Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
90.4Accuracy (GSM8K)
12
May 12, 2026
31Accuracy
12
May 12, 2026
4.7Acceptance Length
12
May 12, 2026
53.6Accuracy
12
May 12, 2026
76.1Accuracy
12
May 12, 2026
38.2Accuracy
12
May 12, 2026
54.59Accuracy
12
May 12, 2026
73.3Pass@16
12
May 12, 2026
86.7Pass@16
12
May 12, 2026
52.4Exact Match
12
Jun 30, 2026
80.6Accuracy
12
May 6, 2026
25.24Accuracy
12
Apr 24, 2026
32Accuracy
12
Apr 24, 2026
75.93Accuracy
12
Apr 24, 2026
94Accuracy
12
Apr 24, 2026
38.6Accuracy (MATH500)
12
Apr 21, 2026
67.3Accuracy
12
Apr 21, 2026
71.7AMC 23 Score
12
Apr 20, 2026
65.7Average Score
12
Apr 16, 2026
52.19Accuracy
12
Apr 15, 2026
44.7Average Accuracy
12
May 7, 2026
57.4Accuracy
12
Apr 13, 2026
78.79Score
12
Apr 13, 2026
34.34Score
12
Apr 13, 2026
86.67Pass@K
12
Apr 13, 2026