Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
78.33Accuracy on AIME 2024
20
Jun 23, 2026
92.1Accuracy (ACC)
20
Jun 23, 2026
68.14Math Score
20
Jun 19, 2026
10.88Success Score
20
Jun 17, 2026
17.31Accuracy
20
Jun 16, 2026
67.59Mean@32
20
Jun 11, 2026
85.4Mean@32
20
Jun 11, 2026
82.81Mean@32
20
Jun 11, 2026
34.58Mean@32
20
Jun 11, 2026
47.4Pass@1 Accuracy
20
Jun 9, 2026
71.4Accuracy
20
Jun 4, 2026
89.2Accuracy
20
Jun 4, 2026
76.7Accuracy
20
Jun 4, 2026
69.7Accuracy
20
Jun 4, 2026
5.97Speedup
20
May 29, 2026
75.5Accuracy
20
May 28, 2026
92.4Accuracy
20
May 28, 2026
81.96GSM8K Accuracy
20
May 27, 2026
73.9AVG@K
20
May 26, 2026
63.2AVG@K
20
May 26, 2026
73.3AVG@K
20
May 26, 2026
44Accuracy
20
May 26, 2026
83.8Accuracy (SVAMP)
20
May 26, 2026
76.7Accuracy
20
May 25, 2026
40.86P@1
20
May 22, 2026