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

CanItEdit

Benchmarks

Task NameDataset NameSOTA ResultTrend
Code EditingCanItEdit
Pass@160
17
Instructional code editingCanItEdit Lazy Instructions
Pass@143.89
13
Instructional code editingCanItEdit Descriptive Instructions
Pass@153.06
13
Code EditingCanItEdit original (test)
Pass@1 (Average)39.9
9
Showing 4 of 4 rows