Multimodal Evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
2,565.72Score
902
Jul 3, 2026
64Score
249
Jul 7, 2026
2,375.9MME Score
179
Jun 23, 2026
69.5Accuracy
177
Jun 30, 2026
82.8Accuracy
163
Jul 3, 2026
86MMB^CN Score
146
Jul 1, 2026
1,864MME-P Score
139
Jun 23, 2026
77.3Accuracy
117
Jun 9, 2026
121.88Score
73
May 27, 2026
2,631.7Total Score
67
May 19, 2026
83Accuracy
67
Jun 23, 2026
61.9GQA
59
Jun 25, 2026
79.2LLaVA-Bench Score
48
May 29, 2026
81.6Score
46
May 15, 2026
60.37Overall Score
43
Mar 9, 2026
60.21Score
43
Mar 9, 2026
97.3Overall Score
43
Jul 7, 2026
57.6Score
36
May 15, 2026
85.31Score
34
Jul 1, 2026
52.48Score
30
Jun 17, 2026
1,854.51Total Score
30
Jul 1, 2026
71.67Accuracy
29
Mar 9, 2026
100Relative Accuracy
28
Apr 13, 2026
66.8SEED-Bench Score
28
Mar 9, 2026
71.2Accuracy
24
Jul 2, 2026