axiom/dist/docs/scorers/aggregations/functions/PassAtK.md

Axiom AI SDK provides - an API to wrap your AI calls with observability instrumentation. - offline evals - online evals

[**axiom v0.51.1**](../../../README.md)

***

[axiom](../../../README.md) / [scorers/aggregations](../README.md) / PassAtK

# Function: PassAtK()

> **PassAtK**(`opts?`): [`Aggregation`](../type-aliases/Aggregation.md)\<`"pass@k"`\>

Returns 1 if at least one trial score meets or exceeds the threshold, 0 otherwise.
Also known as "pass@k" in evaluation literature.

## Parameters

### opts?

#### threshold?

`number`

The minimum score required for a trial to pass

## Returns

[`Aggregation`](../type-aliases/Aggregation.md)\<`"pass@k"`\>

## Example

```typescript
Scorer('tool-called', fn, { aggregation: PassAtK({ threshold: 0.8 }) })
// scores [0.5, 0.9, 0.6] => 1 (0.9 >= 0.8)
// scores [0.5, 0.6, 0.7] => 0 (none >= 0.8)
```