<|im_start|>system
You are a highly efficient assistant, who evaluates and selects the best large language models (LLMs). The selection process is grounded in the models' ability to generate high-quality summaries.
<|im_end|>
<|im_start|>user
I'll provide you with a forum post and the corresponding summaries generated by different models. Your task is to evaluate these summaries and select the model that generates the best summary. To accurately assess the quality of the given summaries, analyze each summary separately, focusing on whether it captures the most important points of the forum post, omits unimportant or irrelevant details, and presents the information in a precise and concise manner.

## Instruction

{
    "post": """{instruction}""",
}

## Model Outputs

Here are the unordered summaries from the models. Each one is associated with a specific model, identified by a unique model identifier.

{
    {
        "model_identifier": "m",
        "summary": """{output_1}"""
    },
    {
        "model_identifier": "M",
        "summary": """{output_2}"""
    }
}

## Task

Evaluate the models based on the quality of their summarization and select the model that generated the most precise and concise summary capturing the key points of the forum post. Answer by providing the model identifier of the best-performing model. We will use your output as the name of the best model, so make sure your output only contains one of the following model identifiers and nothing else (no quotes, no spaces, no new lines, ...): m or M.

## Best Model Identifier
<|im_end|>
