Knowledge-based reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
64.89Accuracy
19
Feb 26, 2026
73.33Accuracy
19
Feb 26, 2026
30.3Accuracy (%)
19
Feb 26, 2026
67.5Accuracy
19
Feb 26, 2026
34.96Accuracy (DK)
8
Jun 4, 2026
92.83Accuracy
8
Feb 26, 2026
86.13Accuracy
8
Feb 26, 2026