Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
49.8Pass@1
19
Apr 14, 2026
81.6Accuracy
19
May 11, 2026
92.33Accuracy
19
Jun 2, 2026
89.39Average Score @16
19
Mar 11, 2026
70.22Pass@1
19
Mar 11, 2026
64.76Pass@1
19
Mar 11, 2026
73.37pass@1 Score
19
Mar 11, 2026
102.5Retention Percentage
19
Mar 10, 2026
94.6Accuracy
19
Mar 4, 2026
46.2Pass@1
19
Mar 4, 2026
95pass@1
19
May 21, 2026
54.4Pass@1
19
Feb 27, 2026
74.3AIME 24 Score
19
Feb 26, 2026
85.9Accuracy
19
Feb 26, 2026
82.5Pass@1
19
Apr 14, 2026
81.11ALL Accuracy
19
Feb 26, 2026
91.2Pass@3 Accuracy
19
Feb 26, 2026
76Pass@3 Accuracy
19
Feb 26, 2026
58.5Accuracy
19
Feb 26, 2026
47.4Pass@1
19
Feb 26, 2026
88.78Pass@1
19
Feb 26, 2026
51.2Mean@64 Acc
19
Feb 26, 2026
53.6Mean@64 Accuracy
19
Feb 26, 2026
78.02Average Accuracy
19
Feb 26, 2026
45.19Pass@1
18
Jul 7, 2026