Logical reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
11.3LRL
27
May 12, 2026
58.9Accuracy
27
May 21, 2026
100Accuracy
26
May 7, 2026
63.55Accuracy
26
Jun 15, 2026
93.5Accuracy
25
May 7, 2026
99.4Accuracy
25
May 7, 2026
99.5Accuracy
25
May 7, 2026
86.4Accuracy
24
Jun 4, 2026
88.31Accuracy (DetectiveQA)
24
May 14, 2026
98.8BPA
24
Feb 26, 2026
91.66Accuracy
24
Feb 26, 2026
99.7Accuracy
24
Feb 26, 2026
91.1Normal Score
23
May 29, 2026
62Accuracy
23
Feb 26, 2026
56.2Accuracy
23
Feb 26, 2026
75Accuracy
23
Feb 26, 2026
91.8Accuracy
23
Feb 26, 2026
78.1Accuracy
23
Feb 26, 2026
74.35Accuracy
22
May 13, 2026
43.16Accuracy
22
Feb 26, 2026
53.6Accuracy
21
Jun 2, 2026
27.5Accuracy
21
Jun 2, 2026
60.3Accuracy
21
Jun 2, 2026
86.8Accuracy
21
Jun 2, 2026
84Accuracy
21
May 26, 2026