Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
79.51Average@32
12
Jun 16, 2026
77.5EM Accuracy
12
Jun 16, 2026
52.2EM Accuracy
12
Jun 16, 2026
33.3EM Accuracy
12
Jun 16, 2026
36.7EM Accuracy
12
Jun 16, 2026
84.6EM (Accuracy)
12
Jun 16, 2026
66.7Accuracy
12
Jun 16, 2026
97.5Accuracy
12
Jun 16, 2026
80.2Accuracy
12
Jun 16, 2026
86.9Accuracy
12
Jun 12, 2026
50.4Accuracy
12
Jun 11, 2026
74Accuracy
12
Jun 11, 2026
89.9Accuracy
12
Jun 11, 2026
41.1Score
12
Jun 11, 2026
72.2Score
12
Jun 11, 2026
62Accuracy
12
Jun 11, 2026
1.9Average Score @16
12
Jun 11, 2026
71.9Average Score @16
12
Jun 11, 2026
49.4Avg@16
12
Jun 11, 2026
81.6Accuracy (%)
12
Jun 11, 2026
77.7Accuracy
12
Jun 11, 2026
0.16Wall-clock Time (s)
12
Jun 11, 2026
0.98Wall-clock Time (s)
12
Jun 11, 2026
47.43Wall-clock Time (s)
12
Jun 11, 2026
83.4Mean@4
12
Jun 9, 2026