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

MathChat

Benchmarks

Task NameDataset NameSOTA ResultTrend
Error CorrectionMathChat-EC (test)
Accuracy84.7
10
Follow-up Question AnsweringMathChat-FQA 1st turn
Accuracy83.4
10
Mathematical dialogueMathChat
Normalized Score77.87
5
Dialogue-based Mathematical Problem SolvingMathChat
R189.7
2
Showing 4 of 4 rows