Multiple Choice Question Answering on ItaBench translated multiple-choice
57.92ARC-E (Italian)Qwen3
Evaluation Results
| Method | Links | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Qwen32025.12 | 57.92 | 35.78 | 46.47 | 30.21 | 51.82 | 62.18 | 63.76 | 43.84 | 53.4 | 79.39 | 61.7 | 57.9 | 57.92 | 53.28 | |
| Gemma32025.12 | 53.54 | 35.16 | 48.03 | 30.32 | 38.52 | 60.99 | 64.14 | 47.58 | 53.81 | 80.41 | 63.98 | 61.25 | 52.46 | 53.09 | |
| Gamayun2025.12 | 52.57 | 35.78 | 52.93 | 32.61 | 42.24 | 62.18 | 61.62 | 41.84 | 54.21 | 85.89 | 64.74 | 58.7 | 58.61 | 54.15 | |
| EuroLM2025.12 | 50.64 | 34.36 | 52.2 | 33.2 | 24.37 | 61.16 | 63.64 | 44.76 | 61.42 | 85.18 | 65.27 | 58.27 | 50.64 | 53.31 | |
| Qwen2.52025.12 | 47.21 | 32.33 | 47.82 | 31.1 | 49.06 | 61.93 | 65.03 | 49.07 | 45.08 | 85.58 | 60.89 | 61.15 | 57.62 | 53.37 | |
| Llama3.22025.12 | 44.11 | 28.8 | 42.62 | 29.48 | 37.81 | 59.2 | 63.51 | 47.44 | 45.58 | 81.42 | 60.54 | 61.64 | 56.94 | 50.7 |