Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
98Original Accuracy
40
Apr 10, 2026
1Rank
40
Mar 20, 2026
1Rank
40
Mar 20, 2026
1Rank
40
Mar 20, 2026
1Rank
40
Mar 20, 2026
83Accuracy
40
Apr 10, 2026
93.16Accuracy
40
Mar 4, 2026
69.6GSM-Hard pass@1 Acc
40
May 26, 2026
91.3Pass@1
40
Apr 29, 2026
57.9Accuracy
40
Jun 1, 2026
47.1Avg@1 Accuracy
40
Mar 4, 2026
96.5Acc
40
Feb 26, 2026
72.5Finetune Accuracy
40
Feb 26, 2026
86.02Pass@1 Score
39
Jun 30, 2026
69Pass@16
39
Jun 9, 2026
93.3Accuracy
39
Jun 26, 2026
87Exact Match Accuracy
39
Jun 2, 2026
94.4Accuracy
39
Jul 9, 2026
94.39Accuracy
39
Feb 26, 2026
68.13Pass@1
39
Feb 26, 2026
62.1Pass@1
39
Feb 26, 2026
60.9Accuracy
39
Apr 20, 2026
68.1Pass@1 Accuracy
38
Jun 30, 2026
93.2Accuracy
38
May 28, 2026
56.7Accuracy
38
Jun 11, 2026