": "-",
991
  "open_source": false,
992
  "release_date": "2024-12",
993
- "Overall": 62.64,
994
- "Style": 87.1,
995
- "World Knowledge": 90.66,
996
- "Attribute-Overall": 67.31,
997
- "Quantity": 66.67,
998
- "Expression": 57.69,
999
- "Material": 67.92,
1000
  "Size": 65.97,
1001
- "Shape": 56.88,
1002
- "Color": 95.0,
1003
- "Action-Overall": 60.84,
1004
  "Hand": 50.0,
1005
  "Full body": 70.65,
1006
- "Animal": 75.74,
1007
- "Non Contact": 58.16,
1008
- "Contact": 49.4,
1009
- "State": 62.26,
1010
  "Relationship-Overall": 62.56,
1011
- "Composition": 62.16,
1012
- "Similarity": 55.56,
1013
- "Inclusion": 63.59,
1014
- "Comparison": 71.88,
1015
- "Compound-Overall": 44.2,
1016
- "Imagination": 42.6,
1017
- "Feature matching": 45.83,
1018
  "Grammar-Overall": 63.64,
1019
- "Pronoun Reference": 72.06,
1020
- "Consistency": 56.94,
1021
- "Negation": 60.38,
1022
- "Layout-Overall": 59.7,
1023
- "2D": 60.29,
1024
- "3D": 59.09,
1025
- "Logical Reasoning": 28.86,
1026
- "Text": 61.49
1027
  },
1028
  {
1029
  "model": "FLUX-kontext-max",
@@ -1031,40 +1031,40 @@
1031
  "hf": "-",
1032
  "open_source": false,
1033
  "release_date": "2025-05",
1034
- "Overall": 80.08,
1035
- "Style": 96.39,
1036
- "World Knowledge": 93.71,
1037
  "Attribute-Overall": 80.93,
1038
- "Quantity": 75.0,
1039
- "Expression": 77.03,
1040
- "Material": 80.66,
1041
- "Size": 86.11,
1042
- "Shape": 75.62,
1043
  "Color": 94.17,
1044
- "Action-Overall": 76.62,
1045
  "Hand": 67.95,
1046
- "Full body": 79.89,
1047
  "Animal": 77.94,
1048
- "Non Contact": 75.0,
1049
- "Contact": 72.02,
1050
  "State": 84.43,
1051
- "Relationship-Overall": 83.29,
1052
- "Composition": 85.14,
1053
- "Similarity": 76.67,
1054
- "Inclusion": 89.44,
1055
- "Comparison": 79.69,
1056
- "Compound-Overall": 78.22,
1057
- "Imagination": 82.65,
1058
- "Feature matching": 73.7,
1059
- "Grammar-Overall": 78.67,
1060
- "Pronoun Reference": 85.0,
1061
- "Consistency": 77.31,
1062
- "Negation": 73.46,
1063
  "Layout-Overall": 85.04,
1064
  "2D": 86.74,
1065
  "3D": 83.33,
1066
- "Logical Reasoning": 63.41,
1067
- "Text": 64.53
1068
  },
1069
  {
1070
  "model": "FLUX-kontext-pro",
@@ -1072,40 +1072,40 @@
1072
  "hf": "-",
1073
  "open_source": false,
1074
  "release_date": "2025-05",
1075
- "Overall": 75.36,
1076
- "Style": 94.08,
1077
- "World Knowledge": 91.45,
1078
- "Attribute-Overall": 78.66,
1079
- "Quantity": 74.31,
1080
- "Expression": 72.3,
1081
- "Material": 77.36,
1082
- "Size": 83.33,
1083
- "Shape": 71.88,
1084
  "Color": 97.5,
1085
- "Action-Overall": 76.52,
1086
  "Hand": 75.0,
1087
- "Full body": 77.17,
1088
- "Animal": 81.62,
1089
- "Non Contact": 69.9,
1090
- "Contact": 72.62,
1091
- "State": 83.02,
1092
- "Relationship-Overall": 78.83,
1093
- "Composition": 81.76,
1094
- "Similarity": 73.89,
1095
- "Inclusion": 82.78,
1096
- "Comparison": 73.44,
1097
- "Compound-Overall": 74.1,
1098
- "Imagination": 76.02,
1099
- "Feature matching": 72.14,
1100
- "Grammar-Overall": 71.6,
1101
- "Pronoun Reference": 83.46,
1102
- "Consistency": 75.0,
1103
- "Negation": 56.92,
1104
- "Layout-Overall": 83.14,
1105
- "2D": 85.61,
1106
- "3D": 80.68,
1107
- "Logical Reasoning": 55.23,
1108
- "Text": 50.0
1109
  },
1110
  {
1111
  "model": "wan2.2-t2i-plus",
@@ -1113,40 +1113,40 @@
1113
  "hf": "-",
1114
  "open_source": false,
1115
  "release_date": "2025-07",
1116
- "Overall": 64.71,
1117
- "Style": 91.2,
1118
- "World Knowledge": 86.71,
1119
- "Attribute-Overall": 69.23,
1120
- "Quantity": 75.0,
1121
  "Expression": 55.77,
1122
- "Material": 65.57,
1123
- "Size": 72.92,
1124
- "Shape": 61.25,
1125
- "Color": 92.5,
1126
- "Action-Overall": 69.14,
1127
- "Hand": 60.26,
1128
- "Full body": 78.57,
1129
  "Animal": 69.12,
1130
  "Non Contact": 68.88,
1131
- "Contact": 58.93,
1132
- "State": 75.94,
1133
- "Relationship-Overall": 72.77,
1134
  "Composition": 70.27,
1135
- "Similarity": 69.66,
1136
- "Inclusion": 75.54,
1137
- "Comparison": 78.91,
1138
- "Compound-Overall": 60.98,
1139
- "Imagination": 67.95,
1140
- "Feature matching": 53.91,
1141
- "Grammar-Overall": 67.65,
1142
- "Pronoun Reference": 76.84,
1143
- "Consistency": 55.56,
1144
- "Negation": 68.08,
1145
- "Layout-Overall": 74.44,
1146
- "2D": 76.84,
1147
  "3D": 71.97,
1148
  "Logical Reasoning": 42.05,
1149
- "Text": 12.93
1150
  },
1151
  {
1152
  "model": "FLUX.1-dev",
@@ -1400,40 +1400,40 @@
1400
  "hf": "https://huggingface.co/ByteDance-Seed/BAGEL-7B-MoT",
1401
  "open_source": true,
1402
  "release_date": "2025-05",
1403
- "Overall": 60.66,
1404
- "Style": 89.3,
1405
- "World Knowledge": 84.81,
1406
- "Attribute-Overall": 66.45,
1407
- "Quantity": 61.11,
1408
- "Expression": 46.15,
1409
- "Material": 69.34,
1410
- "Size": 78.47,
1411
- "Shape": 55.62,
1412
- "Color": 94.17,
1413
- "Action-Overall": 60.74,
1414
- "Hand": 54.49,
1415
- "Full body": 59.78,
1416
- "Animal": 68.38,
1417
- "Non Contact": 58.16,
1418
- "Contact": 52.98,
1419
- "State": 69.81,
1420
- "Relationship-Overall": 70.18,
1421
- "Composition": 75.0,
1422
- "Similarity": 68.33,
1423
- "Inclusion": 71.2,
1424
- "Comparison": 60.16,
1425
- "Compound-Overall": 56.06,
1426
- "Imagination": 63.52,
1427
- "Feature matching": 48.44,
1428
- "Grammar-Overall": 65.78,
1429
- "Pronoun Reference": 73.53,
1430
- "Consistency": 66.67,
1431
- "Negation": 56.92,
1432
- "Layout-Overall": 74.63,
1433
- "2D": 77.94,
1434
- "3D": 71.21,
1435
- "Logical Reasoning": 30.91,
1436
- "Text": 7.76
1437
  },
1438
  {
1439
  "model": "BLIP3-o",
@@ -1441,40 +1441,40 @@
1441
  "hf": "https://huggingface.co/BLIP3o/BLIP3o-Model-8B",
1442
  "open_source": true,
1443
  "release_date": "2025-05",
1444
- "Overall": 59.71,
1445
- "Style": 91.4,
1446
- "World Knowledge": 79.59,
1447
- "Attribute-Overall": 63.68,
1448
- "Quantity": 53.47,
1449
- "Expression": 59.62,
1450
- "Material": 63.21,
1451
- "Size": 75.0,
1452
- "Shape": 51.88,
1453
- "Color": 84.17,
1454
- "Action-Overall": 63.12,
1455
- "Hand": 54.49,
1456
- "Full body": 69.02,
1457
- "Animal": 68.38,
1458
- "Non Contact": 59.69,
1459
- "Contact": 50.6,
1460
- "State": 74.06,
1461
- "Relationship-Overall": 67.89,
1462
- "Composition": 73.99,
1463
- "Similarity": 62.78,
1464
- "Inclusion": 65.22,
1465
- "Comparison": 64.84,
1466
- "Compound-Overall": 54.25,
1467
- "Imagination": 62.76,
1468
- "Feature matching": 45.57,
1469
- "Grammar-Overall": 67.65,
1470
- "Pronoun Reference": 78.31,
1471
- "Consistency": 59.72,
1472
- "Negation": 63.08,
1473
- "Layout-Overall": 68.1,
1474
- "2D": 74.63,
1475
- "3D": 61.36,
1476
- "Logical Reasoning": 40.23,
1477
- "Text": 1.15
1478
  },
1479
  {
1480
  "model": "CogView4",
@@ -1523,40 +1523,40 @@
1523
  "hf": "https://huggingface.co/Tencent-Hunyuan/HunyuanDiT",
1524
  "open_source": true,
1525
  "release_date": "2024-05",
1526
- "Overall": 51.07,
1527
- "Style": 92.9,
1528
- "World Knowledge": 78.8,
1529
- "Attribute-Overall": 63.14,
1530
- "Quantity": 70.14,
1531
- "Expression": 47.44,
1532
- "Material": 69.34,
1533
- "Size": 62.5,
1534
- "Shape": 46.88,
1535
  "Color": 86.67,
1536
- "Action-Overall": 48.95,
1537
  "Hand": 35.9,
1538
- "Full body": 53.8,
1539
- "Animal": 56.62,
1540
- "Non Contact": 43.37,
1541
- "Contact": 37.5,
1542
- "State": 63.68,
1543
- "Relationship-Overall": 59.52,
1544
- "Composition": 61.49,
1545
- "Similarity": 62.78,
1546
- "Inclusion": 59.24,
1547
  "Comparison": 50.78,
1548
- "Compound-Overall": 41.11,
1549
- "Imagination": 48.21,
1550
- "Feature matching": 33.85,
1551
- "Grammar-Overall": 56.28,
1552
- "Pronoun Reference": 66.18,
1553
- "Consistency": 56.94,
1554
- "Negation": 45.38,
1555
- "Layout-Overall": 45.15,
1556
- "2D": 38.97,
1557
- "3D": 51.52,
1558
- "Logical Reasoning": 23.41,
1559
- "Text": 1.44
1560
  },
1561
  {
1562
  "model": "Janus",
@@ -1564,40 +1564,40 @@
1564
  "hf": "https://huggingface.co/deepseek-ai/Janus-1.3B",
1565
  "open_source": true,
1566
  "release_date": "2024-10",
1567
- "Overall": 50.4,
1568
- "Style": 90.1,
1569
- "World Knowledge": 70.41,
1570
- "Attribute-Overall": 54.7,
1571
- "Quantity": 35.42,
1572
- "Expression": 38.46,
1573
- "Material": 61.79,
1574
- "Size": 66.67,
1575
- "Shape": 42.5,
1576
- "Color": 88.33,
1577
- "Action-Overall": 49.43,
1578
- "Hand": 30.77,
1579
- "Full body": 51.63,
1580
  "Animal": 62.5,
1581
- "Non Contact": 44.9,
1582
- "Contact": 35.71,
1583
- "State": 67.92,
1584
- "Relationship-Overall": 53.3,
1585
- "Composition": 52.7,
1586
- "Similarity": 51.67,
1587
- "Inclusion": 58.15,
1588
  "Comparison": 50.0,
1589
- "Compound-Overall": 46.26,
1590
- "Imagination": 56.89,
1591
  "Feature matching": 35.42,
1592
- "Grammar-Overall": 57.62,
1593
- "Pronoun Reference": 65.07,
1594
- "Consistency": 49.07,
1595
- "Negation": 56.92,
1596
- "Layout-Overall": 54.66,
1597
- "2D": 55.51,
1598
- "3D": 53.79,
1599
- "Logical Reasoning": 26.36,
1600
- "Text": 1.15
1601
  },
1602
  {
1603
  "model": "Janus-flow",
@@ -1605,40 +1605,40 @@
1605
  "hf": "https://huggingface.co/deepseek-ai/JanusFlow-1.3B",
1606
  "open_source": true,
1607
  "release_date": "2024-11",
1608
- "Overall": 45.15,
1609
- "Style": 84.6,
1610
- "World Knowledge": 59.65,
1611
- "Attribute-Overall": 47.44,
1612
- "Quantity": 44.44,
1613
- "Expression": 31.41,
1614
- "Material": 51.42,
1615
- "Size": 55.56,
1616
- "Shape": 31.25,
1617
- "Color": 76.67,
1618
- "Action-Overall": 42.21,
1619
- "Hand": 22.44,
1620
- "Full body": 47.28,
1621
- "Animal": 52.94,
1622
- "Non Contact": 34.69,
1623
- "Contact": 32.14,
1624
- "State": 60.38,
1625
- "Relationship-Overall": 48.48,
1626
- "Composition": 56.08,
1627
- "Similarity": 42.78,
1628
- "Inclusion": 48.37,
1629
- "Comparison": 39.06,
1630
- "Compound-Overall": 43.3,
1631
- "Imagination": 56.38,
1632
- "Feature matching": 29.95,
1633
- "Grammar-Overall": 58.82,
1634
- "Pronoun Reference": 66.91,
1635
- "Consistency": 47.69,
1636
- "Negation": 59.62,
1637
- "Layout-Overall": 43.84,
1638
- "2D": 47.43,
1639
- "3D": 40.15,
1640
- "Logical Reasoning": 22.05,
1641
- "Text": 1.15
1642
  },
1643
  {
1644
  "model": "Emu3",
@@ -1687,40 +1687,40 @@
1687
  "hf": "https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic",
1688
  "open_source": true,
1689
  "release_date": "2024-02",
1690
- "Overall": 44.74,
1691
- "Style": 89.2,
1692
- "World Knowledge": 74.84,
1693
- "Attribute-Overall": 52.14,
1694
- "Quantity": 60.42,
1695
- "Expression": 44.23,
1696
- "Material": 54.72,
1697
- "Size": 47.22,
1698
- "Shape": 38.75,
1699
- "Color": 71.67,
1700
- "Action-Overall": 41.63,
1701
- "Hand": 28.85,
1702
- "Full body": 50.54,
1703
- "Animal": 50.74,
1704
- "Non Contact": 33.16,
1705
- "Contact": 27.38,
1706
- "State": 56.6,
1707
- "Relationship-Overall": 51.65,
1708
- "Composition": 61.15,
1709
- "Similarity": 50.56,
1710
- "Inclusion": 45.65,
1711
- "Comparison": 39.84,
1712
- "Compound-Overall": 35.7,
1713
- "Imagination": 44.64,
1714
- "Feature matching": 26.56,
1715
- "Grammar-Overall": 51.2,
1716
- "Pronoun Reference": 58.82,
1717
- "Consistency": 47.22,
1718
- "Negation": 46.54,
1719
- "Layout-Overall": 34.89,
1720
- "2D": 30.51,
1721
- "3D": 39.39,
1722
- "Logical Reasoning": 15.0,
1723
- "Text": 1.15
1724
  },
1725
  {
1726
  "model": "SDXL",
@@ -1728,40 +1728,40 @@
1728
  "hf": "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0",
1729
  "open_source": true,
1730
  "release_date": "2023-07",
1731
- "Overall": 39.61,
1732
- "Style": 86.5,
1733
- "World Knowledge": 72.94,
1734
- "Attribute-Overall": 42.52,
1735
- "Quantity": 42.36,
1736
  "Expression": 25.0,
1737
- "Material": 50.47,
1738
- "Size": 41.67,
1739
- "Shape": 31.87,
1740
- "Color": 66.67,
1741
- "Action-Overall": 33.46,
1742
- "Hand": 19.87,
1743
- "Full body": 36.96,
1744
- "Animal": 41.91,
1745
- "Non Contact": 26.02,
1746
- "Contact": 21.43,
1747
- "State": 51.42,
1748
- "Relationship-Overall": 44.04,
1749
- "Composition": 53.72,
1750
- "Similarity": 37.22,
1751
- "Inclusion": 38.04,
1752
- "Comparison": 39.84,
1753
- "Compound-Overall": 25.0,
1754
- "Imagination": 32.91,
1755
- "Feature matching": 16.93,
1756
- "Grammar-Overall": 48.13,
1757
- "Pronoun Reference": 51.84,
1758
- "Consistency": 42.59,
1759
- "Negation": 48.85,
1760
- "Layout-Overall": 29.85,
1761
- "2D": 28.31,
1762
- "3D": 31.44,
1763
- "Logical Reasoning": 12.27,
1764
- "Text": 1.44
1765
  },
1766
  {
1767
  "model": "GPT-4o",
 
703
  "hf": "-",
704
  "open_source": false,
705
  "release_date": "2025-09",
706
+ "Overall": 87.35,
707
  "Style": 98.8,
708
  "World Knowledge": 95.41,
709
  "Attribute-Overall": 88.57,
 
785
  "hf": "-",
786
  "open_source": false,
787
  "release_date": "2024-11",
788
+ "Overall": 69.75,
789
+ "Style": 93.44,
790
  "World Knowledge": 90.36,
791
+ "Attribute-Overall": 74.03,
792
+ "Quantity": 72.86,
793
+ "Expression": 51.97,
794
+ "Material": 89.42,
795
+ "Size": 68.06,
796
+ "Shape": 65.62,
797
+ "Color": 95.0,
798
+ "Action-Overall": 70.21,
799
+ "Hand": 62.18,
800
+ "Full body": 79.35,
801
+ "Animal": 82.35,
802
+ "Non Contact": 66.15,
803
+ "Contact": 60.37,
804
+ "State": 71.7,
805
+ "Relationship-Overall": 72.56,
806
+ "Composition": 74.32,
807
+ "Similarity": 62.22,
808
+ "Inclusion": 77.84,
809
+ "Comparison": 75.78,
810
+ "Compound-Overall": 67.76,
811
+ "Imagination": 71.65,
812
+ "Feature matching": 63.71,
813
+ "Grammar-Overall": 70.08,
814
  "Pronoun Reference": 71.21,
815
+ "Consistency": 67.59,
816
+ "Negation": 71.03,
817
+ "Layout-Overall": 76.33,
818
+ "2D": 77.61,
819
+ "3D": 75.0,
820
+ "Logical Reasoning": 49.31,
821
+ "Text": 33.43
822
  },
823
  {
824
  "model": "Nano Banana",
 
867
  "hf": "-",
868
  "open_source": false,
869
  "release_date": "2024-06",
870
+ "Overall": 61.96,
871
+ "Style": 87.2,
872
+ "World Knowledge": 87.18,
873
+ "Attribute-Overall": 66.35,
874
  "Quantity": 67.36,
875
+ "Expression": 48.08,
876
+ "Material": 64.15,
877
  "Size": 69.44,
878
+ "Shape": 64.38,
879
  "Color": 91.67,
880
+ "Action-Overall": 59.22,
881
+ "Hand": 55.77,
882
+ "Full body": 58.15,
883
+ "Animal": 63.24,
884
+ "Non Contact": 61.22,
885
  "Contact": 51.79,
886
+ "State": 64.15,
887
+ "Relationship-Overall": 69.04,
888
+ "Composition": 72.64,
889
  "Similarity": 66.67,
890
+ "Inclusion": 70.11,
891
+ "Comparison": 62.5,
892
+ "Compound-Overall": 54.25,
893
+ "Imagination": 60.97,
894
+ "Feature matching": 47.4,
895
+ "Grammar-Overall": 61.1,
896
+ "Pronoun Reference": 78.68,
897
+ "Consistency": 58.33,
898
+ "Negation": 45.0,
899
+ "Layout-Overall": 64.55,
900
+ "2D": 67.28,
901
+ "3D": 61.74,
902
+ "Logical Reasoning": 31.59,
903
+ "Text": 39.08
904
  },
905
  {
906
  "model": "HiDream_v2L",
 
908
  "hf": "-",
909
  "open_source": false,
910
  "release_date": "2025-07",
911
+ "Overall": 61.64,
912
+ "Style": 87.99,
913
  "World Knowledge": 89.62,
914
+ "Attribute-Overall": 64.38,
915
+ "Quantity": 65.71,
916
+ "Expression": 44.87,
917
  "Material": 57.82,
918
  "Size": 74.26,
919
+ "Shape": 59.87,
920
+ "Color": 94.92,
921
+ "Action-Overall": 59.5,
922
+ "Hand": 51.28,
923
+ "Full body": 58.56,
924
+ "Animal": 67.65,
925
+ "Non Contact": 61.98,
926
+ "Contact": 51.52,
927
+ "State": 65.09,
928
+ "Relationship-Overall": 66.62,
929
+ "Composition": 71.23,
930
  "Similarity": 64.2,
931
  "Inclusion": 65.93,
932
+ "Comparison": 60.32,
933
  "Compound-Overall": 49.28,
934
  "Imagination": 53.75,
935
  "Feature matching": 44.76,
936
+ "Grammar-Overall": 58.86,
937
+ "Pronoun Reference": 72.35,
938
+ "Consistency": 60.0,
939
+ "Negation": 44.23,
940
+ "Layout-Overall": 69.06,
941
+ "2D": 70.41,
942
+ "3D": 67.68,
943
+ "Logical Reasoning": 26.73,
944
  "Text": 44.31
945
  },
946
  {
 
949
  "hf": "-",
950
  "open_source": false,
951
  "release_date": "2025-01",
952
+ "Overall": 77.69,
953
+ "Style": 91.9,
954
+ "World Knowledge": 95.73,
955
+ "Attribute-Overall": 83.01,
956
  "Quantity": 77.08,
957
+ "Expression": 75.0,
958
+ "Material": 83.02,
959
  "Size": 89.58,
960
+ "Shape": 80.0,
961
+ "Color": 96.67,
962
+ "Action-Overall": 80.23,
963
+ "Hand": 76.92,
964
+ "Full body": 84.24,
965
+ "Animal": 83.09,
966
  "Non Contact": 76.02,
967
  "Contact": 75.6,
968
+ "State": 84.91,
969
+ "Relationship-Overall": 82.61,
970
+ "Composition": 84.12,
971
+ "Similarity": 75.56,
972
  "Inclusion": 87.5,
973
+ "Comparison": 82.03,
974
+ "Compound-Overall": 72.68,
975
+ "Imagination": 78.32,
976
+ "Feature matching": 66.93,
977
  "Grammar-Overall": 76.87,
978
+ "Pronoun Reference": 83.82,
979
+ "Consistency": 77.31,
980
  "Negation": 69.23,
981
+ "Layout-Overall": 86.75,
982
+ "2D": 88.97,
983
+ "3D": 84.47,
984
+ "Logical Reasoning": 56.82,
985
+ "Text": 50.29
986
  },
987
  {
988
  "model": "Recraft",
 
990
  "hf": "-",
991
  "open_source": false,
992
  "release_date": "2024-12",
993
+ "Overall": 62.63,
994
+ "Style": 87.2,
995
+ "World Knowledge": 90.19,
996
+ "Attribute-Overall": 68.16,
997
+ "Quantity": 68.06,
998
+ "Expression": 56.41,
999
+ "Material": 70.75,
1000
  "Size": 65.97,
1001
+ "Shape": 57.5,
1002
+ "Color": 95.83,
1003
+ "Action-Overall": 60.55,
1004
  "Hand": 50.0,
1005
  "Full body": 70.65,
1006
+ "Animal": 76.47,
1007
+ "Non Contact": 55.61,
1008
+ "Contact": 48.81,
1009
+ "State": 63.21,
1010
  "Relationship-Overall": 62.56,
1011
+ "Composition": 64.53,
1012
+ "Similarity": 59.44,
1013
+ "Inclusion": 59.24,
1014
+ "Comparison": 67.19,
1015
+ "Compound-Overall": 44.85,
1016
+ "Imagination": 43.37,
1017
+ "Feature matching": 46.35,
1018
  "Grammar-Overall": 63.64,
1019
+ "Pronoun Reference": 73.16,
1020
+ "Consistency": 58.33,
1021
+ "Negation": 58.08,
1022
+ "Layout-Overall": 57.84,
1023
+ "2D": 58.82,
1024
+ "3D": 56.82,
1025
+ "Logical Reasoning": 29.55,
1026
+ "Text": 61.78
1027
  },
1028
  {
1029
  "model": "FLUX-kontext-max",
 
1031
  "hf": "-",
1032
  "open_source": false,
1033
  "release_date": "2025-05",
1034
+ "Overall": 80.0,
1035
+ "Style": 96.59,
1036
+ "World Knowledge": 94.19,
1037
  "Attribute-Overall": 80.93,
1038
+ "Quantity": 75.69,
1039
+ "Expression": 74.32,
1040
+ "Material": 82.55,
1041
+ "Size": 86.81,
1042
+ "Shape": 74.38,
1043
  "Color": 94.17,
1044
+ "Action-Overall": 77.38,
1045
  "Hand": 67.95,
1046
+ "Full body": 83.15,
1047
  "Animal": 77.94,
1048
+ "Non Contact": 77.04,
1049
+ "Contact": 70.83,
1050
  "State": 84.43,
1051
+ "Relationship-Overall": 85.08,
1052
+ "Composition": 87.5,
1053
+ "Similarity": 78.89,
1054
+ "Inclusion": 90.0,
1055
+ "Comparison": 81.25,
1056
+ "Compound-Overall": 78.99,
1057
+ "Imagination": 83.93,
1058
+ "Feature matching": 73.96,
1059
+ "Grammar-Overall": 78.53,
1060
+ "Pronoun Reference": 84.23,
1061
+ "Consistency": 78.7,
1062
+ "Negation": 72.69,
1063
  "Layout-Overall": 85.04,
1064
  "2D": 86.74,
1065
  "3D": 83.33,
1066
+ "Logical Reasoning": 61.36,
1067
+ "Text": 61.92
1068
  },
1069
  {
1070
  "model": "FLUX-kontext-pro",
 
1072
  "hf": "-",
1073
  "open_source": false,
1074
  "release_date": "2025-05",
1075
+ "Overall": 75.84,
1076
+ "Style": 94.78,
1077
+ "World Knowledge": 91.61,
1078
+ "Attribute-Overall": 79.2,
1079
+ "Quantity": 75.0,
1080
+ "Expression": 71.62,
1081
+ "Material": 76.89,
1082
+ "Size": 84.72,
1083
+ "Shape": 74.38,
1084
  "Color": 97.5,
1085
+ "Action-Overall": 77.66,
1086
  "Hand": 75.0,
1087
+ "Full body": 79.35,
1088
+ "Animal": 80.88,
1089
+ "Non Contact": 71.94,
1090
+ "Contact": 73.21,
1091
+ "State": 84.91,
1092
+ "Relationship-Overall": 79.34,
1093
+ "Composition": 81.42,
1094
+ "Similarity": 75.56,
1095
+ "Inclusion": 83.33,
1096
+ "Comparison": 74.22,
1097
+ "Compound-Overall": 72.68,
1098
+ "Imagination": 75.0,
1099
+ "Feature matching": 70.31,
1100
+ "Grammar-Overall": 72.69,
1101
+ "Pronoun Reference": 84.23,
1102
+ "Consistency": 76.85,
1103
+ "Negation": 57.69,
1104
+ "Layout-Overall": 84.47,
1105
+ "2D": 85.98,
1106
+ "3D": 82.95,
1107
+ "Logical Reasoning": 55.68,
1108
+ "Text": 50.29
1109
  },
1110
  {
1111
  "model": "wan2.2-t2i-plus",
 
1113
  "hf": "-",
1114
  "open_source": false,
1115
  "release_date": "2025-07",
1116
+ "Overall": 64.82,
1117
+ "Style": 91.1,
1118
+ "World Knowledge": 87.34,
1119
+ "Attribute-Overall": 70.19,
1120
+ "Quantity": 76.39,
1121
  "Expression": 55.77,
1122
+ "Material": 66.51,
1123
+ "Size": 71.53,
1124
+ "Shape": 64.38,
1125
+ "Color": 94.17,
1126
+ "Action-Overall": 68.0,
1127
+ "Hand": 58.33,
1128
+ "Full body": 75.82,
1129
  "Animal": 69.12,
1130
  "Non Contact": 68.88,
1131
+ "Contact": 57.74,
1132
+ "State": 75.0,
1133
+ "Relationship-Overall": 73.03,
1134
  "Composition": 70.27,
1135
+ "Similarity": 67.98,
1136
+ "Inclusion": 77.72,
1137
+ "Comparison": 79.69,
1138
+ "Compound-Overall": 61.37,
1139
+ "Imagination": 66.92,
1140
+ "Feature matching": 55.73,
1141
+ "Grammar-Overall": 66.53,
1142
+ "Pronoun Reference": 73.9,
1143
+ "Consistency": 56.74,
1144
+ "Negation": 66.92,
1145
+ "Layout-Overall": 74.77,
1146
+ "2D": 77.49,
1147
  "3D": 71.97,
1148
  "Logical Reasoning": 42.05,
1149
+ "Text": 13.83
1150
  },
1151
  {
1152
  "model": "FLUX.1-dev",
 
1400
  "hf": "https://huggingface.co/ByteDance-Seed/BAGEL-7B-MoT",
1401
  "open_source": true,
1402
  "release_date": "2025-05",
1403
+ "Overall": 59.91,
1404
+ "Style": 90.08,
1405
+ "World Knowledge": 85.42,
1406
+ "Attribute-Overall": 67.73,
1407
+ "Quantity": 56.82,
1408
+ "Expression": 50.0,
1409
+ "Material": 73.53,
1410
+ "Size": 77.94,
1411
+ "Shape": 59.03,
1412
+ "Color": 94.44,
1413
+ "Action-Overall": 62.14,
1414
+ "Hand": 51.32,
1415
+ "Full body": 64.88,
1416
+ "Animal": 67.19,
1417
+ "Non Contact": 64.53,
1418
+ "Contact": 56.58,
1419
+ "State": 66.83,
1420
+ "Relationship-Overall": 70.64,
1421
+ "Composition": 77.31,
1422
+ "Similarity": 68.92,
1423
+ "Inclusion": 70.0,
1424
+ "Comparison": 59.17,
1425
+ "Compound-Overall": 56.86,
1426
+ "Imagination": 67.5,
1427
+ "Feature matching": 46.73,
1428
+ "Grammar-Overall": 65.85,
1429
+ "Pronoun Reference": 74.17,
1430
+ "Consistency": 64.44,
1431
+ "Negation": 58.47,
1432
+ "Layout-Overall": 76.56,
1433
+ "2D": 77.73,
1434
+ "3D": 75.44,
1435
+ "Logical Reasoning": 23.85,
1436
+ "Text": 0.0
1437
  },
1438
  {
1439
  "model": "BLIP3-o",
 
1441
  "hf": "https://huggingface.co/BLIP3o/BLIP3o-Model-8B",
1442
  "open_source": true,
1443
  "release_date": "2025-05",
1444
+ "Overall": 59.57,
1445
+ "Style": 92.81,
1446
+ "World Knowledge": 79.97,
1447
+ "Attribute-Overall": 64.77,
1448
+ "Quantity": 48.48,
1449
+ "Expression": 60.26,
1450
+ "Material": 66.67,
1451
+ "Size": 76.47,
1452
+ "Shape": 56.94,
1453
+ "Color": 83.33,
1454
+ "Action-Overall": 64.59,
1455
+ "Hand": 57.24,
1456
+ "Full body": 71.43,
1457
+ "Animal": 71.09,
1458
+ "Non Contact": 63.95,
1459
+ "Contact": 50.66,
1460
+ "State": 71.15,
1461
+ "Relationship-Overall": 65.99,
1462
+ "Composition": 70.77,
1463
+ "Similarity": 57.43,
1464
+ "Inclusion": 66.25,
1465
+ "Comparison": 65.83,
1466
+ "Compound-Overall": 54.57,
1467
+ "Imagination": 64.06,
1468
+ "Feature matching": 45.54,
1469
+ "Grammar-Overall": 69.05,
1470
+ "Pronoun Reference": 81.67,
1471
+ "Consistency": 61.11,
1472
+ "Negation": 62.29,
1473
+ "Layout-Overall": 67.19,
1474
+ "2D": 69.55,
1475
+ "3D": 64.91,
1476
+ "Logical Reasoning": 36.78,
1477
+ "Text": 0.0
1478
  },
1479
  {
1480
  "model": "CogView4",
 
1523
  "hf": "https://huggingface.co/Tencent-Hunyuan/HunyuanDiT",
1524
  "open_source": true,
1525
  "release_date": "2024-05",
1526
+ "Overall": 51.38,
1527
+ "Style": 94.1,
1528
+ "World Knowledge": 80.7,
1529
+ "Attribute-Overall": 62.71,
1530
+ "Quantity": 67.36,
1531
+ "Expression": 44.23,
1532
+ "Material": 71.7,
1533
+ "Size": 61.81,
1534
+ "Shape": 47.5,
1535
  "Color": 86.67,
1536
+ "Action-Overall": 49.05,
1537
  "Hand": 35.9,
1538
+ "Full body": 54.89,
1539
+ "Animal": 54.41,
1540
+ "Non Contact": 46.94,
1541
+ "Contact": 35.71,
1542
+ "State": 62.74,
1543
+ "Relationship-Overall": 59.64,
1544
+ "Composition": 60.14,
1545
+ "Similarity": 64.44,
1546
+ "Inclusion": 60.33,
1547
  "Comparison": 50.78,
1548
+ "Compound-Overall": 41.62,
1549
+ "Imagination": 46.68,
1550
+ "Feature matching": 36.46,
1551
+ "Grammar-Overall": 55.48,
1552
+ "Pronoun Reference": 62.87,
1553
+ "Consistency": 57.87,
1554
+ "Negation": 45.77,
1555
+ "Layout-Overall": 44.78,
1556
+ "2D": 39.34,
1557
+ "3D": 50.38,
1558
+ "Logical Reasoning": 24.55,
1559
+ "Text": 1.15
1560
  },
1561
  {
1562
  "model": "Janus",
 
1564
  "hf": "https://huggingface.co/deepseek-ai/Janus-1.3B",
1565
  "open_source": true,
1566
  "release_date": "2024-10",
1567
+ "Overall": 51.6,
1568
+ "Style": 90.08,
1569
+ "World Knowledge": 73.56,
1570
+ "Attribute-Overall": 55.34,
1571
+ "Quantity": 35.61,
1572
+ "Expression": 37.82,
1573
+ "Material": 60.29,
1574
+ "Size": 66.18,
1575
+ "Shape": 48.61,
1576
+ "Color": 90.74,
1577
+ "Action-Overall": 50.92,
1578
+ "Hand": 31.58,
1579
+ "Full body": 52.38,
1580
  "Animal": 62.5,
1581
+ "Non Contact": 50.0,
1582
+ "Contact": 39.47,
1583
+ "State": 65.87,
1584
+ "Relationship-Overall": 56.54,
1585
+ "Composition": 58.85,
1586
+ "Similarity": 52.7,
1587
+ "Inclusion": 61.25,
1588
  "Comparison": 50.0,
1589
+ "Compound-Overall": 47.1,
1590
+ "Imagination": 59.38,
1591
  "Feature matching": 35.42,
1592
+ "Grammar-Overall": 61.74,
1593
+ "Pronoun Reference": 70.0,
1594
+ "Consistency": 52.22,
1595
+ "Negation": 60.59,
1596
+ "Layout-Overall": 52.01,
1597
+ "2D": 51.82,
1598
+ "3D": 52.19,
1599
+ "Logical Reasoning": 28.74,
1600
+ "Text": 0.0
1601
  },
1602
  {
1603
  "model": "Janus-flow",
 
1605
  "hf": "https://huggingface.co/deepseek-ai/JanusFlow-1.3B",
1606
  "open_source": true,
1607
  "release_date": "2024-11",
1608
+ "Overall": 47.1,
1609
+ "Style": 86.34,
1610
+ "World Knowledge": 62.98,
1611
+ "Attribute-Overall": 49.2,
1612
+ "Quantity": 43.18,
1613
+ "Expression": 30.77,
1614
+ "Material": 55.39,
1615
+ "Size": 57.35,
1616
+ "Shape": 33.33,
1617
+ "Color": 82.41,
1618
+ "Action-Overall": 43.57,
1619
+ "Hand": 22.37,
1620
+ "Full body": 48.81,
1621
+ "Animal": 57.81,
1622
+ "Non Contact": 38.95,
1623
+ "Contact": 36.84,
1624
+ "State": 54.81,
1625
+ "Relationship-Overall": 51.45,
1626
+ "Composition": 62.69,
1627
+ "Similarity": 36.49,
1628
+ "Inclusion": 53.75,
1629
+ "Comparison": 42.5,
1630
+ "Compound-Overall": 46.49,
1631
+ "Imagination": 60.0,
1632
+ "Feature matching": 33.63,
1633
+ "Grammar-Overall": 62.8,
1634
+ "Pronoun Reference": 70.0,
1635
+ "Consistency": 51.11,
1636
+ "Negation": 64.41,
1637
+ "Layout-Overall": 45.76,
1638
+ "2D": 46.82,
1639
+ "3D": 44.74,
1640
+ "Logical Reasoning": 22.41,
1641
+ "Text": 0.0
1642
  },
1643
  {
1644
  "model": "Emu3",
 
1687
  "hf": "https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic",
1688
  "open_source": true,
1689
  "release_date": "2024-02",
1690
+ "Overall": 46.02,
1691
+ "Style": 89.78,
1692
+ "World Knowledge": 75.8,
1693
+ "Attribute-Overall": 53.86,
1694
+ "Quantity": 60.61,
1695
+ "Expression": 43.59,
1696
+ "Material": 58.33,
1697
+ "Size": 45.59,
1698
+ "Shape": 39.58,
1699
+ "Color": 81.48,
1700
+ "Action-Overall": 44.08,
1701
+ "Hand": 29.61,
1702
+ "Full body": 54.17,
1703
+ "Animal": 54.69,
1704
+ "Non Contact": 37.21,
1705
+ "Contact": 28.29,
1706
+ "State": 57.21,
1707
+ "Relationship-Overall": 53.34,
1708
+ "Composition": 63.46,
1709
+ "Similarity": 51.35,
1710
+ "Inclusion": 48.75,
1711
+ "Comparison": 40.0,
1712
+ "Compound-Overall": 35.98,
1713
+ "Imagination": 44.06,
1714
+ "Feature matching": 28.27,
1715
+ "Grammar-Overall": 54.88,
1716
+ "Pronoun Reference": 62.92,
1717
+ "Consistency": 51.11,
1718
+ "Negation": 49.58,
1719
+ "Layout-Overall": 36.38,
1720
+ "2D": 33.18,
1721
+ "3D": 39.47,
1722
+ "Logical Reasoning": 16.09,
1723
+ "Text": 0.0
1724
  },
1725
  {
1726
  "model": "SDXL",
 
1728
  "hf": "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0",
1729
  "open_source": true,
1730
  "release_date": "2023-07",
1731
+ "Overall": 40.22,
1732
+ "Style": 87.45,
1733
+ "World Knowledge": 72.28,
1734
+ "Attribute-Overall": 44.66,
1735
+ "Quantity": 41.67,
1736
  "Expression": 25.0,
1737
+ "Material": 54.9,
1738
+ "Size": 44.85,
1739
+ "Shape": 36.11,
1740
+ "Color": 68.52,
1741
+ "Action-Overall": 35.1,
1742
+ "Hand": 19.74,
1743
+ "Full body": 38.1,
1744
+ "Animal": 45.31,
1745
+ "Non Contact": 26.74,
1746
+ "Contact": 24.34,
1747
+ "State": 52.4,
1748
+ "Relationship-Overall": 46.37,
1749
+ "Composition": 55.38,
1750
+ "Similarity": 41.22,
1751
+ "Inclusion": 38.75,
1752
+ "Comparison": 43.33,
1753
+ "Compound-Overall": 26.68,
1754
+ "Imagination": 33.75,
1755
+ "Feature matching": 19.94,
1756
+ "Grammar-Overall": 48.48,
1757
+ "Pronoun Reference": 54.58,
1758
+ "Consistency": 41.67,
1759
+ "Negation": 47.46,
1760
+ "Layout-Overall": 30.8,
1761
+ "2D": 25.0,
1762
+ "3D": 36.4,
1763
+ "Logical Reasoning": 10.34,
1764
+ "Text": 0.0
1765
  },
1766
  {
1767
  "model": "GPT-4o",