Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
93.97Mean@4
23
Jun 9, 2026
49Accuracy
23
Feb 26, 2026
77.8Accuracy
23
May 22, 2026
77.9Accuracy
22
Jul 7, 2026
98Accuracy (GSM8K)
22
Jun 19, 2026
47.1Pass@1
22
Jun 17, 2026
45.2Pass@1
22
Jun 17, 2026
83.8Pass@1
22
Jun 17, 2026
68.5Pass@1
22
Jun 17, 2026
17.8Pass@1
22
Jun 17, 2026
32.8Pass@1
22
Jun 17, 2026
91.5MATH500 Score
22
May 28, 2026
62.29Accuracy (GSM+)
22
Jun 24, 2026
61.2MATH Score
22
Jul 2, 2026
45.96Pass@1
22
Jun 30, 2026
74.8Accuracy
22
Jul 2, 2026
83Pass@1
22
Jun 17, 2026
76.2Accuracy
22
Apr 21, 2026
97.2Accuracy
22
Apr 21, 2026
33.3AIME24 Score
22
Apr 7, 2026
42.07Pass@16
22
May 8, 2026
92.6pass@32
22
May 15, 2026
43.56Pass@1
22
Mar 24, 2026
56.62Pass@1
22
Mar 24, 2026
47.1Pass@1 Accuracy
22
May 8, 2026