Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
93.8Accuracy
7
Jun 4, 2026
64.76Accuracy
7
Jun 4, 2026
93.28Accuracy
7
Jun 4, 2026
84.3Accuracy (%)
7
Jun 2, 2026
81.66AIME 2024 Score
7
Jun 2, 2026
0.441Top-1 Accuracy
7
Jun 2, 2026
73.85Top-1 Accuracy
7
Jun 2, 2026
79.63Top-1 Accuracy
7
Jun 2, 2026
1Spearman Rho (Agreement)
7
May 29, 2026
59.2Best AIME25 Score
7
May 25, 2026
61.5Accuracy
7
May 21, 2026
67.93Kazakh (Cyrl) Accuracy
7
May 21, 2026
7.33Kazakh (Cyrl) Score
7
May 21, 2026
85.6Math500 Accuracy
7
May 20, 2026
46.5Pass@1 Score
7
May 20, 2026
6.3Pass@1
7
May 20, 2026
36.56Accuracy (MATH test)
7
May 15, 2026
79.68Accuracy
7
May 15, 2026
94.26Accuracy (avg@K)
7
May 14, 2026
33.23Avg@K
7
May 14, 2026
87.17Accuracy (avg@K)
7
May 14, 2026
68.75Average Score (avg@K)
7
May 14, 2026
77.92Avg @K Score
7
May 14, 2026
23.19Accuracy
7
May 13, 2026
0.941Pass@32
7
May 13, 2026