Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
83.4Score
17
Feb 26, 2026
42.38GSM8K Score
17
Feb 26, 2026
66.4m1@t1
17
Feb 26, 2026
43.27Accuracy
16
Jul 7, 2026
37.6Accuracy
16
Jul 3, 2026
71.5Accuracy
16
Jun 23, 2026
92.6Accuracy
16
Jun 23, 2026
74.7Mean@32 Accuracy
16
Jun 23, 2026
57.4Accuracy
16
Jun 30, 2026
88.1Accuracy
16
Jun 23, 2026
90.5Response Accuracy
16
Jun 17, 2026
83.8Accuracy
16
Jun 16, 2026
69.34Accuracy
16
Jun 11, 2026
70.7Pass@1 Accuracy
16
Jun 11, 2026
83Pass@1 Accuracy
16
Jun 11, 2026
4.757Acceptance Length (τ)
16
Jun 11, 2026
86.67Accuracy
16
Jun 11, 2026
86.67Accuracy
16
Jun 11, 2026
33.6Accuracy
16
Jun 4, 2026
57.5Accuracy
16
Jun 4, 2026
73.3Accuracy
16
Jun 4, 2026
57.5Accuracy
16
Jun 4, 2026
55.88GSM8K Score
16
Jun 4, 2026
75pass@4 Accuracy
16
Jun 2, 2026
11.11pass@4 Accuracy
16
Jun 2, 2026