Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
55.9Exact-match Accuracy
6
Jun 30, 2026
47.6Accuracy (Exact Match)
6
Jun 30, 2026
60.1Exact Match Accuracy
6
Jun 30, 2026
43.91Average Performance
6
Jun 26, 2026
5.6Pass@1
6
Jun 25, 2026
96.59Accuracy
6
Jun 23, 2026
81.6Avg@1 Score
6
Jun 19, 2026
76.3Accuracy
6
Jun 19, 2026
37.85Pass@1 Score
6
Jun 16, 2026
49.11Pass@1
6
Jun 16, 2026
63.41Pass@1
6
Jun 16, 2026
63.3Accuracy
6
Jun 16, 2026
86.7Accuracy
6
Jun 16, 2026
53.4Accuracy
6
Jun 16, 2026
82.9Accuracy
6
Jun 16, 2026
53.1Pass@8
6
Jun 15, 2026
42.41Pass@8
6
Jun 15, 2026
59Accuracy
6
Jun 11, 2026
82Pass@1 Score
6
Jun 11, 2026
89Pass@1 Accuracy
6
Jun 11, 2026
93Pass@1
6
Jun 11, 2026
2,578.42Avg Tokens
6
Jun 9, 2026
48.57PCR
6
Jun 9, 2026
43.9PCR
6
Jun 9, 2026
58.82PCR
6
Jun 9, 2026