Mathematical Problem Solving
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
2,677.2AUTC Score
17
Mar 5, 2026
31Mean@32 Accuracy
16
Jun 23, 2026
46.7Mean@32 Accuracy
16
Jun 23, 2026
60.4Mean@32 Accuracy
16
Jun 23, 2026
100AIME 2026 Score
16
Jul 2, 2026
90.8Pass@1
16
May 19, 2026
76.67Accuracy
16
Jun 9, 2026
78.6Avg@5 Accuracy
16
Feb 26, 2026
0.909Avg@5 (%)
16
Feb 26, 2026
94.3Avg@5 (%)
16
Feb 26, 2026
76.75Accuracy
16
Feb 26, 2026
96Accuracy
15
Jun 18, 2026
93.5Accuracy
15
Apr 28, 2026
89.5Pass@1
15
Mar 4, 2026
74.2Pass@1
15
Mar 4, 2026
31.33Accuracy
15
Feb 26, 2026
91.6Pass@1
15
May 8, 2026
73.54Accuracy (avg@k)
14
May 12, 2026
80.21Accuracy (avg@k)
14
May 12, 2026
97.83Accuracy (avg@k)
14
May 12, 2026
71Accuracy
14
Apr 28, 2026
31.66Accuracy
13
Jun 23, 2026
93.75Score
13
May 20, 2026
85.7Accuracy
13
Apr 28, 2026
97.5pass@1
13
Feb 26, 2026