Multiple-choice question answering on Multiple-choice benchmarks EN
75.78AccuracyQwen3 14B merge-EU
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen3 14B merge-EUBackbone=Qwen3 14B, Variant=merge-EU2026.03 | 75.78 | |
| Llama 3.1 8B merge-EUBackbone=Llama 3.1 8B, Variant=merge-EU2026.03 | 75.08 | |
| Qwen3 14B merge-ESBackbone=Qwen3 14B, Variant=merge-ES2026.03 | 74.78 | |
| Qwen3 14B merge-multiBackbone=Qwen3 14B, Variant=merge-multi2026.03 | 74.77 | |
| Qwen3 14B merge-CABackbone=Qwen3 14B, Variant=merge-CA2026.03 | 74.5 | |
| Qwen3 14B merge-GLBackbone=Qwen3 14B, Variant=merge-GL2026.03 | 74.28 | |
| Llama 3.1 8B merge-ESBackbone=Llama 3.1 8B, Variant=merge-ES2026.03 | 74.24 | |
| Llama 3.1 8B merge-multiBackbone=Llama 3.1 8B, Variant=merge-multi2026.03 | 74.06 | |
| Llama 3.1 8B InstructBackbone=Llama 3.1 8B, Variant=Instruct2026.03 | 73.87 | |
| Llama 3.1 8B joint-EUBackbone=Llama 3.1 8B, Variant=joint-EU2026.03 | 73.71 | |
| Llama 3.1 8B merge-GLBackbone=Llama 3.1 8B, Variant=merge-GL2026.03 | 73.56 | |
| Llama 3.1 8B merge-CABackbone=Llama 3.1 8B, Variant=merge-CA2026.03 | 73.48 | |
| Qwen3 8B merge-EUBackbone=Qwen3 8B, Variant=merge-EU2026.03 | 72.67 | |
| Qwen3 8B merge-ESBackbone=Qwen3 8B, Variant=merge-ES2026.03 | 72.44 | |
| Qwen3 8B merge-multiBackbone=Qwen3 8B, Variant=merge-multi2026.03 | 72.19 | |
| Qwen3 14B InstructBackbone=Qwen3 14B, Variant=Instruct2026.03 | 71.82 | |
| Qwen3 8B merge-GLBackbone=Qwen3 8B, Variant=merge-GL2026.03 | 71.47 | |
| Qwen3 8B merge-CABackbone=Qwen3 8B, Variant=merge-CA2026.03 | 71.1 | |
| Qwen3 8B InstructBackbone=Qwen3 8B, Variant=Instruct2026.03 | 69.84 | |
| ALIA 40B InstructBackbone=ALIA 40B, Variant=Instruct2026.03 | 66.04 | |
| Salamandra 7B InstructBackbone=Salamandra 7B, Variant=Instruct2026.03 | 57.27 | |
| Salamandra 2B InstructBackbone=Salamandra 2B, Variant=Instruct2026.03 | 37.13 |