Our new X account is live! Follow @wizwand_team for updates

Linguistic Minimal Pair Evaluation on BLiMP, SLING, and RuBLiMP Combined (test)

0.928Average Score

Llama (GPb+CT)

Updated 4d ago

Evaluation Results

Method	Links
Llama (GPb+CT) 2025.06		0.928
Llama (GPb) 2025.06		0.884
Llama (CT) 2025.06		0.8
Llama (Base) 2025.06		0.788