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

ComplexInstruct

Benchmarks

Task NameDataset NameSOTA ResultTrend
Instruction FollowingComplexInstruct Level 2
ISR94.6
32
Instruction FollowingComplexInstruct Level 6
ISR64.2
23
Instruction FollowingComplexInstruct Level 5
ISR0.76
23
Instruction FollowingComplexInstruct Level 4
ISR82.2
23
Instruction FollowingComplexInstruct Level 3
ISR88.7
23
Instruction FollowingComplexInstruct Level 1
ISR0.982
23
Instruction FollowingComplexInstruct Level 6 v1.0
ISR23.6
9
Instruction FollowingComplexInstruct Level 5 v1.0
Instruction Success Rate36.4
9
Instruction FollowingComplexInstruct Level 4 v1.0
ISR51.4
9
Instruction FollowingComplexInstruct Level 3 v1.0
ISR66.6
9
Instruction FollowingComplexInstruct Level 2 v1.0
ISR81.3
9
Instruction FollowingComplexInstruct Level 1 v1.0
ISR95
9
Showing 12 of 12 rows