List your company

Multilingual LLM-as-a-Judge on Wino-X

72.92AccuracySEMJ
49.540855.610461.6867.7496Jun 6, 2026

Evaluation results

MethodLinks
SEMJ2026.0672.9239.22
Monolingual Ref2026.0668.7529.35
Monolingual Vote2026.0667.8622.68
Base Judge2026.0666.9621.52
Multilingual Vote2026.0650.44—