Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Stylistic Alignment on Frontier API Corpora
Loading...
0.22
Deviation from 1.0
pythia-410m-λ-5.0
-0.2628
2.9961
6.255
9.5139
Apr 8, 2026
Deviation from 1.0
Improvement vs. λ=5.0
Updated 5d ago
Evaluation Results
Method
Method
Links
Deviation from 1.0
Improvement vs. λ=5.0
pythia-410m-λ-5.0
Model Scale=410M, Entr...
2026.04
0.22
-
gemini-2.5-flash
Model Tier=Frontier
2026.04
6.82
96.7
gpt-4o-mini
Model Tier=Frontier
2026.04
7.21
96.9
claude-3-5-haiku
Model Tier=Frontier
2026.04
12.29
98.2
Feedback
Search any
task
Search any
task