MathQA
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
MathQA
98.84Accuracy
354
MathQA (test)
87.6Accuracy
52
MathQA (test)
81.05Accuracy
41
MathQA
78.7Accuracy
36
MathQA (test)
81.5Accuracy
34
MathQA
25.19Retention
28
MathQA
28.4Accuracy
26
MathQA
75.9CACC
25
MathQA OOD (test)
63Accuracy
24
MathQA
44Accuracy
20
MathQA
66.15Accuracy
18
MathQA
80.2Accuracy
12
MathQA
98.18Q Score
12
MathQA
52.4Exact Match
12
MathQA leave-one-out setup
56.9Average Accuracy
12
MathQA
2,555Average Acceptance Length τ
12
MathQA
52.34Exact Match (EM)
10
MathQA
64.55Accuracy
8
MathQA
0.344ECE' Gain
8
MathQA Python
87.4Pass@80
8
MathQA
24.32Accuracy
7
MathQA
43.45Accuracy
6
MathQA
60.1Exact Match Accuracy
6
MathQA (test)
83Program Accuracy
6
MathQA
64Accuracy
4