Instruction Following on AlpacaEval Indonesian
64.2Win RateCLO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CLOModel=Mistral-7B-v0.1, Eval Lang=Target2025.05 | 64.2 | 13 | |
| CLOModel=Llama-2-7B, Eval Lang=English2025.05 | 62.4 | 13.1 | |
| CLOModel=Mistral-7B-v0.1, Eval Lang=English2025.05 | 62.4 | 10.1 | |
| CLOModel=Llama-2-13B, Eval Lang=Target2025.05 | 61.7 | 9.3 | |
| CLOModel=Qwen-2.5-3B, Eval Lang=English2025.05 | 61 | 10.2 | |
| CLOModel=Llama-2-13B, Eval Lang=English2025.05 | 59.8 | 6.9 | |
| CLOModel=Llama-3-8B, Eval Lang=English2025.05 | 57.7 | 6.1 | |
| CLOModel=Llama-3-8B, Eval Lang=Target2025.05 | 56.4 | 1.5 | |
| CLOModel=Llama-2-7B, Eval Lang=Target2025.05 | 55.8 | 5 | |
| SFT+DPOModel=Llama-3-8B, Eval Lang=Target2025.05 | 54.9 | — | |
| CLOModel=Qwen-2.5-3B, Eval Lang=Target2025.05 | 54.9 | 1.1 | |
| SFT+DPOModel=Qwen-2.5-3B, Eval Lang=Target2025.05 | 53.8 | — | |
| SFT+DPOModel=Llama-2-13B, Eval Lang=English2025.05 | 52.9 | — | |
| SFT+DPOModel=Llama-2-13B, Eval Lang=Target2025.05 | 52.4 | — | |
| SFT+DPOModel=Mistral-7B-v0.1, Eval Lang=English2025.05 | 52.3 | — | |
| SFT+DPOModel=Llama-3-8B, Eval Lang=English2025.05 | 51.6 | — | |
| SFT+DPOModel=Mistral-7B-v0.1, Eval Lang=Target2025.05 | 51.2 | — | |
| SFT+DPOModel=Llama-2-7B, Eval Lang=Target2025.05 | 50.8 | — | |
| SFT+DPOModel=Qwen-2.5-3B, Eval Lang=English2025.05 | 50.8 | — | |
| SFT+DPOModel=Llama-2-7B, Eval Lang=English2025.05 | 49.3 | — |