Math Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
68.2Accuracy (%)
23
May 18, 2026
16.16Accuracy
23
Apr 14, 2026
99.7MultiArith
23
Apr 21, 2026
76.7Accuracy
22
Apr 24, 2026
77.8Accuracy
22
Apr 8, 2026
78Accuracy (Seen)
21
May 26, 2026
66.2Pass@1
21
May 11, 2026
34.9Accuracy (HMMT25)
21
May 6, 2026
86.2BA @20
20
May 29, 2026
72Accuracy
20
Jul 3, 2026
93.1AMC23 Score
20
May 19, 2026
11.7Pass@1
19
Apr 2, 2026
48.2Pass@1 Accuracy
19
Feb 26, 2026
40.53Pass@1
18
Jun 30, 2026
43.1Average Accuracy
18
Apr 23, 2026
66.3Accuracy
18
Apr 23, 2026
68.6Pass@1
18
Apr 13, 2026
63.3Pass@1
18
Apr 14, 2026
62.4Pass@1 Accuracy
18
May 21, 2026
65.78Pass@16
18
Apr 2, 2026
86.58Pass@1
18
Apr 28, 2026
61.09Accuracy
17
Jun 9, 2026
34.3Multi@5 Accuracy
16
Jun 1, 2026
58.2Multi@5 Accuracy
16
Jun 1, 2026
76.7AIME 25 Accuracy
16
Jul 7, 2026