Mathematical Reasoning on MGSM Basque
85.2AccuracyClaude 3.5 Sonnet
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude 3.5 SonnetModel Scale=Proprietary2025.06 | 85.2 | |
| 70B + CEU IENModel Scale=70B, Training Variant=+ CEU IEN2025.06 | 80 | |
| GPT-4oModel Scale=Proprietary2025.06 | 79.2 | |
| 70B INSTRUCT ENModel Scale=70B, Training Variant=INSTRUCT EN2025.06 | 76.4 | |
| 8B + CEU IENModel Scale=8B, Training Variant=+ CEU IEN2025.06 | 54 | |
| 8B + CEU IEN+EUModel Scale=8B, Training Variant=+ CEU IEN+EU2025.06 | 50.8 | |
| 8B + CEU IEUModel Scale=8B, Training Variant=+ CEU IEU2025.06 | 46.4 | |
| 8B INSTRUCT ENModel Scale=8B, Training Variant=INSTRUCT EN2025.06 | 45.6 |