Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Generalization on LLaMA Evaluation Expanded Languages 3.1-8B
Loading...
69.37
Overall Score
DeltaMoE
58.502
61.3235
64.145
66.9665
May 18, 2026
Overall Score
Updated 15d ago
Evaluation Results
Method
Method
Links
Overall Score
DeltaMoE
Category=Baseline w/ M...
2026.05
69.37
MoLA
Category=Baseline w/ M...
2026.05
68.39
Dense-FT-Delta
Category=Baselines w/...
2026.05
66.88
Dense-FT-Avg
Category=Baselines w/...
2026.05
66.39
Dense-FT-Avg-2FLOPs
Category=Baselines w/...
2026.05
65.81
LLaMA-3.1-8B-Instruct
Category=Base Model
2026.05
64.91
Dense-FT-Delta-2FLOPs
Category=Baselines w/...
2026.05
64.38
LLaMA-Pro
Category=Baseline w/ M...
2026.05
58.92
Feedback
Search any
task
Search any
task