Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
43Accuracy
22
Apr 21, 2026
0.056Expected Calibration Error (ECE)
22
Mar 5, 2026
93.3Score
22
Mar 4, 2026
82.6Pass@8
22
Feb 26, 2026
89.92GSM8K Accuracy
22
May 15, 2026
73.3Pass@1
22
Jul 7, 2026
37.2Accuracy
22
Jun 1, 2026
0.952Accuracy
22
Jun 30, 2026
48.8Accuracy (avg@16)
22
Feb 26, 2026
89.8Accuracy
22
Feb 26, 2026
40.14Pass@1
22
Feb 26, 2026
87.1Pass@1
22
Feb 26, 2026
66.4AIME 24 Score
22
Jun 11, 2026
82.8Accuracy
22
Feb 26, 2026
14.6AIME24 Score
21
Jun 23, 2026
41.64Average Accuracy
21
Jun 12, 2026
20Pass@1
21
Jun 2, 2026
21.67Average Score @16
21
Jun 2, 2026
36.25Avg@16
21
Jun 2, 2026
48.1Avg@12 Accuracy
21
May 28, 2026
73.1Avg@12 Accuracy
21
May 28, 2026
79.2Avg@12 Accuracy
21
May 28, 2026
67.5AMC 2023 Score
21
May 26, 2026
36.7Raw Score
21
May 26, 2026
16.3Accuracy (HMMT25)
21
May 21, 2026