Abstract Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
83.41AbsR Accuracy
56
Feb 26, 2026
77.1Pass@2
24
Jun 16, 2026
97.8Accuracy (Overall)
21
Apr 21, 2026
60Accuracy
18
Jun 26, 2026
97Accuracy
18
Jun 26, 2026
98Accuracy
17
Jun 4, 2026
97.29Accuracy
16
Jun 26, 2026
79.6Pass@2
12
Jun 2, 2026
100Accuracy
11
May 20, 2026
100Accuracy
10
Jul 1, 2026
72Mean Accuracy
10
Apr 24, 2026
79.3Mean Accuracy
10
Apr 24, 2026
63.04Accuracy
9
Jun 26, 2026
61.1Mean Accuracy
8
Apr 24, 2026
100Accuracy
7
Feb 26, 2026
63.21Accuracy
5
May 20, 2026
55.93Pass@k
5
Mar 10, 2026
24.6Accuracy
5
Feb 26, 2026
79.9Accuracy
5
Feb 26, 2026
45.2Accuracy
5
Feb 26, 2026
68.6Accuracy
5
Feb 26, 2026
36.8Accuracy
5
Feb 26, 2026
70.1Accuracy
5
Feb 26, 2026
77Accuracy
5
Feb 26, 2026
77.3Accuracy
5
Feb 26, 2026