Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
50.8Accuracy
63
May 11, 2026
91.09Average@16
63
May 28, 2026
95.7Accuracy
63
May 21, 2026
81.9Accuracy (Avg)
62
May 28, 2026
59.6HS
62
Feb 26, 2026
97.24Accuracy
62
Apr 23, 2026
82.8Accuracy
61
May 29, 2026
6.6Average Length
61
May 29, 2026
98.9Pass@1 Score
61
May 22, 2026
79.74Accuracy
61
Feb 26, 2026
50Performance (%)
60
May 28, 2026
83.33AIME 2024 Accuracy
60
Jun 15, 2026
80.6Avg@8
60
May 29, 2026
95.83Exact Match Accuracy (GSM8K Test)
60
Apr 14, 2026
60.6Exact Match
60
Apr 14, 2026
93.63Exact Match Accuracy (GSM8K)
60
Apr 14, 2026
79.92AQuA Exact Match
60
Apr 14, 2026
60.5Pass@1 Accuracy
60
Jun 19, 2026
43Math Score
60
Feb 26, 2026
87.01Accuracy
59
Jul 2, 2026
51.6Accuracy
59
May 26, 2026
97.4Pass@1 Accuracy
59
May 11, 2026
91.67Accuracy
59
Mar 4, 2026
3,000Pass@1
59
Feb 26, 2026
35.9Accuracy
59
Feb 26, 2026