---
title: "pairwise(judge:dimensions:scoringMode:evaluationTarget:)"
framework: evaluations
role: symbol
role_heading: Type Method
path: "evaluations/modeljudgeevaluator/pairwise(judge:dimensions:scoringmode:evaluationtarget:)"
---

# pairwise(judge:dimensions:scoringMode:evaluationTarget:)

Creates a multi-metric pairwise comparison evaluator.

## Declaration

```swift
static func pairwise(judge: any LanguageModel, dimensions: [ScoreDimension], scoringMode: ScoringMode = .discrete, evaluationTarget: (@Sendable (Input.ExpectedValue) -> String)? = nil) -> ModelJudgeEvaluator<Input>
```

## Parameters

- `judge`: The language model to use as judge.
- `dimensions`: The dimensions to score for the comparison.
- `scoringMode`: A value that indicates whether scores are discrete (default) or allow any floating-point value.
- `evaluationTarget`: An optional closure that converts the value to a string. Both responses use this target.

## See Also

### Creating a pairwise evaluator

- [pairwise(_:scale:judge:scoringMode:evaluationTarget:)](evaluations/modeljudgeevaluator/pairwise(_:scale:judge:scoringmode:evaluationtarget:).md)