Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

StruQ

Benchmarks

Task NameDataset NameSOTA ResultTrend
Structured Query Instruction FollowingStruQ clean
Capability78.89
8
Instruction Adherence and Security RobustnessStruQ 1.0 (Adversarial)
Capability Score85.46
4
Instruction Adherence and Security RobustnessStruQ Clean 1.0
Capability Score84.87
4
Showing 3 of 3 rows