MATH
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
MATH Level-4
73.1SR (%)
14
MATH Overall
68.5SR
14
MATH-500
96.4Accuracy (MATH-500)
14
Math 500
9.86S_incor
14
MATH 500
93Accuracy (ACC)
14
MATH 500
97.83Accuracy (avg@k)
14
MATH
48.7Accuracy
14
MATH (test)
52.7Exact Match (EM)
14
MATH (test)
0.001Execution Cost
14
MATH 500
87.4Accuracy
14
MATH 500
96.1Accuracy
14
MATH 500
90.4Pass@1 Rate
14
MATH
94Average Score @8
14
MATH
98.4Pass@8
14
MATH 500
79.6Accuracy
14
MATH
1Relative Cost
14
MATH 500
95.7Pass@4 Rate
14
MATH 500
81.8Average Accuracy@16
14
MATH500
82.73MATH500 Score
14
MATH500
63.6Accuracy
14
MATH
85.56Accuracy
14
MATH
56.4Overall Performance
14
MATH 500
86Avg@32
14
MATH
85.7Pass@1
14
Math500
92.35Accuracy
14