Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.646Avg@5
48
Feb 26, 2026
93.7Token Savings
48
Feb 26, 2026
84.1Token Savings
48
Feb 26, 2026
68.1Token Savings
48
Feb 26, 2026
80.2Accuracy
48
Jun 4, 2026
38.36Accuracy
48
Feb 26, 2026
0.839Accuracy
48
Feb 26, 2026
72.5Pass@1
48
May 13, 2026
88.9Accuracy
47
Jun 9, 2026
156.22Gain
47
May 13, 2026
70.7Avg@16 Accuracy
47
May 28, 2026
76.1Accuracy (ACC)
47
May 27, 2026
97.66SAT Math Accuracy
47
Mar 20, 2026
95.27Strict Match Accuracy
47
Jun 1, 2026
41.54Pass@1
46
Jun 12, 2026
45Acc
46
May 22, 2026
75.4Average Score
46
Jun 30, 2026
87.5Pass@1
46
Feb 26, 2026
74.1Accuracy
46
Apr 14, 2026
56Accuracy
45
Jun 30, 2026
0.95Sel-AUC
45
Jun 17, 2026
0.849Sel-AUC
45
Jun 17, 2026
42.29Avg@16
45
Jun 9, 2026
75Avg@16
45
Jun 9, 2026
97.2Answer Accuracy
45
Feb 26, 2026