Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
61.5Pass@16
24
Jun 9, 2026
2.02ECE
24
Jun 5, 2026
66.67Accuracy (%)
24
Jul 9, 2026
97.4Accuracy
24
Jun 4, 2026
73.3Accuracy
24
Jun 30, 2026
97.12maj@16 Accuracy
24
May 29, 2026
97.2Maj@16
24
May 29, 2026
67.03Maj@16
24
May 29, 2026
46.32maj@16
24
May 29, 2026
6.99Speedup
24
May 29, 2026
7.64Speedup
24
May 29, 2026
37.4Mean@16 Score
24
May 28, 2026
63.8Mean@16
24
May 28, 2026
25Accuracy
24
May 27, 2026
30Accuracy
24
May 27, 2026
78Peak Accuracy
24
May 27, 2026
92.1Accuracy
24
May 22, 2026
69Pass@16 (Avg)
24
May 22, 2026
65.6Pass@16
24
May 22, 2026
53.3Pass@16
24
May 22, 2026
71.7Avg@16 Accuracy
24
May 22, 2026
25Avg@16
24
May 22, 2026
66.42Average Accuracy
24
Jun 30, 2026
80Accuracy
24
May 19, 2026
49.6Pass@k
24
May 13, 2026