Abstract Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
80Success Rate
4
Jun 4, 2026
0RHAE
4
May 26, 2026
3.54Frugality Index (Fp)
4
May 15, 2026
19.4Accuracy
4
Feb 26, 2026
92.2Accuracy
4
Feb 26, 2026
70.5Accuracy
4
Feb 26, 2026
89.9Accuracy
4
Feb 26, 2026
86.8Accuracy
2
Feb 26, 2026
76.11Accuracy
1
Jul 1, 2026
98.03Accuracy
1
Apr 30, 2026
62.6Accuracy
1
Apr 30, 2026