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

ClassEval

Benchmarks

Task NameDataset NameSOTA ResultTrend
Code GenerationClassEval
Spd4.28
33
Code Generation and Watermark DetectionClassEval (test)
Pass@521
14
Code GenerationClassEval
Pass@1 (Class-level)27
9
Showing 3 of 3 rows