Get eval runs

GEThttps:/api.openai.com/v1/evals/{eval_id}/runs

Get a list of runs for an evaluation.

Path parameters

  • eval_id
    string
    Required
    The ID of the evaluation to retrieve runs for.

Query parameters

  • after
    string
    Identifier for the last run from the previous pagination request.
  • limit
    integer
    Defaults: 20
    Number of runs to retrieve.
  • order
    string
    Defaults: asc

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

  • status
    string

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

Response

A list of EvalRun objects matching the specified ID.

Example request
1
curl https://api.openai.com/v1/evals/egroup_67abd54d9b0081909a86353f6fb9317a/runs \
2
-H "Authorization: Bearer $OPENAI_API_KEY" \
3
-H "Content-Type: application/json"
Example response
1
{
2
"object": "list",
3
"data": [
4
{
5
"object": "eval.run",
6
"id": "evalrun_67e0c7d31560819090d60c0780591042",
7
"eval_id": "eval_67e0c726d560819083f19a957c4c640b",
8
"report_url": "https://platform.openai.com/evaluations/eval_67e0c726d560819083f19a957c4c640b",
9
"status": "completed",
10
"model": "o3-mini",
11
"name": "bulk_with_negative_examples_o3-mini",
12
"created_at": 1742784467,
13
"result_counts": {
14
"total": 1,
15
"errored": 0,
16
"failed": 0,
17
"passed": 1
18
},
19
"per_model_usage": [
20
{
21
"model_name": "o3-mini",
22
"invocation_count": 1,
23
"prompt_tokens": 563,
24
"completion_tokens": 874,
25
"total_tokens": 1437,
26
"cached_tokens": 0
27
}
28
],
29
"per_testing_criteria_results": [
30
{
31
"testing_criteria": "Push Notification Summary Grader-1808cd0b-eeec-4e0b-a519-337e79f4f5d1",
32
"passed": 1,
33
"failed": 0
34
}
35
],
36
"data_source": {
37
"type": "completions",
38
"source": {
39
"type": "file_content",
40
"content": [
41
{
42
"item": {
43
"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"
44
}
45
}
46
]
47
},
48
"input_messages": {
49
"type": "template",
50
"template": [
51
{
52
"type": "message",
53
"role": "developer",
54
"content": {
55
"type": "input_text",
56
"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"
57
}
58
},
59
{
60
"type": "message",
61
"role": "user",
62
"content": {
63
"type": "input_text",
64
"text": "<push_notifications>{{item.notifications}}</push_notifications>"
65
}
66
}
67
]
68
},
69
"model": "o3-mini",
70
"sampling_params": null
71
},
72
"error": null,
73
"metadata": {}
74
}
75
],
76
"first_id": "evalrun_67e0c7d31560819090d60c0780591042",
77
"last_id": "evalrun_67e0c7d31560819090d60c0780591042",
78
"has_more": true
79
}
Built with