## Overview

The `MultimodalFaithfulnessEvaluator` assesses whether an agent response is grounded in the image content, detecting hallucinations such as invented details, unsupported assumptions, external knowledge, and speculation.

## Key Features

-   **Output-Level Evaluation**: Scores a single agent response per case
-   **Binary Scoring**: `1.0` if fully grounded, `0.0` if any hallucination is found
-   **Automatic Reference Comparison**: Appends a reference suffix to the rubric when `expected_output` is provided on the case
-   **Hallucination Detection**: Designed to catch invented details, unsupported assumptions, and speculation

## When to Use

Use the `MultimodalFaithfulnessEvaluator` when you need to:

-   Detect hallucinations in image captions or VQA answers
-   Verify that a response only states what is verifiable from the image
-   Screen for inferred-but-unseen details (emotions, off-screen events, brand names, locations)
-   Complement correctness checks with a groundedness check

## Evaluation Level

This evaluator operates at the **OUTPUT\_LEVEL**, scoring a single agent response per case.

## Parameters

### `rubric` (optional)

-   **Type**: `str | None`
-   **Default**: `FAITHFULNESS_RUBRIC_V0`
-   **Description**: Custom rubric. Leave unset to use the default rubric.

### `model` (optional)

-   **Type**: `Model | str | None`
-   **Default**: `None` (uses default Bedrock model)
-   **Description**: Multimodal judge model.

### `include_inputs` (optional)

-   **Type**: `bool`
-   **Default**: `True`

### `system_prompt` (optional)

-   **Type**: `str | None`
-   **Default**: `None` (uses the built-in `MLLM_JUDGE_SYSTEM_PROMPT`)

### `reference_suffix` (optional)

-   **Type**: `str | None`
-   **Default**: `None` (uses the built-in default suffix)

## Scoring System

| Score | Label | Meaning |
| --- | --- | --- |
| 1.0 | Faithful | Response only contains information verifiable from the image |
| 0.0 | Unfaithful | Response contains one or more hallucinations |

A response passes only if the score is `1.0`.

## Basic Usage

```python
import asyncio

from strands_evals import Case, Experiment
from strands_evals.evaluators import MultimodalFaithfulnessEvaluator
from strands_evals.types import MultimodalInput
from strands_evals.types.evaluation_report import EvaluationReport


def task_function(case: Case) -> str:
    # Replace with your multimodal agent invocation.
    return "A family is having a picnic in Central Park."


cases = [
    Case(
        name="park-scene",
        input=MultimodalInput(
            media="/path/to/picnic.jpg",
            instruction="Describe what is happening in the image.",
        ),
    ),
]

experiment = Experiment(cases=cases, evaluators=[MultimodalFaithfulnessEvaluator()])

async def main():
    report = await experiment.run_evaluations_async(task_function)
    report.run_display()

asyncio.run(main())
```

## Combining with Other Evaluators

Pair with correctness to distinguish “wrong” from “ungrounded”. `Experiment.run_evaluations` returns one combined report across all evaluators — each row in `report.cases` carries an `evaluator` key naming the producing evaluator:

```python
from strands_evals import Experiment
from strands_evals.evaluators import (
    MultimodalCorrectnessEvaluator,
    MultimodalFaithfulnessEvaluator,
)
from strands_evals.types.evaluation_report import EvaluationReport

evaluators = [
    MultimodalCorrectnessEvaluator(),   # Are the claims factually right?
    MultimodalFaithfulnessEvaluator(),  # Are they supported by the image?
]

experiment = Experiment(cases=cases, evaluators=evaluators)

async def main():
    report = await experiment.run_evaluations_async(task_function)
    report.run_display()

asyncio.run(main())
```

## Related Evaluators

-   [**MultimodalOutputEvaluator**](/pr-cms-3708/docs/user-guide/evals-sdk/evaluators/multimodal_output_evaluator/index.md): Parent class with full parameter reference
-   [**MultimodalCorrectnessEvaluator**](/pr-cms-3708/docs/user-guide/evals-sdk/evaluators/multimodal_correctness_evaluator/index.md): Strict factual correctness
-   [**FaithfulnessEvaluator**](/pr-cms-3708/docs/user-guide/evals-sdk/evaluators/faithfulness_evaluator/index.md): Text-only counterpart grounded in conversation history

## Related pages

- [Multimodal Correctness Evaluator](/pr-cms-3708/docs/user-guide/evals-sdk/evaluators/multimodal_correctness_evaluator/index.md) (2 shared tags)
- [Multimodal Instruction Following Evaluator](/pr-cms-3708/docs/user-guide/evals-sdk/evaluators/multimodal_instruction_following_evaluator/index.md) (2 shared tags)
- [Multimodal Output Evaluator](/pr-cms-3708/docs/user-guide/evals-sdk/evaluators/multimodal_output_evaluator/index.md) (2 shared tags)
- [Multimodal Overall Quality Evaluator](/pr-cms-3708/docs/user-guide/evals-sdk/evaluators/multimodal_overall_quality_evaluator/index.md) (2 shared tags)
- [Google](/pr-cms-3708/docs/user-guide/concepts/model-providers/google/index.md) (1 shared tag)
- [Vercel](/pr-cms-3708/docs/user-guide/concepts/model-providers/vercel/index.md) (1 shared tag)
- [OpenAI](/pr-cms-3708/docs/user-guide/concepts/model-providers/openai/index.md) (1 shared tag)
- [Writer](/pr-cms-3708/docs/user-guide/concepts/model-providers/writer/index.md) (1 shared tag)
- [Amazon Nova](/pr-cms-3708/docs/user-guide/concepts/model-providers/amazon-nova/index.md) (1 shared tag)
- [Amazon Bedrock](/pr-cms-3708/docs/user-guide/concepts/model-providers/amazon-bedrock/index.md) (1 shared tag)