Human Preference Evaluation on Basque Arena
1,183Arena Content ScoreGPT-4o
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| GPT-4oModel Scale=Proprietary2025.06 | 1,183 | 1,093 | 1,188 | |
| Claude 3.5 SonnetModel Scale=Proprietary2025.06 | 1,150 | 1,082 | 1,153 | |
| 70B + CEU IENModel Scale=70B, Training Variant=+ CEU IEN2025.06 | 1,127 | 1,083 | 1,141 | |
| 8B + CEU IEN+EUModel Scale=8B, Training Variant=+ CEU IEN+EU2025.06 | 1,047 | 1,038 | 1,050 | |
| 8B + CEU IEUModel Scale=8B, Training Variant=+ CEU IEU2025.06 | 1,045 | 1,034 | 1,050 | |
| 8B + CEU IENModel Scale=8B, Training Variant=+ CEU IEN2025.06 | 1,031 | 1,036 | 1,038 | |
| 8B INSTRUCT ENModel Scale=8B, Training Variant=INSTRUCT EN2025.06 | 766 | 783 | 722 |