K&K Logic Puzzles
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
K&K Logic Puzzles OOD
99Score Threshold 2 (OOD)
25
K&K Logic Puzzles In-domain
98Accuracy (Level 3)
25
K&K Logic Puzzles
95Accuracy (Level 3)
15
K&K Logic Puzzles
96Accuracy (Level 3)
12