Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
100Pass@1 Accuracy
71
Jun 9, 2026
68.2Accuracy
70
Jun 30, 2026
89.52Accuracy
70
Jun 15, 2026
94Accuracy
70
Jun 2, 2026
93.33Pass Rate@8
68
Jun 17, 2026
10.86Speedup
68
Jun 19, 2026
98.5Pass@1
68
May 8, 2026
92.2Pass@1
68
Jun 16, 2026
53.3Accuracy (%)
67
Apr 10, 2026
88.2Pass@1
67
Mar 24, 2026
48.1Accuracy
67
Apr 20, 2026
51.2Accuracy
67
Jun 30, 2026
0.738PRR
66
Apr 29, 2026
88.8Accuracy (Bn)
66
Jun 25, 2026
92.3Acc@4
66
Feb 26, 2026
79.9Pass@1 Accuracy
66
May 26, 2026
84.44Accuracy
66
Jun 1, 2026
88.6Pass@16
65
Mar 6, 2026
100Accuracy (Pass@1)
65
May 28, 2026
80pass@1
65
Feb 26, 2026
53.4Accuracy
64
Jun 30, 2026
45.8Pass@k Accuracy
64
Jun 8, 2026
40.4Pass@k Accuracy
64
Jun 8, 2026
46Pass@k Accuracy
64
Jun 8, 2026
48Pass@k Accuracy
64
Jun 8, 2026