Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Stylistic Naturalness Comparison on Stylistic Naturalness Evaluation
Loading...
0.22
Distance from 1.0
pythia-410m-λ-5.0
-3.9152
23.9974
51.91
79.8226
Apr 8, 2026
Distance from 1.0
Relative Improvement vs λ=5.0
Updated 5d ago
Evaluation Results
Method
Method
Links
Distance from 1.0
Relative Improvement vs λ=5.0
pythia-410m-λ-5.0
Size=410M
2026.04
0.22
-
Llama-3.2-3B (base)
Size=3B
2026.04
2.97
92.6
OLMo-1B (base)
Size=1B
2026.04
7.08
96.9
Gemma-2-2b-it
Size=2B
2026.04
9.13
97.6
Llama-3.2-3B-Instruct
Size=3B
2026.04
9.87
97.8
OLMo-1B-Instruct
Size=1B
2026.04
103.6
99.8
Feedback
Search any
task
Search any
task