Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
27.5Peak Accuracy
12
May 27, 2026
37.3Peak Accuracy
12
May 27, 2026
52.57Accuracy
12
May 26, 2026
65.21Accuracy
12
May 26, 2026
55.57Accuracy
12
May 26, 2026
87.93Accuracy
12
May 26, 2026
24.58Accuracy
12
May 26, 2026
29.58Accuracy
12
May 26, 2026
76.4AIME 2024 Score
12
May 26, 2026
6.7Pass@16 Accuracy
12
May 25, 2026
67Accuracy
12
May 22, 2026
58.2Solve Rate (MATH)
12
May 21, 2026
82.22Accuracy
12
May 21, 2026
93.33AIME 24 Accuracy
12
May 21, 2026
46.8Accuracy
12
May 20, 2026
68.7Accuracy
12
May 19, 2026
63.1Accuracy
12
May 19, 2026
53.3Accuracy
12
May 19, 2026
70Accuracy
12
May 19, 2026
93.6Accuracy
12
May 19, 2026
43.4Accuracy@1
12
May 15, 2026
69.7Accuracy @ 1
12
May 15, 2026
48.1Accuracy (Numina)
12
May 14, 2026
81.88Absolute Score
12
May 13, 2026
40Accuracy (Exact Match)
12
Jul 1, 2026