Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Physical Commonsense Reasoning on PIQA (val test)
Loading...
79.42
Accuracy
LLaDA (Base)
58.1624
63.6812
69.2
74.7188
Feb 19, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
LLaDA (Base)
Pruning Ratio=0.0
2026.02
79.42
Sink-Aware (Ours)
Pruning Ratio=0.3
2026.02
69.55
LLaDA-structure
Pruning Ratio=0.3
2026.02
68.34
Sink-Aware (Ours)
Pruning Ratio=0.5
2026.02
60.37
LLaDA-structure
Pruning Ratio=0.5
2026.02
58.98
Feedback
Search any
task
Search any
task