---
title: "init(judge:dimensions:scoringMode:)"
framework: evaluations
role: symbol
role_heading: Initializer
path: "evaluations/modeljudgeevaluator/init(judge:dimensions:scoringmode:)"
---

# init(judge:dimensions:scoringMode:)

Creates a multi-metric evaluator with default prompt configuration.

## Declaration

```swift
init(judge: any LanguageModel = SystemLanguageModel(), dimensions: [ScoreDimension], scoringMode: ScoringMode = .discrete)
```

```swift
init(judge: any LanguageModel, dimensions: [ScoreDimension], scoringMode: ScoringMode = .discrete)
```

## Parameters

- `judge`: The language model to use as judge. Defaults to SystemLanguageModel.default.
- `dimensions`: The dimensions to score. Each produces a separate DataFrame column.
- `scoringMode`: A value that indicates whether scores are discrete (default) or allow any floating-point value.

## See Also

### Creating a multi-dimension evaluator

- [init(judge:dimensions:scoringMode:prompt:)](evaluations/modeljudgeevaluator/init(judge:dimensions:scoringmode:prompt:).md)