<|im_start|>system
You are a helpful assistant who reviews a debate between two other assistants in evaluating the quality of the outputs for a given instruction.
<|im_end|>
<|im_start|>user
The two assistants, Assistant (a) and Assistant (b), are given an instruction, Output (a) and Output (b). They are asked to select the Output (a) or Output (b) that is better for the given instruction. Output (a) and Output (b) are generated by two different AI chatbots respectively.
Assistant (a) and Assistant (b) have conflicting evaluations. Your goal is to review their evaluations and give your final decision on which output is better.

Here are some rules of the evaluation:
(1) You should prioritize evaluating whether the output honestly/precisely/closely executes the instruction, then consider its helpfulness, accuracy, level of detail, harmlessness, etc.
(2) Outputs should NOT contain more/less than what the instruction asks for, as such outputs do NOT precisely execute the instruction.
(3) You should avoid any potential bias and your judgment should be as objective as possible. For example, the order in which the outputs were presented should NOT affect your judgment, as Output (a) and Output (b) are **equally likely** to be the better.

Now carefully review the instruction, Output (a), Output (b), and the debate between Assistant (a) and Assistant (b). Select the Output (a) or Output (b) that is better for the given instruction.

You should first provide a brief explanation of your evaluation, and then always end your response with either "Therefore, Output (a) is better." or "Therefore, Output (b) is better." verbatim.
Do NOT say both / neither are good.
Do NOT output any other words.
Do NOT say "Output (a) is better" or "Output (b) is better" at the beginning. You should do reasoning and thinking **before** claiming which is better.

# Instruction:
{input}

# Output (a):
{output_1}

# Output (b):
{output_2}

# Debate between Assistant (a) and Assistant (b)
## Evaluation given by Assistant (a), who thinks Output (a) is better:
{explanation_1}
## Evaluation given by Assistant (b), who thinks Output (b) is better:
{explanation_2}

# Decision (Give a brief explanation of your evaluation followed by either "Therefore, Output (a) is better." or "Therefore, Output (b) is better." verbatim. Always claim which is better at the end. In your explanation, you should always use "Output (a)" or "Output (b)" to refer to the two outputs respectively.):
<|im_end|>