Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
99.2GSM8k Accuracy
28
Apr 23, 2026
71.41Accuracy
28
Apr 20, 2026
89.47FA
28
Apr 15, 2026
93.5Accuracy
28
Jun 4, 2026
25.19Retention
28
Apr 8, 2026
28.9Retention
28
Apr 8, 2026
73.39Retention
28
Apr 8, 2026
80.21Average Accuracy
28
Jun 18, 2026
0.088ECE
28
Mar 5, 2026
64.7Pass@1
28
May 7, 2026
56GSM8K Accuracy
28
Feb 26, 2026
95.52Accuracy
28
Mar 24, 2026
53.4Score
28
Feb 27, 2026
93.3Acc
28
Feb 26, 2026
95Accuracy
28
Feb 26, 2026
81.96Accuracy
28
Feb 26, 2026
48.4Accuracy
28
Feb 26, 2026
54.7Accuracy
27
Jun 18, 2026
11,381Thinking Tokens
27
Jun 17, 2026
54.79Avg@16 Accuracy
27
Jun 11, 2026
66.9Greedy Accuracy
27
May 29, 2026
86.4Accuracy
27
May 29, 2026
83.3Accuracy
27
May 19, 2026
90Accuracy
27
May 19, 2026
94.8Accuracy
27
May 19, 2026