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

Penguins

Benchmarks

Task NameDataset NameSOTA ResultTrend
Object CountingPenguins (Mixed)
Max Count9.81
6
Object CountingPenguins Separated
Max Count3.74
6
Logical ReasoningPenguins
Accuracy72.734
4
Symbolic ReasoningPenguins
Solve Rate93.3
4
Showing 4 of 4 rows