Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Pruning Evaluation on PIQA and ARC-Easy
Loading...
94.2
Relative Retention (S_Com)
SparseGPT
17.448
37.374
57.3
77.226
Jun 2, 2026
Relative Retention (S_Com)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Relative Retention (S_Com)
SparseGPT
Calibration=IGSP (ours...
2026.06
94.2
SparseGPT
Calibration=MetaMath,...
2026.06
81.83
Magnitude
Calibration=None, Mode...
2026.06
20.4
Feedback
Search any
task
Search any
task
