---
title: "Execute answer-correctness evaluator"
method: POST
path: "/v2/evaluators/answer-correctness/execute"
tags: ["evaluators"]
---

# Execute answer-correctness evaluator

`POST /v2/evaluators/answer-correctness/execute`

Evaluate factual accuracy by comparing answers against ground truth

**Request Body:**
- `input.question` (string, required): The original question
- `input.completion` (string, required): The completion to evaluate
- `input.ground_truth` (string, required): The expected correct answer

## Request body

- RequestAnswerCorrectnessRequest
  - `input` RequestAnswerCorrectnessInput, required
    - `completion` string, required
    - `ground_truth` string, required
    - `question` string, required

## Response `200`

OK

- ResponseAnswerCorrectnessResponse
  - `correctness_score` number

## Other responses

- `400` — Bad Request
- `500` — Internal Server Error

## Changes

> 11 revisions in range; 1 could not be searched.

- **2026-04-12** `bd3e46b75d87` — 1 info
  - endpoint added
- **2026-01-01** `aef6c851927f` — 1 breaking
  - api path removed without deprecation

[Change history](https://skmtc.dev/traceloop/apis/traceloop-api/changes/v2/evaluators/answer-correctness/execute/post.md)

---

[API](https://skmtc.dev/traceloop/apis/traceloop-api.md) · [All operations](https://skmtc.dev/traceloop/apis/traceloop-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/traceloop/traceloop-api/revisions/9c12a04a5947/schema)