Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
87Pass@1
12
Feb 26, 2026
95.7Pass@1
12
Feb 26, 2026
66.7Accuracy
12
Feb 26, 2026
53.6Accuracy
12
Feb 26, 2026
82.8Accuracy
12
Feb 26, 2026
85Accuracy
12
Feb 26, 2026
90Accuracy
12
Feb 26, 2026
90.9Accuracy
12
Feb 26, 2026
20AIME2025
12
Feb 26, 2026
44.2Accuracy
12
Feb 26, 2026
89.6Accuracy
12
May 26, 2026
2.3Algebra Accuracy
12
Feb 26, 2026
88.8Accuracy (Math500)
11
Jul 8, 2026
79.77Accuracy
11
Jul 7, 2026
76.12Accuracy
11
Jul 7, 2026
996Threshold
11
Jun 30, 2026
823Threshold (Thr.)
11
Jun 30, 2026
60.1Accuracy
11
Jun 26, 2026
67.52Accuracy
11
Jun 26, 2026
90Accuracy
11
Jun 19, 2026
66.6Average Score
11
Jun 11, 2026
58.28Average @ k
11
Jun 9, 2026
93.1MWP Accuracy
11
Jun 4, 2026
96.33Accuracy
11
Jun 1, 2026
76.85Accuracy
11
May 28, 2026