Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
57.69Average Accuracy
24
Mar 6, 2026
73Pass@1
23
Jul 9, 2026
52.5Avg@32
23
Jun 9, 2026
92.4GSM8K Score
23
May 26, 2026
94Pass@1 Accuracy
23
Jun 30, 2026
65.3Accuracy
23
Jul 8, 2026
60.58AIME24 Score
23
May 11, 2026
86.7Pass@1 Accuracy
23
May 15, 2026
19Greedy Accuracy
23
May 29, 2026
76.9Accuracy
23
Mar 31, 2026
52Acc@1
23
Apr 28, 2026
61.4Accuracy
23
Jun 2, 2026
78MATH-500 Score
23
Mar 20, 2026
1.65ECE
23
Mar 5, 2026
97Accuracy (%)
23
Mar 10, 2026
91.9pass@8
23
Feb 26, 2026
74.84Accuracy
23
Mar 31, 2026
9.9Domain Accuracy
23
Feb 26, 2026
92.4Avg@16 Score
23
Mar 4, 2026
68.38Accuracy
23
May 27, 2026
89.1Score
23
Feb 26, 2026
35.8Accuracy
23
Feb 26, 2026
61.7avg@16
23
May 11, 2026
44.25Avg Success Rate @8
23
Feb 26, 2026
93.85Avg@32 Accuracy
23
Feb 26, 2026