Multiple Choice Question Answering on EusExams
82.68AccuracyClaude 3.5 Sonnet
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude 3.5 SonnetModel Scale=Proprietary2025.06 | 82.68 | |
| GPT-4oModel Scale=Proprietary2025.06 | 79.17 | |
| 70B + CEU IENModel Scale=70B, Training Variant=+ CEU IEN2025.06 | 71.56 | |
| 70B INSTRUCT ENModel Scale=70B, Training Variant=INSTRUCT EN2025.06 | 63.28 | |
| 8B + CEU IEN+EUModel Scale=8B, Training Variant=+ CEU IEN+EU2025.06 | 56.23 | |
| 8B + CEU IEUModel Scale=8B, Training Variant=+ CEU IEU2025.06 | 56.01 | |
| 8B + CEU IENModel Scale=8B, Training Variant=+ CEU IEN2025.06 | 56 | |
| 8B INSTRUCT ENModel Scale=8B, Training Variant=INSTRUCT EN2025.06 | 46.21 |