Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language Modeling Utility on LM Eval Harness
Loading...
0.48
HellaSwag Accuracy
Pre Edit
0.456
0.468
0.48
0.492
Jun 9, 2025
HellaSwag Accuracy
Perplexity (OpenAI Lambada)
Perplexity (Standard Lambada)
Perplexity (Wikitext)
Winogrande Accuracy
PIQA Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
HellaSwag Accuracy
Perplexity (OpenAI Lambada)
Perplexity (Standard Lambada)
Perplexity (Wikitext)
Winogrande Accuracy
PIQA Accuracy
Pre Edit
Model State=Pre-edit
2025.06
0.48
3.98
5.96
10.88
0.65
0.76
PME
Model State=Post-edit
2025.06
0.48
4.07
6.48
10.89
0.65
0.76
MEMIT
Model State=Post-edit
2025.06
0.48
4.24
6.59
10.93
0.64
0.76
Feedback
Search any
task
Search any
task
