Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
70.65MATH Score
18
Jun 8, 2026
70.25Pass@1
18
Jun 5, 2026
90.13Pass@1
18
Jun 5, 2026
96.4Accuracy
18
Jun 5, 2026
92.4Accuracy
18
Jun 5, 2026
46.5ACC
18
Jun 5, 2026
65.4Accuracy
18
Jun 5, 2026
24.1Avg@16
18
Jun 23, 2026
86.7Accuracy (mv %)
18
Jun 1, 2026
97.3Accuracy (mv %)
18
Jun 1, 2026
96.6Accuracy
18
Jun 1, 2026
43.94Mean@8
18
Jun 1, 2026
50.83Mean@8
18
Jun 1, 2026
89.7Accuracy
18
Jun 30, 2026
28.8Delta LL (GSM8K)
18
May 29, 2026
87.3Accuracy
18
May 28, 2026
89.9Accuracy
18
May 26, 2026
49.3Accuracy
18
Jun 5, 2026
28.67P@1 Accuracy
18
May 22, 2026
33.7Accuracy
18
May 22, 2026
83.8Accuracy
18
May 22, 2026
43.2Accuracy
18
May 22, 2026
35.6Accuracy
18
May 22, 2026
81.2Accuracy
18
May 22, 2026
61.5Pass@1 Accuracy
18
May 22, 2026