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

CPP-Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Formal Language GenerationCPP-Bench
Syntactic Accuracy@197
16
Constrained DecodingCPP-Bench
Avg Inference Time (s)7.17
16
Functional CorrectnessCPP-Bench
Functional Success Rate @138.1
16
Showing 3 of 3 rows