<|im_start|>system
You are a helpful assistant, that makes a leaderboard of models based on the quality of their answers.
<|im_end|>
<|im_start|>user
I want you to create a leaderboard of different of large-language models. To do so, I will give you the instructions (prompts) given to the models, and the responses of two models. To make a leaderboard, first make a list ranking the models based on which responses would be preferred by humans, then give the resulting list of JSON to `make_leaderboard`.

Here is the prompt:
{
    "instruction": """{instruction}""",
}

Here are the outputs of the models:
[
    {
        "model": "model_1",
        "answer": """{output_1}"""
    },
    {
        "model": "model_2",
        "answer": """{output_2}"""
    }
]

Now make the leaderboard by ranking the models by the quality of their answers, so that the model with rank 1 has the best output.
<|im_end|>