Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
64Accuracy
7
Apr 13, 2026
72Accuracy
7
Apr 13, 2026
66Accuracy
7
Apr 13, 2026
58Accuracy (ZH)
7
Apr 13, 2026
336Tokens at Best Step (K)
7
Apr 10, 2026
1,640Tokens at Best Step (K)
7
Apr 10, 2026
98.5Accuracy
7
Apr 7, 2026
97.8Accuracy
7
Apr 7, 2026
72.16Average Score
7
Mar 31, 2026
87.5Avg@8 Score
7
Mar 31, 2026
18.8Accuracy (Xho)
7
Mar 24, 2026
58.4Accuracy
7
Mar 24, 2026
94Avg@4 Score
7
Mar 12, 2026
93Average Accuracy @16
7
Mar 12, 2026
82.1Avg@16 Score
7
Mar 12, 2026
95.3Accuracy
7
May 12, 2026
28.56Average Accuracy
7
Mar 11, 2026
57.5Accuracy (AMC)
7
Mar 4, 2026
92.55GSM Score
7
Feb 26, 2026
65.77Average Accuracy
7
Feb 26, 2026
70MATH 500 Score
7
Feb 26, 2026
66.45Avg Accuracy
7
Feb 26, 2026
51.1GSM8K Accuracy
7
Feb 26, 2026
37.2Accuracy
7
Feb 26, 2026
0.815Acc
7
Feb 26, 2026