Symbolic Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
90.4Accuracy
68
May 14, 2026
92.4Accuracy
67
Mar 24, 2026
100Accuracy
45
Mar 24, 2026
0.819Accuracy
31
May 14, 2026
99.9Accuracy
27
Mar 24, 2026
80.3Accuracy
26
Feb 26, 2026
36.5Accuracy
25
Feb 26, 2026
80.3Accuracy
25
Feb 26, 2026
49.61Accuracy
24
Feb 26, 2026
90.5Solve Rate
14
Feb 26, 2026
100Accuracy
12
Feb 27, 2026
86.96Accuracy
11
Feb 26, 2026
80.75Accuracy
10
Mar 24, 2026
99.5Accuracy
10
Feb 27, 2026
87.2Accuracy
10
Feb 26, 2026
100Calibrated Accuracy
8
Feb 26, 2026
81.9Accuracy
8
Feb 26, 2026
98LLC-4 Accuracy
7
Feb 27, 2026
99.4Accuracy
7
Feb 26, 2026
47.5Pass@2
6
Mar 6, 2026
65.7Accuracy
6
Feb 26, 2026
98.6Accuracy
6
Feb 26, 2026
0.187Accuracy (Clean, Avg)
5
Feb 26, 2026
42.7Acc (Clean, Avg)
5
Feb 26, 2026
67.52Accuracy
4
Feb 26, 2026