Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
61.5Accuracy
35
May 19, 2026
58.7Mistral-7B Accuracy
35
Apr 24, 2026
94.8Accuracy
35
Apr 23, 2026
98.6Pass@k
35
May 8, 2026
62.1Pass@1
35
May 22, 2026
100Accuracy
35
Apr 21, 2026
93.3Accuracy
35
Feb 27, 2026
89.1Top-1 Accuracy (maj@1)
35
Feb 26, 2026
98.2Accuracy
35
Jun 9, 2026
93.1Pass@1
35
Feb 26, 2026
98Accuracy
35
Feb 26, 2026
23.8Accuracy
35
Apr 14, 2026
51.3Accuracy
35
Apr 14, 2026
92.1Accuracy (MATH500)
34
Jul 7, 2026
86.3Accuracy (AIME24)
34
Jun 9, 2026
86.7Pass@1 Accuracy
34
Jun 8, 2026
62.1Accuracy
34
Jun 30, 2026
78.3Pass@1 Accuracy
34
Apr 28, 2026
17.9Avg@32
34
Jun 23, 2026
68.5Math Aggregate Score
34
Apr 7, 2026
62.5Accuracy
34
Jun 12, 2026
47Accuracy
34
Feb 26, 2026
91.2Accuracy
34
Feb 26, 2026
80.8Accuracy
34
May 13, 2026
77.08Accuracy
33
Jun 16, 2026