Multiple-choice question answering on Multiple-choice benchmarks CA
66.84AccuracyQwen3 14B merge-CA
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen3 14B merge-CABackbone=Qwen3 14B, Variant=merge-CA2026.03 | 66.84 | |
| Qwen3 14B merge-multiBackbone=Qwen3 14B, Variant=merge-multi2026.03 | 65.17 | |
| Qwen3 14B merge-ESBackbone=Qwen3 14B, Variant=merge-ES2026.03 | 64.9 | |
| ALIA 40B InstructBackbone=ALIA 40B, Variant=Instruct2026.03 | 64.68 | |
| Qwen3 14B merge-EUBackbone=Qwen3 14B, Variant=merge-EU2026.03 | 64.62 | |
| Qwen3 14B merge-GLBackbone=Qwen3 14B, Variant=merge-GL2026.03 | 64.46 | |
| Llama 3.1 8B merge-CABackbone=Llama 3.1 8B, Variant=merge-CA2026.03 | 63.99 | |
| Qwen3 8B merge-CABackbone=Qwen3 8B, Variant=merge-CA2026.03 | 62.66 | |
| Qwen3 14B InstructBackbone=Qwen3 14B, Variant=Instruct2026.03 | 62.14 | |
| Llama 3.1 8B merge-multiBackbone=Llama 3.1 8B, Variant=merge-multi2026.03 | 61.72 | |
| Llama 3.1 8B InstructBackbone=Llama 3.1 8B, Variant=Instruct2026.03 | 61.56 | |
| Qwen3 8B merge-multiBackbone=Qwen3 8B, Variant=merge-multi2026.03 | 61.34 | |
| Qwen3 8B merge-EUBackbone=Qwen3 8B, Variant=merge-EU2026.03 | 60.94 | |
| Llama 3.1 8B merge-ESBackbone=Llama 3.1 8B, Variant=merge-ES2026.03 | 60.62 | |
| Llama 3.1 8B merge-EUBackbone=Llama 3.1 8B, Variant=merge-EU2026.03 | 60.61 | |
| Qwen3 8B merge-ESBackbone=Qwen3 8B, Variant=merge-ES2026.03 | 60.26 | |
| Llama 3.1 8B merge-GLBackbone=Llama 3.1 8B, Variant=merge-GL2026.03 | 59.96 | |
| Qwen3 8B merge-GLBackbone=Qwen3 8B, Variant=merge-GL2026.03 | 59.77 | |
| Qwen3 8B InstructBackbone=Qwen3 8B, Variant=Instruct2026.03 | 59.37 | |
| Llama 3.1 8B joint-EUBackbone=Llama 3.1 8B, Variant=joint-EU2026.03 | 57.81 | |
| Salamandra 7B InstructBackbone=Salamandra 7B, Variant=Instruct2026.03 | 56.55 | |
| Salamandra 2B InstructBackbone=Salamandra 2B, Variant=Instruct2026.03 | 43.18 |