# {py:mod}`feedback_forensics.tools.ff_model_comparison`

```{py:module} feedback_forensics.tools.ff_model_comparison
```

```{autodoc2-docstring} feedback_forensics.tools.ff_model_comparison
:allowtitles:
```

## Module Contents

### Functions

````{list-table}
:class: autosummary longtable
:align: left

* - {py:obj}`create_pairwise_datasets <feedback_forensics.tools.ff_model_comparison.create_pairwise_datasets>`
  - ```{autodoc2-docstring} feedback_forensics.tools.ff_model_comparison.create_pairwise_datasets
    :summary:
    ```
* - {py:obj}`compare_models <feedback_forensics.tools.ff_model_comparison.compare_models>`
  - ```{autodoc2-docstring} feedback_forensics.tools.ff_model_comparison.compare_models
    :summary:
    ```
* - {py:obj}`run <feedback_forensics.tools.ff_model_comparison.run>`
  - ```{autodoc2-docstring} feedback_forensics.tools.ff_model_comparison.run
    :summary:
    ```
````

### API

````{py:function} create_pairwise_datasets(model_names: list[str], reference_models: list[str], generations: dict[str, pandas.DataFrame], output_path: str = 'output/tmp/pairwise_datasets')
:canonical: feedback_forensics.tools.ff_model_comparison.create_pairwise_datasets

```{autodoc2-docstring} feedback_forensics.tools.ff_model_comparison.create_pairwise_datasets
```
````

````{py:function} compare_models(prompts: list[str], model_names: list[str], reference_models: list[str], output_path: str = 'output/')
:canonical: feedback_forensics.tools.ff_model_comparison.compare_models

```{autodoc2-docstring} feedback_forensics.tools.ff_model_comparison.compare_models
```
````

````{py:function} run()
:canonical: feedback_forensics.tools.ff_model_comparison.run

```{autodoc2-docstring} feedback_forensics.tools.ff_model_comparison.run
```
````