> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Async Function Performance Evaluation

> Benchmark an async agent.arun call over 10 iterations with PerformanceEval.arun, printing runtime and memory results.

Demonstrates performance evaluation for an asynchronous function.

```python async_function.py theme={null}
"""
Async Function Performance Evaluation
=====================================

Demonstrates performance evaluation for an asynchronous function.
"""

import asyncio

from agno.agent import Agent
from agno.eval.performance import PerformanceEval
from agno.models.openai import OpenAIChat


# ---------------------------------------------------------------------------
# Create Benchmark Function
# ---------------------------------------------------------------------------
async def arun_agent():
    agent = Agent(
        model=OpenAIChat(id="gpt-5.2"),
        system_message="Be concise, reply with one sentence.",
    )
    response = await agent.arun("What is the capital of France?")
    return response


# ---------------------------------------------------------------------------
# Create Evaluation
# ---------------------------------------------------------------------------
performance_eval = PerformanceEval(func=arun_agent, num_iterations=10)

# ---------------------------------------------------------------------------
# Run Evaluation
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    asyncio.run(performance_eval.arun(print_summary=True, print_results=True))
```

## Run the Example

<Snippet file="create-venv-step.mdx" />

**1. Install dependencies**

```bash theme={null}
uv pip install -U agno memory-profiler openai
```

**2. Export your OpenAI API key**

```bash Mac/Linux theme={null}
export OPENAI_API_KEY="your_openai_api_key_here"
```

```bash Windows theme={null}
$Env:OPENAI_API_KEY="your_openai_api_key_here"
```

**3. Run the example**

Save the code above as `async_function.py`, then run:

```bash theme={null}
python async_function.py
```

Full source: [cookbook/09\_evals/performance/async\_function.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/09_evals/performance/async_function.py)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.