Skip to main content
"""
Tool-Enabled Accuracy Evaluation
================================

Demonstrates accuracy evaluation for an agent using calculator tools.
"""

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 Evaluation
# ---------------------------------------------------------------------------
evaluation = AccuracyEval(
    name="Tools Evaluation",
    model=OpenAIChat(id="o4-mini"),
    agent=Agent(
        model=OpenAIChat(id="gpt-5.2"),
        tools=[CalculatorTools()],
    ),
    input="What is 10!?",
    expected_output="3628800",
)

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