Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
79.6SVAMP Accuracy
8
Feb 26, 2026
69.1GSM8K Accuracy
8
Feb 26, 2026
0.776Accuracy
8
Feb 26, 2026
72.3Accuracy (Exact Match)
8
Feb 26, 2026
17.6Accuracy
8
Feb 26, 2026
34Comparable SC (%)
8
Feb 27, 2026
7,651.62Avg Context Length (tokens)
8
Feb 26, 2026
46Accuracy
8
Feb 26, 2026
9.22Pass@1 Rate
7
Jul 7, 2026
66.91Pass@1
7
Jul 7, 2026
39Score
7
Jul 3, 2026
66.7Pass@1
7
Jul 3, 2026
73Pass@1
7
Jul 3, 2026
90.45GSM8K Score
7
Jul 2, 2026
70Accuracy
7
Jun 30, 2026
76.7Accuracy
7
Jun 30, 2026
79.17Accuracy
7
Jun 26, 2026
74.5Accuracy
7
Jun 23, 2026
0.056Train Loss
7
Jun 17, 2026
48.75Accuracy
7
Jun 16, 2026
66.4Accuracy (%)
7
Jun 15, 2026
38.3Accuracy (%)
7
Jun 15, 2026
20Pass@1 Accuracy
7
Jun 8, 2026
70Pass@1 Accuracy
7
Jun 8, 2026
60AIME 2024 Score
7
Jun 8, 2026