此示例展示了一个更复杂的评估，用于比较 Agent 输出的完整正确性。

​
代码

from typing import Optional

from agno.agent import Agent
from agno.eval.accuracy import AccuracyEval, AccuracyResult
from agno.models.openai import OpenAIChat
from agno.tools.calculator import CalculatorTools

evaluation = AccuracyEval(
    model=OpenAIChat(id="o4-mini"),
    agent=Agent(
        model=OpenAIChat(id="gpt-4o"),
        tools=[CalculatorTools(enable_all=True)],
    ),
    input="What is 10*5 then to the power of 2? do it step by step",
    expected_output="2500",
    additional_guidelines="Agent output should include the steps and the final answer.",
)

result: Optional[AccuracyResult] = evaluation.run(print_results=True)
assert result is not None and result.avg_score >= 8