Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
83.3Pass@1
25
May 28, 2026
51.47Accuracy
25
Mar 4, 2026
84.38Avg@16 Accuracy
25
May 29, 2026
93.1AVG@8
25
Feb 26, 2026
93.33Accuracy
25
Feb 26, 2026
82.65Pass@1
25
Feb 26, 2026
88.9Accuracy
25
Feb 26, 2026
93.1Solve Rate
25
Mar 6, 2026
17GSM-Hard Accuracy
24
Jul 1, 2026
6.16Speedup Ratio
24
Jul 1, 2026
6.17Speedup Ratio
24
Jul 1, 2026
63.3Accuracy
24
Jul 2, 2026
79.8Accuracy
24
Jun 24, 2026
59.2Accuracy
24
Jun 24, 2026
46.92Final Accuracy
24
Jun 23, 2026
48.57Accuracy (GSM-Hard)
24
Jun 17, 2026
80.64Accuracy
24
Jun 17, 2026
59.07Pass@1
24
Jun 16, 2026
64.6Accuracy
24
Jun 16, 2026
73.3Accuracy
24
Jun 16, 2026
96.2Accuracy
24
Jun 16, 2026
32.69Average Score @16
24
Jun 9, 2026
46.72Avg@16
24
Jun 9, 2026
8.33Avg@16
24
Jun 9, 2026
29.06Average Score @16
24
Jun 9, 2026