Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
46.38Accuracy
11
May 28, 2026
94.7Overall Accuracy
11
May 26, 2026
97.5Overall Accuracy
11
May 26, 2026
97.3Overall Accuracy
11
May 26, 2026
98.4Overall Accuracy
11
May 26, 2026
57.5Testing Accuracy
11
Jun 30, 2026
92.1Accuracy (n=15)
11
May 21, 2026
46.2Accuracy
11
Jun 8, 2026
18.13Average Score (@16)
11
May 14, 2026
1,986.5Token Count
11
Apr 24, 2026
97.2Accuracy
11
Apr 23, 2026
19.1CoT-E
11
Apr 21, 2026
53.7CoT-E
11
Apr 21, 2026
21.2CoT Error
11
Apr 21, 2026
65.2CoT-E
11
Apr 21, 2026
56.7CoT-E
11
Apr 21, 2026
57Accuracy
11
Jun 19, 2026
47.6Accuracy
11
Apr 20, 2026
95.6Accuracy
11
May 8, 2026
54.89GSM8K Accuracy
11
Apr 14, 2026
100Completion Rate
11
Apr 9, 2026
63.5Score
11
Apr 7, 2026
83.2Pass@1 Accuracy (avg@64)
11
Apr 2, 2026
90.5Pass@1 (avg@64)
11
Apr 2, 2026
75Accuracy
11
May 22, 2026