> ## 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.

# 9.11 or 9.9

> Groq reasoning model works through the classic 9.11 vs 9.9 comparison.

Demonstrates Groq with a reasoning model for numeric comparison.

```python 11_or_9_9.py theme={null}
"""
9.11 vs 9.9 Comparison
======================

Demonstrates Groq with a reasoning model for numeric comparison.
"""

from agno.agent import Agent
from agno.models.deepseek import DeepSeek
from agno.models.groq import Groq

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
    model=Groq(
        id="qwen/qwen3.6-27b",
        temperature=0.6,
        max_tokens=1024,
        top_p=0.95,
    ),
    reasoning_model=DeepSeek(id="deepseek-reasoner"),
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent.print_response(
        "9.11 and 9.9 -- which is bigger?",
        stream=True,
        show_full_reasoning=True,
    )
```

## Run the Example

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

**1. Install dependencies**

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

**2. Export your API keys**

```bash Mac/Linux theme={null}
export DEEPSEEK_API_KEY="your_deepseek_api_key_here"
export GROQ_API_KEY="your_groq_api_key_here"
```

```bash Windows theme={null}
$Env:DEEPSEEK_API_KEY="your_deepseek_api_key_here"
$Env:GROQ_API_KEY="your_groq_api_key_here"
```

**3. Run the example**

Save the code above as `11_or_9_9.py`, then run:

```bash theme={null}
python 11_or_9_9.py
```

Full source: [cookbook/10\_reasoning/models/groq/9\_11\_or\_9\_9.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/10_reasoning/models/groq/9_11_or_9_9.py)


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