Math Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
95.9Accuracy
276
Jun 9, 2026
98.87Accuracy
254
Jun 1, 2026
93.55Accuracy
194
Jun 9, 2026
100Accuracy (GSM8K)
190
Jul 8, 2026
90.54Accuracy
160
May 26, 2026
95.6Accuracy
127
Jun 25, 2026
93.8Accuracy
126
Feb 26, 2026
79Accuracy
109
May 29, 2026
100Pass@1 Accuracy
99
May 26, 2026
80Accuracy
95
Mar 31, 2026
96.5Accuracy
89
Jun 9, 2026
74.4Accuracy
82
Mar 10, 2026
90.7Accuracy
76
May 20, 2026
48.5Accuracy (%)
73
Jun 23, 2026
82.6Accuracy
73
May 26, 2026
35.84Pass@1
68
May 12, 2026
40.5Pass@1 Accuracy
68
May 12, 2026
87.2Pass@1 Rate
66
May 22, 2026
98.3Accuracy
65
Apr 14, 2026
440.5Mean Wall-Clock Time (s)
61
Jun 26, 2026
96.8Pass@1 Accuracy
61
Jun 16, 2026
94.6Accuracy
60
May 18, 2026
94.4Accuracy
60
Apr 8, 2026
96Accuracy
59
May 12, 2026
56.1Accuracy
59
Jun 9, 2026