Skip to main content
"""
Basic Accuracy Evaluation
=========================

Demonstrates synchronous and asynchronous accuracy evaluations.
"""

import asyncio
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

# ---------------------------------------------------------------------------
# Create Sync Evaluation
# ---------------------------------------------------------------------------
evaluation = AccuracyEval(
    name="Calculator Evaluation",
    model=OpenAIChat(id="o4-mini"),
    agent=Agent(
        model=OpenAIChat(id="gpt-4o"),
        tools=[CalculatorTools()],
    ),
    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.",
    num_iterations=1,
)

# ---------------------------------------------------------------------------
# Create Async Evaluation
# ---------------------------------------------------------------------------
async_evaluation = AccuracyEval(
    model=OpenAIChat(id="o4-mini"),
    agent=Agent(
        model=OpenAIChat(id="gpt-4o"),
        tools=[CalculatorTools()],
    ),
    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.",
    num_iterations=3,
)

# ---------------------------------------------------------------------------
# Run Evaluation
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    result: Optional[AccuracyResult] = evaluation.run(print_results=True)
    assert result is not None and result.avg_score >= 8

    async_result: Optional[AccuracyResult] = asyncio.run(
        async_evaluation.arun(print_results=True)
    )
    assert async_result is not None and async_result.avg_score >= 8

​
Run the Example

# Clone and setup repo
git clone https://github.com/agno-agi/agno.git
cd agno/cookbook/09_evals/accuracy

# Create and activate virtual environment
./scripts/demo_setup.sh
source .venvs/demo/bin/activate

python accuracy_basic.py