Multimodal Evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
603.57MME-c Score
10
Apr 24, 2026
57.8Score
10
Apr 7, 2026
77.39Accuracy
10
Feb 27, 2026
80.1Accuracy
10
Feb 26, 2026
78.5Accuracy
10
Feb 26, 2026
69.1Average Score
10
Feb 26, 2026
56.82Average Score
10
Feb 26, 2026
78SeedBench Score
8
Jun 26, 2026
61.82Score
8
Feb 26, 2026
67.9SEEDI Score
7
Jul 7, 2026
57.8Perceptual Score
7
Jun 24, 2026
60.84GQA
7
Feb 26, 2026
70.2Accuracy
7
Feb 27, 2026
0.629SEED Score
7
Feb 26, 2026
200MME Translation Score
6
May 13, 2026
1,478Token Count
6
Feb 26, 2026
37.7Recognition Accuracy
5
Jun 26, 2026
165Count Score
4
May 7, 2026
357.5Conceptual Score (C)
4
May 4, 2026
1,414P-score
4
Feb 26, 2026
67.6Score
4
Feb 26, 2026
75.6Score
4
Feb 26, 2026
100.9Relative Score (%)
3
Jun 1, 2026
63.9Accuracy
3
May 4, 2026
285.4BD-Metric
3
Feb 26, 2026