Update Evaluation Run

Update the name or other properties of an existing evaluation run.

PATCH /eval-runs/{eval_run_id}

Update Evaluation Run

cURL

curl --request PATCH \
  --url https://api.example.com/eval-runs/{eval_run_id} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>"
}
'

import requests

url = "https://api.example.com/eval-runs/{eval_run_id}"

payload = { "name": "<string>" }
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.patch(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'PATCH',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({name: '<string>'})
};

fetch('https://api.example.com/eval-runs/{eval_run_id}', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.example.com/eval-runs/{eval_run_id}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "PATCH",
  CURLOPT_POSTFIELDS => json_encode([
    'name' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.example.com/eval-runs/{eval_run_id}"

	payload := strings.NewReader("{\n  \"name\": \"<string>\"\n}")

	req, _ := http.NewRequest("PATCH", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.patch("https://api.example.com/eval-runs/{eval_run_id}")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/eval-runs/{eval_run_id}")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Patch.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"name\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body

200

{
  "id": "a03fa2f4-900d-482d-afe0-470d4cd8d1f4",
  "agent_id": "basic-agent",
  "model_id": "gpt-4o",
  "model_provider": "OpenAI",
  "name": "Test ",
  "eval_type": "reliability",
  "eval_data": {
    "eval_status": "PASSED",
    "failed_tool_calls": [],
    "passed_tool_calls": [
      "multiply"
    ]
  },
  "eval_input": {
    "expected_tool_calls": [
      "multiply"
    ]
  },
  "created_at": "2025-08-27T15:41:59Z",
  "updated_at": "2025-08-27T15:41:59Z"
}

{
  "detail": "Bad request",
  "error_code": "BAD_REQUEST"
}

{
  "detail": "Unauthenticated access",
  "error_code": "UNAUTHENTICATED"
}

{
  "detail": "Not found",
  "error_code": "NOT_FOUND"
}

{
  "detail": "Validation error",
  "error_code": "VALIDATION_ERROR"
}

{
  "detail": "Internal server error",
  "error_code": "INTERNAL_SERVER_ERROR"
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

eval_run_id · string · required

Query Parameters

db_id · string | null

The ID of the database to use

table · string | null

Table to use for rename operation

Body

application/json

name · string · required

New name for the evaluation run

Required string length: 1 - 255

Response

200

application/json

Evaluation run updated successfully

id · string · required

Unique identifier for the evaluation run

eval_type · enum<string> · required

Type of evaluation (accuracy, performance, or reliability)

Available options: accuracy, agent_as_judge, performance, reliability

eval_data · Eval Data · object · required

Evaluation results and metrics

agent_id · string | null

Agent ID that was evaluated

model_id · string | null

Model ID used in evaluation

model_provider · string | null

Model provider name

team_id · string | null

Team ID that was evaluated

workflow_id · string | null

Workflow ID that was evaluated

name · string | null

Name of the evaluation run

evaluated_component_name · string | null

Name of the evaluated component

eval_input · Eval Input · object | null

Input parameters used for the evaluation

created_at · string<date-time> | null

Timestamp when evaluation was created

updated_at · string<date-time> | null

Timestamp when evaluation was last updated