Skip to content
For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to the page URL.
Primary navigation

Get eval runs

RunListPage evals().runs().list(RunListParamsparams = RunListParams.none(), RequestOptionsrequestOptions = RequestOptions.none())
GET/evals/{eval_id}/runs

Get a list of runs for an evaluation.

ParametersExpand Collapse
RunListParams params
Optional<String> evalId
Optional<String> after

Identifier for the last run from the previous pagination request.

Optional<Long> limit

Number of runs to retrieve.

Optional<Order> order

Sort order for runs by timestamp. Use asc for ascending order or desc for descending order. Defaults to asc.

Optional<Status> status

Filter runs by status. One of queued | in_progress | failed | completed | canceled.

ReturnsExpand Collapse
class RunListResponse:

A schema representing an evaluation run.

String id

Unique identifier for the evaluation run.

long createdAt

Unix timestamp (in seconds) when the evaluation run was created.

formatunixtime
DataSource dataSource

Information about the run’s data source.

An object representing an error response from the Eval API.

String evalId

The identifier of the associated evaluation.

Optional<Metadata> metadata

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.

String model

The model that is evaluated, if applicable.

String name

The name of the evaluation run.

JsonValue; object_ "eval.run"constant"eval.run"constant

The type of the object. Always “eval.run”.

List<PerModelUsage> perModelUsage

Usage statistics for each model during the evaluation run.

List<PerTestingCriteriaResult> perTestingCriteriaResults

Results per testing criteria applied during the evaluation run.

String reportUrl

The URL to the rendered evaluation run report on the UI dashboard.

formaturi
ResultCounts resultCounts

Counters summarizing the outcomes of the evaluation run.

String status

The status of the evaluation run.

Get eval runs

package com.openai.example;

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.evals.runs.RunListPage;
import com.openai.models.evals.runs.RunListParams;

public final class Main {
    private Main() {}

    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.fromEnv();

        RunListPage page = client.evals().runs().list("eval_id");
    }
}
{
  "object": "list",
  "data": [
    {
      "object": "eval.run",
      "id": "evalrun_67e0c7d31560819090d60c0780591042",
      "eval_id": "eval_67e0c726d560819083f19a957c4c640b",
      "report_url": "https://platform.openai.com/evaluations/eval_67e0c726d560819083f19a957c4c640b",
      "status": "completed",
      "model": "o3-mini",
      "name": "bulk_with_negative_examples_o3-mini",
      "created_at": 1742784467,
      "result_counts": {
        "total": 1,
        "errored": 0,
        "failed": 0,
        "passed": 1
      },
      "per_model_usage": [
        {
          "model_name": "o3-mini",
          "invocation_count": 1,
          "prompt_tokens": 563,
          "completion_tokens": 874,
          "total_tokens": 1437,
          "cached_tokens": 0
        }
      ],
      "per_testing_criteria_results": [
        {
          "testing_criteria": "Push Notification Summary Grader-1808cd0b-eeec-4e0b-a519-337e79f4f5d1",
          "passed": 1,
          "failed": 0
        }
      ],
      "data_source": {
        "type": "completions",
        "source": {
          "type": "file_content",
          "content": [
            {
              "item": {
                "notifications": "\n- New message from Sarah: \"Can you call me later?\"\n- Your package has been delivered!\n- Flash sale: 20% off electronics for the next 2 hours!\n"
              }
            }
          ]
        },
        "input_messages": {
          "type": "template",
          "template": [
            {
              "type": "message",
              "role": "developer",
              "content": {
                "type": "input_text",
                "text": "\n\n\n\nYou are a helpful assistant that takes in an array of push notifications and returns a collapsed summary of them.\nThe push notification will be provided as follows:\n<push_notifications>\n...notificationlist...\n</push_notifications>\n\nYou should return just the summary and nothing else.\n\n\nYou should return a summary that is concise and snappy.\n\n\nHere is an example of a good summary:\n<push_notifications>\n- Traffic alert: Accident reported on Main Street.- Package out for delivery: Expected by 5 PM.- New friend suggestion: Connect with Emma.\n</push_notifications>\n<summary>\nTraffic alert, package expected by 5pm, suggestion for new friend (Emily).\n</summary>\n\n\nHere is an example of a bad summary:\n<push_notifications>\n- Traffic alert: Accident reported on Main Street.- Package out for delivery: Expected by 5 PM.- New friend suggestion: Connect with Emma.\n</push_notifications>\n<summary>\nTraffic alert reported on main street. You have a package that will arrive by 5pm, Emily is a new friend suggested for you.\n</summary>\n"
              }
            },
            {
              "type": "message",
              "role": "user",
              "content": {
                "type": "input_text",
                "text": "<push_notifications>{{item.notifications}}</push_notifications>"
              }
            }
          ]
        },
        "model": "o3-mini",
        "sampling_params": null
      },
      "error": null,
      "metadata": {}
    }
  ],
  "first_id": "evalrun_67e0c7d31560819090d60c0780591042",
  "last_id": "evalrun_67e0c7d31560819090d60c0780591042",
  "has_more": true
}
Returns Examples
{
  "object": "list",
  "data": [
    {
      "object": "eval.run",
      "id": "evalrun_67e0c7d31560819090d60c0780591042",
      "eval_id": "eval_67e0c726d560819083f19a957c4c640b",
      "report_url": "https://platform.openai.com/evaluations/eval_67e0c726d560819083f19a957c4c640b",
      "status": "completed",
      "model": "o3-mini",
      "name": "bulk_with_negative_examples_o3-mini",
      "created_at": 1742784467,
      "result_counts": {
        "total": 1,
        "errored": 0,
        "failed": 0,
        "passed": 1
      },
      "per_model_usage": [
        {
          "model_name": "o3-mini",
          "invocation_count": 1,
          "prompt_tokens": 563,
          "completion_tokens": 874,
          "total_tokens": 1437,
          "cached_tokens": 0
        }
      ],
      "per_testing_criteria_results": [
        {
          "testing_criteria": "Push Notification Summary Grader-1808cd0b-eeec-4e0b-a519-337e79f4f5d1",
          "passed": 1,
          "failed": 0
        }
      ],
      "data_source": {
        "type": "completions",
        "source": {
          "type": "file_content",
          "content": [
            {
              "item": {
                "notifications": "\n- New message from Sarah: \"Can you call me later?\"\n- Your package has been delivered!\n- Flash sale: 20% off electronics for the next 2 hours!\n"
              }
            }
          ]
        },
        "input_messages": {
          "type": "template",
          "template": [
            {
              "type": "message",
              "role": "developer",
              "content": {
                "type": "input_text",
                "text": "\n\n\n\nYou are a helpful assistant that takes in an array of push notifications and returns a collapsed summary of them.\nThe push notification will be provided as follows:\n<push_notifications>\n...notificationlist...\n</push_notifications>\n\nYou should return just the summary and nothing else.\n\n\nYou should return a summary that is concise and snappy.\n\n\nHere is an example of a good summary:\n<push_notifications>\n- Traffic alert: Accident reported on Main Street.- Package out for delivery: Expected by 5 PM.- New friend suggestion: Connect with Emma.\n</push_notifications>\n<summary>\nTraffic alert, package expected by 5pm, suggestion for new friend (Emily).\n</summary>\n\n\nHere is an example of a bad summary:\n<push_notifications>\n- Traffic alert: Accident reported on Main Street.- Package out for delivery: Expected by 5 PM.- New friend suggestion: Connect with Emma.\n</push_notifications>\n<summary>\nTraffic alert reported on main street. You have a package that will arrive by 5pm, Emily is a new friend suggested for you.\n</summary>\n"
              }
            },
            {
              "type": "message",
              "role": "user",
              "content": {
                "type": "input_text",
                "text": "<push_notifications>{{item.notifications}}</push_notifications>"
              }
            }
          ]
        },
        "model": "o3-mini",
        "sampling_params": null
      },
      "error": null,
      "metadata": {}
    }
  ],
  "first_id": "evalrun_67e0c7d31560819090d60c0780591042",
  "last_id": "evalrun_67e0c7d31560819090d60c0780591042",
  "has_more": true
}