Logical Inference
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
76.75Task Success Rate (TSR)
30
May 28, 2026
93.39Accuracy
8
Feb 26, 2026
94.21Accuracy
8
Feb 26, 2026
95.45Accuracy
8
Feb 26, 2026
0.967Accuracy
8
Feb 26, 2026
97.5Accuracy
8
Feb 26, 2026