List your company

Instruction Following on AlpacaEval Indonesian

64.2Win RateCLO
48.70452.72756.7560.773May 20, 2025

Evaluation results

MethodLinks
CLOModel=Mistral-7B-v0.1, Eval Lang=Target2025.0564.213
CLOModel=Llama-2-7B, Eval Lang=English2025.0562.413.1
CLOModel=Mistral-7B-v0.1, Eval Lang=English2025.0562.410.1
CLOModel=Llama-2-13B, Eval Lang=Target2025.0561.79.3
CLOModel=Qwen-2.5-3B, Eval Lang=English2025.056110.2
CLOModel=Llama-2-13B, Eval Lang=English2025.0559.86.9
CLOModel=Llama-3-8B, Eval Lang=English2025.0557.76.1
CLOModel=Llama-3-8B, Eval Lang=Target2025.0556.41.5
CLOModel=Llama-2-7B, Eval Lang=Target2025.0555.85
SFT+DPOModel=Llama-3-8B, Eval Lang=Target2025.0554.9—
CLOModel=Qwen-2.5-3B, Eval Lang=Target2025.0554.91.1
SFT+DPOModel=Qwen-2.5-3B, Eval Lang=Target2025.0553.8—
SFT+DPOModel=Llama-2-13B, Eval Lang=English2025.0552.9—
SFT+DPOModel=Llama-2-13B, Eval Lang=Target2025.0552.4—
SFT+DPOModel=Mistral-7B-v0.1, Eval Lang=English2025.0552.3—
SFT+DPOModel=Llama-3-8B, Eval Lang=English2025.0551.6—
SFT+DPOModel=Mistral-7B-v0.1, Eval Lang=Target2025.0551.2—
SFT+DPOModel=Llama-2-7B, Eval Lang=Target2025.0550.8—
SFT+DPOModel=Qwen-2.5-3B, Eval Lang=English2025.0550.8—
SFT+DPOModel=Llama-2-7B, Eval Lang=English2025.0549.3—