---
title: "Create evaluation"
method: POST
path: "/openai/evals"
tags: ["Evals"]
---

# Create evaluation

`POST /openai/evals`

Create the structure of an evaluation that can be used to test a model's performance.
An evaluation is a set of testing criteria and the config for a data source, which dictates the schema of the data used in the evaluation. After creating an evaluation, you can run it on different models and model parameters. We support several types of graders and datasources.
For more information, see the [Evals guide](https://platform.openai.com/docs/guides/evals).

## Query parameters

- `api-version` string, required

## Request body

- CreateEvalRequest
  - `name` string — The name of the evaluation.
  - `metadata` OpenAIMetadata — Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
  - `data_source_config` unknown, required
  - `testing_criteria` unknown[], required — A list of graders for all eval runs in this group. Graders can reference variables in the data source using double curly braces notation, like `{{item.variable_name}}`. To reference the model's output, use the `sample` namespace (ie, `{{sample.output_text}}`).
    - unknown
  - `properties` object — Set of immutable 16 key-value pairs that can be attached to an object for storing additional information. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

## Response `200`

The request has succeeded.

- Eval — An Eval object with a data source config and testing criteria. An Eval represents a task to be done for your LLM integration. Like: - Improve the quality of my chatbot - See how well my chatbot handles customer support - Check if o4-mini is better at my usecase than gpt-4o
  - `object` 'eval', required — The object type.
  - `id` string, required — Unique identifier for the evaluation.
  - `name` string, required — The name of the evaluation.
  - `data_source_config` unknown, required
  - `testing_criteria` unknown[], required — A list of testing criteria.
    - unknown
  - `created_at` integer, required — The Unix timestamp (in seconds) for when the eval was created.
  - `metadata` OpenAIMetadata, required — Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
  - `modified_at` integer
  - `created_by` string — the name of the person who created the run.
  - `properties` object — Set of immutable 16 key-value pairs that can be attached to an object for storing additional information. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

## Other responses

- `default` — An unexpected error response.

---

[API](https://skmtc.net/azure/apis/ai-azure-ai-projects.md) · [All operations](https://skmtc.net/azure/apis/ai-azure-ai-projects/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/azure/ai-azure-ai-projects/versions/b52c14a89ea1/schema)