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

Formulation QA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Formulation QAFormulation QA (Standard)
Accuracy58.7
12
Formulation QAFormulation QA (OOD)
Accuracy39.4
6
Showing 2 of 2 rows