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

CCP

Benchmarks

Task NameDataset NameSOTA ResultTrend
Refusal EvaluationCCP Sensitive
Reject Rate92.35
13
Component-Configurator-ProblemCCP Overall (test)
Solving Percentage89
3
Component-Configurator-ProblemCCP Hard split
Solving Percentage96
3
Component-Configurator-ProblemCCP (Easy)
Solving Percentage100
3
Showing 4 of 4 rows