Visual Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
87.2Accuracy
13
Jun 1, 2026
76.9Score
12
Jun 11, 2026
75.25Overall Score
12
Jul 7, 2026
31.7Accuracy
12
Jun 2, 2026
39Score
12
Apr 28, 2026
93.6Overall Score
12
Feb 26, 2026
62Performance Gain Sum
12
Apr 21, 2026
92.2Overall Score
11
Feb 26, 2026
72Accuracy
11
Feb 26, 2026
58.3Accuracy
11
Feb 26, 2026
80.8Accuracy
11
Feb 26, 2026
81.1Accuracy
11
Feb 26, 2026
83.9Accuracy
11
Feb 26, 2026
97.7Overall Accuracy
11
Feb 26, 2026
77.33Accuracy
10
Jun 12, 2026
93.33Accuracy
10
Jun 12, 2026
85.71Accuracy
10
Jun 12, 2026
86.3Union Score
10
May 26, 2026
83Union Score
10
May 26, 2026
92Union
10
May 26, 2026
90Union Score
10
May 26, 2026
92.3Union Score
10
May 26, 2026
92.1Average Accuracy
10
Mar 13, 2026
100Accuracy (Scale 16)
10
Mar 13, 2026
100Accuracy (Scale 3)
10
Mar 13, 2026