Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
77Acc
81
Mar 20, 2026
89.6Accuracy
81
May 19, 2026
93.3AIME 2026 Accuracy
80
Jun 9, 2026
95.22Accuracy
80
Jun 9, 2026
68.1Pass@1
80
Mar 18, 2026
88Accuracy (ZH)
80
Jun 2, 2026
97.6Accuracy
79
May 29, 2026
93.3Pass@1 Accuracy
79
Jun 12, 2026
89.2Accuracy
79
Feb 26, 2026
52.9Pass@1
78
Jun 23, 2026
79.17Accuracy
78
Jun 23, 2026
88.4Accuracy
78
Jun 9, 2026
96.4Pass@1
77
May 7, 2026
83.8Accuracy
77
Jun 2, 2026
95.24Accuracy (ACC)
76
Jun 16, 2026
80.2Accuracy
75
Mar 13, 2026
68.3Pass@1 Accuracy
73
May 7, 2026
80.9Accuracy
73
Jun 24, 2026
82.1GSM-Sym Accuracy
73
Apr 6, 2026
85.2Accuracy
73
Apr 9, 2026
91.2Accuracy
73
Feb 26, 2026
25.6Accuracy
72
Jun 2, 2026
0.766Accuracy
72
Mar 25, 2026
68.4Pass@k Accuracy
71
Jun 8, 2026
95.2Accuracy (%)
71
Jul 2, 2026