MathQA
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
MathQA Python Original (test)
84.7Pass@80
4
MathQA
92CSR
3
MathQA
22.1PPL
3
MathQA
100.79Normalized Performance
3
MathQA
89.2Accuracy
3
MathQA Python Filtered (dev)
20.7PASS@1
3
MathQA
22.21Accuracy
2