Mathematical Problem Solving
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
97.6Accuracy
229
Mar 10, 2026
95.86Accuracy
114
Jun 18, 2026
100Accuracy
113
Apr 30, 2026
93Accuracy
96
Jun 23, 2026
93.3Accuracy
84
Jun 23, 2026
100Score
76
May 20, 2026
86.3Accuracy
60
Mar 24, 2026
78.4Score
59
May 25, 2026
38.5Accuracy
58
Jun 16, 2026
76.67Top-1 Accuracy
54
May 18, 2026
1,289.8AIME Score
52
Mar 5, 2026
91.67Top-1 Accuracy (%)
46
May 11, 2026
93.22Accuracy
45
Jun 30, 2026
95.7Accuracy
40
Apr 21, 2026
15.69Average Time
39
May 12, 2026
3.94Average Time
39
May 12, 2026
15.58Average Time
39
May 12, 2026
81.5Accuracy
30
Jun 4, 2026
98Accuracy Ratio
30
Mar 4, 2026
85Accuracy
28
May 11, 2026
64.9Accuracy
28
Feb 26, 2026
97.81Accuracy (avg@k)
27
Jun 23, 2026
78.36Pass@1
27
May 22, 2026
68.8Accuracy
26
Feb 26, 2026
95.66Accuracy
24
May 19, 2026