Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
60.6Average@16
15
Feb 26, 2026
88.5Average@16
15
Feb 26, 2026
31.8Average@16
15
Feb 26, 2026
29.2Average@16
15
Feb 26, 2026
53.3Pass@1 Mean
15
Apr 15, 2026
58.04Accuracy
15
Feb 26, 2026
0.868Accuracy
15
Feb 26, 2026
22.7Accuracy Delta (%)
15
Feb 26, 2026
0.8Delta Accuracy
15
Mar 19, 2026
98.35P@1
15
Feb 26, 2026
96.66p@1 Accuracy
15
Feb 26, 2026
82.08P@1
15
Feb 26, 2026
87.92p@1
15
Feb 26, 2026
40Sample Count
15
Feb 26, 2026
40Sample Count
15
Feb 26, 2026
88.92Accuracy (k=8)
15
Mar 20, 2026
90Overall Accuracy
15
May 19, 2026
1.39Speedup (x)
15
Feb 26, 2026
92.14Accuracy
15
Feb 26, 2026
45.5Accuracy
15
Feb 26, 2026
62.5Accuracy
15
Feb 26, 2026
75Accuracy
15
Feb 26, 2026
67.8Accuracy
15
Feb 26, 2026
68.8Accuracy (ave@32)
14
Jul 7, 2026
77.6Accuracy (ave@32)
14
Jul 7, 2026