Multimodal Evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
115.8Relative Score
23
Mar 4, 2026
1,787.7Absolute Score
20
Apr 8, 2026
1,898.94MME Score
19
May 12, 2026
1,510Perception Score (P)
18
May 26, 2026
82.2Accuracy
18
May 26, 2026
100.22Average Percentage
16
May 4, 2026
100Average Score
16
Apr 21, 2026
61.4Accuracy
16
May 26, 2026
38.9Score
15
Jun 9, 2026
51.6Rubric Reward
15
May 20, 2026
77.1Accuracy
15
Feb 26, 2026
1,534.8MME Score
14
Jun 18, 2026
1,864Perception Score
14
Apr 13, 2026
1,687MME-P Score
14
Feb 26, 2026
54MMBench Score
13
May 27, 2026
1,851MME Score
13
May 18, 2026
1,376.2Perception Score
13
Apr 7, 2026
62.65Accuracy
13
Feb 26, 2026
94.9Score
12
Feb 27, 2026
1,821.3Accuracy
12
Feb 27, 2026
41.19CLIP-S Score
12
Feb 27, 2026
590MME-C Score
11
May 4, 2026
703.8Score
11
Feb 26, 2026
1,579.6MME Score
10
Jun 18, 2026
1,687MMEPerc Score
10
Jun 11, 2026