Generalization Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
60.9Accuracy
18
Mar 31, 2026
51Average Accuracy
14
Apr 2, 2026
61.6Average@16 Accuracy
14
Apr 2, 2026
40.4Average@16 Accuracy
14
Apr 2, 2026
37.5Total Score
9
Feb 26, 2026
49.25Average Score
3
May 29, 2026