Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
96Pass@1
12
Jul 1, 2026
86.2MATH Score
12
Feb 26, 2026
96Pass@32
12
Feb 26, 2026
93Pass@32
12
Feb 26, 2026
90.31Accuracy
12
May 13, 2026
80Accuracy
12
Apr 21, 2026
96.2Top-1 Accuracy
12
Mar 31, 2026
74.04Accuracy
12
Feb 26, 2026
92.5Pass@1
12
Feb 26, 2026
45.1Pass@1
12
Feb 26, 2026
82.3Accuracy
12
Feb 26, 2026
89.2Accuracy
12
Feb 26, 2026
74.69Accuracy
12
Feb 26, 2026
83.3Pass@1
12
Mar 20, 2026
62.8Pass@1
12
Feb 26, 2026
64Pass@1
12
Feb 26, 2026
56Accuracy
12
Mar 4, 2026
72.5Accuracy
12
Feb 26, 2026
31.1Accuracy
12
Feb 26, 2026
83.2Accuracy
12
Feb 26, 2026
84.8Accuracy
12
Feb 26, 2026
63Pass@1
12
Feb 26, 2026
92.5Pass@1
12
Feb 26, 2026
22Avg Score @16
12
Feb 26, 2026
85.8AUC (%)
12
Feb 26, 2026