Logical reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
84Accuracy
21
May 26, 2026
54Accuracy
21
Apr 20, 2026
1.05G(W) Error
20
Jun 15, 2026
85.26Accuracy
20
Jun 11, 2026
50.94Accuracy
20
May 26, 2026
76.6Accuracy
20
Apr 23, 2026
73.8Accuracy
20
Apr 23, 2026
90.2Accuracy
20
Apr 23, 2026
75.6Accuracy
20
Apr 16, 2026
43Accuracy
20
Mar 24, 2026
90Accuracy
20
Mar 24, 2026
81.03Pass@1
20
Jun 2, 2026
99.61Accuracy
20
Feb 26, 2026
46.6Acc@t1
20
Feb 26, 2026
52.1SynLogic Score
19
Feb 26, 2026
38.7Accuracy
18
Jun 30, 2026
98Accuracy
18
Jun 2, 2026
71.7Accuracy
18
May 28, 2026
0.69PPL2
18
Apr 13, 2026
0.88Pass@1 Accuracy
18
Feb 26, 2026
8.7pass@1
18
Feb 26, 2026
79BPA
18
Feb 26, 2026
93.4BPA Score
18
Feb 26, 2026
76.8Accuracy
17
May 27, 2026
24.38Balanced Accuracy
17
Feb 26, 2026