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

SingleEq

Benchmarks

Task NameDataset NameSOTA ResultTrend
Arithmetic ReasoningSingleEq
Accuracy98.8
73
Arithmetic ReasoningSingleEq (test)
Accuracy0.971
18
Math reasoningSingleeq
EM0.8307
10
Mathematical ReasoningSingleEq
Accuracy (SingleEq)93.2
7
Mathematical ReasoningSingleEQ (test)
Accuracy99.01
4
Mathematical ReasoningSINGLEEQ
Solve Rate96.1
4
Online Out-of-Distribution DetectionSingleEq Near-shift OOD
Accuracy93.15
3
Showing 7 of 7 rows