Multiple Choice Question Answering on BertaQA Local
80.45AccuracyClaude 3.5 Sonnet
Evaluation results
| Method | Links | |
|---|---|---|
| Claude 3.5 SonnetModel Scale=Proprietary2025.06 | 80.45 | |
| 70B + CEU IENModel Scale=70B, Training Variant=+ CEU IEN2025.06 | 77.71 | |
| GPT-4oModel Scale=Proprietary2025.06 | 74.83 | |
| 8B + CEU IEUModel Scale=8B, Training Variant=+ CEU IEU2025.06 | 66.07 | |
| 8B + CEU IEN+EUModel Scale=8B, Training Variant=+ CEU IEN+EU2025.06 | 65.57 | |
| 8B + CEU IENModel Scale=8B, Training Variant=+ CEU IEN2025.06 | 65.23 | |
| 70B INSTRUCT ENModel Scale=70B, Training Variant=INSTRUCT EN2025.06 | 53.51 | |
| 8B INSTRUCT ENModel Scale=8B, Training Variant=INSTRUCT EN2025.06 | 44.97 |