Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
67.34Accuracy@5
54
Jun 1, 2026
76.31Acc@5
54
Jun 1, 2026
96.5Accuracy (GSM8K)
54
Jul 1, 2026
97Accuracy (%)
54
Apr 10, 2026
95Pass@1 Accuracy
54
Apr 6, 2026
72.2Pass@1 Accuracy
54
Apr 6, 2026
80Pass@1
54
Apr 6, 2026
75Accuracy
54
Jun 23, 2026
94.7Accuracy
54
Mar 24, 2026
46.6pass@1 Mean
54
May 7, 2026
77.9Accuracy
54
Apr 21, 2026
68.4Accuracy
54
Apr 9, 2026
99.4Accuracy
54
Jun 4, 2026
71.1Accuracy
54
Feb 26, 2026
89.57Score
54
Feb 26, 2026
73.7Pass@1
54
Feb 26, 2026
76.4Accuracy
54
Jun 9, 2026
59.24GSM8K Score
53
Apr 14, 2026
67.8Average Score (avg@32)
53
Jun 19, 2026
68.4Accuracy
53
Feb 26, 2026
71.9Accuracy
53
Mar 16, 2026
80.8Accuracy (%)
52
May 26, 2026
93.3Accuracy
52
May 26, 2026
54.53Pass@1 Accuracy
52
May 26, 2026
83.33AIME 24 Score
52
Jun 26, 2026