Multilingual LLM-as-a-Judge on Wino-X-Mt
50.44AccuracySEMJ
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SEMJ2026.06 | 50.44 | 0.3156 | |
| Multilingual Vote2026.06 | 50.15 | — | |
| Base Judge2026.06 | 48.97 | 0.2563 | |
| Monolingual Ref2026.06 | 48.97 | 0.2209 | |
| Monolingual Vote2026.06 | 48.08 | 0.2319 |