Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Mathematical Equation Generation on MAWPS (5-fold cross-validation)

92.5Accuracy (5-fold)

Self-Consistency†

75.44479.87284.388.728Oct 14, 2023
Updated 1mo ago

Evaluation Results

MethodLinks
2023.10
92.5
92.3
2023.10
92.2
92.2
2023.10
92.1
2023.10
91.8
2023.10
91.8
2023.10
91.5
2023.10
91.3
2023.10
89.8
2023.10
89.6
2023.10
88.7
2023.10
88.5
2023.10
88.4
2023.10
88
2023.10
86.9
2023.10
85.6
2023.10
84.2
2023.10
84
2023.10
83.4
2023.10
82.6
2023.10
82
2023.10
76.1