Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
93.3Pass@1
6
Feb 26, 2026
94.92Last Score
6
Feb 26, 2026
0.526Last Score
6
Feb 26, 2026
36.71Accuracy
6
Feb 26, 2026
70.7Accuracy
6
Feb 26, 2026
56.4Avg@32 Acc
6
Feb 26, 2026
49.59Avg@32 Accuracy
6
Feb 26, 2026
87.71Avg@32 Accuracy
6
Feb 26, 2026
89.24Accuracy
6
Feb 26, 2026
0.33Inference Cost (USD)
6
Feb 26, 2026
0.387Inference Cost (USD)
6
Feb 26, 2026
0.84pass@1
6
Feb 26, 2026
85.2P@1
6
Feb 26, 2026
73.3MATH Score
6
Feb 26, 2026
80Pass@128
6
Feb 27, 2026
86.7Pass@128
6
Feb 27, 2026
28.22pass@8
6
Feb 26, 2026
25.62Pass@1
6
Feb 26, 2026
86MATH500 Score
6
Feb 26, 2026
23.96Average Score (AIME 24)
6
Feb 26, 2026
66.56Average@16
6
Feb 26, 2026
79.8Accuracy
6
Feb 26, 2026
0.233Pass@1
6
Feb 26, 2026
79.7Mean Accuracy
6
Feb 26, 2026
90.4avg@8 Score
6
Feb 26, 2026