Multimodal Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
72.8Accuracy
25
Jun 1, 2026
77.7Accuracy
25
Feb 26, 2026
70.83Average Accuracy
25
Feb 26, 2026
55Std-10 Score
25
Feb 27, 2026
105.2Relative Average Performance
24
May 14, 2026
46.4ME Score
24
Apr 13, 2026
35.7ME Score
24
Apr 13, 2026
82.5Accuracy
24
Feb 26, 2026
39.2Accuracy
23
Feb 26, 2026
57.88Accuracy
23
Feb 26, 2026
55Accuracy
22
May 22, 2026
26.35Accuracy
22
Jun 4, 2026
45.59Accuracy
21
Jun 23, 2026
51.1MMMU-Pro mean@8 Acc
21
May 12, 2026
2,304Perception Score
21
Apr 14, 2026
35Pass@1
21
Jun 9, 2026
57.14Accuracy
21
May 21, 2026
54.6FEI Average
20
May 22, 2026
48.71FEI Score
20
May 22, 2026
46.07FEI
20
May 22, 2026
55.06FEI Score
20
May 22, 2026
53.8Accuracy
19
Jun 11, 2026
64.35MMBench Accuracy
19
May 12, 2026
33.7Accuracy
19
Mar 5, 2026
90.8Accuracy
19
Feb 26, 2026