Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
4.44MAT Score (GSM8K)
15
Apr 30, 2026
91.37Accuracy
15
Apr 29, 2026
70.3Avg@8 Score
15
Apr 28, 2026
6.77MAT (Accuracy)
15
Apr 24, 2026
23.86AVG@8
15
Apr 23, 2026
99.75AVG@8 Success Rate
15
Apr 23, 2026
25.8Avg@16 Accuracy
15
Apr 23, 2026
44.6Avg@16 Accuracy
15
Apr 23, 2026
65.8Avg Accuracy @16
15
Apr 23, 2026
29.3Avg@16 Accuracy
15
Apr 23, 2026
46.1CoT Error
15
Apr 21, 2026
61.12Pass@1
15
Apr 14, 2026
51.58Pass@1
15
Apr 14, 2026
92.51Pass@1 Rate
15
Apr 14, 2026
82.62Pass@1
15
Apr 14, 2026
25.9AIME 2024 Score
15
Apr 13, 2026
80Accuracy
15
Apr 10, 2026
97.5Accuracy
15
Apr 10, 2026
95.4Accuracy
15
Apr 10, 2026
96.6Accuracy
15
Apr 10, 2026
0.924Accuracy
15
Apr 9, 2026
95.1Accuracy
15
Apr 9, 2026
58.93Avg@5 Accuracy
15
Apr 7, 2026
83.25Avg@10 Accuracy
15
Apr 7, 2026
36Avg@10 Accuracy
15
Apr 7, 2026