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

CollegeMATH

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mathematical ReasoningCollegeMATH
Accuracy52.5
276
Mathematical ReasoningCollegeMath (test)
Accuracy49.5
89
Mathematical ReasoningCollegeMath
Mean Value (MV)52.56
15
Showing 3 of 3 rows