Create Evaluation

curl --request POST \
  --url https://api.nugen.in/api/v3/evaluations/create \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model_id": "model-xyz789",
  "benchmark_id": "benchmark-abc123",
  "custom_metrics": {},
  "model_id_2": "model-def456"
}
'

import requests

url = "https://api.nugen.in/api/v3/evaluations/create"

payload = {
    "model_id": "model-xyz789",
    "benchmark_id": "benchmark-abc123",
    "custom_metrics": {},
    "model_id_2": "model-def456"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model_id: 'model-xyz789',
    benchmark_id: 'benchmark-abc123',
    custom_metrics: {},
    model_id_2: 'model-def456'
  })
};

fetch('https://api.nugen.in/api/v3/evaluations/create', 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.nugen.in/api/v3/evaluations/create",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model_id' => 'model-xyz789',
    'benchmark_id' => 'benchmark-abc123',
    'custom_metrics' => [
        
    ],
    'model_id_2' => 'model-def456'
  ]),
  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.nugen.in/api/v3/evaluations/create"

	payload := strings.NewReader("{\n  \"model_id\": \"model-xyz789\",\n  \"benchmark_id\": \"benchmark-abc123\",\n  \"custom_metrics\": {},\n  \"model_id_2\": \"model-def456\"\n}")

	req, _ := http.NewRequest("POST", 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.post("https://api.nugen.in/api/v3/evaluations/create")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model_id\": \"model-xyz789\",\n  \"benchmark_id\": \"benchmark-abc123\",\n  \"custom_metrics\": {},\n  \"model_id_2\": \"model-def456\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.nugen.in/api/v3/evaluations/create")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model_id\": \"model-xyz789\",\n  \"benchmark_id\": \"benchmark-abc123\",\n  \"custom_metrics\": {},\n  \"model_id_2\": \"model-def456\"\n}"

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

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}

General

Create Evaluation

Create a new model evaluation using an existing benchmark.

This endpoint initiates a model evaluation task using a benchmark from your library. Supports both single model evaluation and comparison mode where two models are evaluated side-by-side.

Request Body:

model_id: Primary model to evaluate (required)
benchmark_id: ID of the benchmark to use for evaluation (required)
model_id_2 (optional): Second model ID for comparison mode
custom_metrics (optional): Custom evaluation metrics configuration

Returns:

evaluation_id: Unique identifier for tracking the evaluation
model_id: The primary model being evaluated
status: Initial status (always PROCESSING)
benchmark_id: The benchmark being used
created_at: Timestamp when evaluation was created
message: Confirmation message

Example Request (Single Model):

POST /api/v3/evaluations
Headers: {"Authorization": "Bearer <api_key>"}

{
  "model_id": "aligned-model-01kmqm4nrn9fw6r",
  "benchmark_id": "benchmark-abc123",
  "custom_metrics": ["accuracy", "relevance"]
}

Example Request (Comparison Mode):

POST /api/v3/evaluations
Headers: {"Authorization": "Bearer <api_key>"}

{
  "model_id": "qwen-v2p5-0p5b-instruct",
  "model_id_2": "aligned-model-01kmqm4nrn9fw6r",
  "benchmark_id": "benchmark-abc123"
}

Example Response:

{
  "evaluation_id": "eval-def456",
  "model_id": "aligned-model-01kmqm4nrn9fw6r",
  "status": "PROCESSING",
  "benchmark_id": "benchmark-abc123",
  "created_at": "2024-01-15T10:30:00Z",
  "message": "Evaluation created successfully and queued for execution"
}

Notes:

Single model mode: Evaluates one model against the benchmark
Comparison mode: Provide model_id_2 to compare two models side-by-side
Evaluation runs asynchronously - use the returned evaluation_id to check status
Use /evaluations/{evaluation_id}/status to track progress

POST

api

evaluations

create

Create Evaluation

curl --request POST \
  --url https://api.nugen.in/api/v3/evaluations/create \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model_id": "model-xyz789",
  "benchmark_id": "benchmark-abc123",
  "custom_metrics": {},
  "model_id_2": "model-def456"
}
'

import requests

url = "https://api.nugen.in/api/v3/evaluations/create"

payload = {
    "model_id": "model-xyz789",
    "benchmark_id": "benchmark-abc123",
    "custom_metrics": {},
    "model_id_2": "model-def456"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model_id: 'model-xyz789',
    benchmark_id: 'benchmark-abc123',
    custom_metrics: {},
    model_id_2: 'model-def456'
  })
};

fetch('https://api.nugen.in/api/v3/evaluations/create', 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.nugen.in/api/v3/evaluations/create",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model_id' => 'model-xyz789',
    'benchmark_id' => 'benchmark-abc123',
    'custom_metrics' => [
        
    ],
    'model_id_2' => 'model-def456'
  ]),
  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.nugen.in/api/v3/evaluations/create"

	payload := strings.NewReader("{\n  \"model_id\": \"model-xyz789\",\n  \"benchmark_id\": \"benchmark-abc123\",\n  \"custom_metrics\": {},\n  \"model_id_2\": \"model-def456\"\n}")

	req, _ := http.NewRequest("POST", 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.post("https://api.nugen.in/api/v3/evaluations/create")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model_id\": \"model-xyz789\",\n  \"benchmark_id\": \"benchmark-abc123\",\n  \"custom_metrics\": {},\n  \"model_id_2\": \"model-def456\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.nugen.in/api/v3/evaluations/create")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model_id\": \"model-xyz789\",\n  \"benchmark_id\": \"benchmark-abc123\",\n  \"custom_metrics\": {},\n  \"model_id_2\": \"model-def456\"\n}"

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

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}

Authorizations

Authorization

string

header

required

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

Body

application/json

model_id

string

required

ID of the model to evaluate

Example:

"model-xyz789"

benchmark_id

string

required

ID of existing benchmark from BenchmarkTask table

Example:

"benchmark-abc123"

custom_metrics

Custom Metrics · object | null

Custom metrics configuration

model_id_2

string | null

ID of second model for comparison mode (eval-compare)

Example:

"model-def456"

Response

Successful Response

Models

Documents

Benchmark

Evaluations

Inference

General

Create Evaluation

Authorizations

Body

Response