Multiple Choice Question Answering on EusTrivia
84.6AccuracyClaude 3.5 Sonnet
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude 3.5 SonnetModel Scale=Proprietary2025.06 | 84.6 | |
| GPT-4oModel Scale=Proprietary2025.06 | 80.7 | |
| 70B + CEU IENModel Scale=70B, Training Variant=+ CEU IEN2025.06 | 74.17 | |
| 70B INSTRUCT ENModel Scale=70B, Training Variant=INSTRUCT EN2025.06 | 62.51 | |
| 8B + CEU IEUModel Scale=8B, Training Variant=+ CEU IEU2025.06 | 62.33 | |
| 8B + CEU IEN+EUModel Scale=8B, Training Variant=+ CEU IEN+EU2025.06 | 62.1 | |
| 8B + CEU IENModel Scale=8B, Training Variant=+ CEU IEN2025.06 | 61.05 | |
| 8B INSTRUCT ENModel Scale=8B, Training Variant=INSTRUCT EN2025.06 | 45.01 |