Abstract Visual Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
100Accuracy (Pass@2)
33
May 14, 2026
99.4Accuracy
28
Mar 4, 2026
98Accuracy (Pass@2)
27
Apr 10, 2026
98.7Accuracy
25
Apr 30, 2026
93.6Average Accuracy
22
Feb 26, 2026
27.3Accuracy
15
Feb 26, 2026
90.4Accuracy
12
Mar 4, 2026
77.4Accuracy
12
Mar 4, 2026
0.631Accuracy
12
Mar 4, 2026
50.3Accuracy
12
Mar 4, 2026
39.8Accuracy
12
Mar 4, 2026
32.1Accuracy
12
Mar 4, 2026
22.7Accuracy
12
Mar 4, 2026
93.2Avg Accuracy
11
Feb 26, 2026
42.4CVR Score
9
Feb 26, 2026
100Accuracy
6
Feb 26, 2026
98.3Accuracy
5
Feb 26, 2026
68.4Classification Accuracy
5
Feb 26, 2026
31.2Accuracy
5
Feb 26, 2026
41.2Accuracy
4
Feb 26, 2026
36Accuracy
4
Feb 26, 2026