curl --request POST \
  --url https://distillation.training.wandb.ai/v1/evals \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "dataset_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "spec": {
    "type": "h2h_judge",
    "judge_model_ref": "<string>",
    "judge_prompt": "You are an intelligent and fair judge of chatbots. Evaluate the following two responses and choose which one is better. If the outputs are of similar quality, you can mark them as a tie.",
    "reference_conversation_count": 0
  },
  "participants": [
    {
      "kind": "original"
    }
  ],
  "sample_size": 123,
  "reference": {
    "kind": "original"
  }
}
'

import requests

url = "https://distillation.training.wandb.ai/v1/evals"

payload = {
    "name": "<string>",
    "dataset_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "spec": {
        "type": "h2h_judge",
        "judge_model_ref": "<string>",
        "judge_prompt": "You are an intelligent and fair judge of chatbots. Evaluate the following two responses and choose which one is better. If the outputs are of similar quality, you can mark them as a tie.",
        "reference_conversation_count": 0
    },
    "participants": [{ "kind": "original" }],
    "sample_size": 123,
    "reference": { "kind": "original" }
}
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({
    name: '<string>',
    dataset_id: '3c90c3cc-0d44-4b50-8888-8dd25736052a',
    spec: {
      type: 'h2h_judge',
      judge_model_ref: '<string>',
      judge_prompt: 'You are an intelligent and fair judge of chatbots. Evaluate the following two responses and choose which one is better. If the outputs are of similar quality, you can mark them as a tie.',
      reference_conversation_count: 0
    },
    participants: [{kind: 'original'}],
    sample_size: 123,
    reference: {kind: 'original'}
  })
};

fetch('https://distillation.training.wandb.ai/v1/evals', 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://distillation.training.wandb.ai/v1/evals",
  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([
    'name' => '<string>',
    'dataset_id' => '3c90c3cc-0d44-4b50-8888-8dd25736052a',
    'spec' => [
        'type' => 'h2h_judge',
        'judge_model_ref' => '<string>',
        'judge_prompt' => 'You are an intelligent and fair judge of chatbots. Evaluate the following two responses and choose which one is better. If the outputs are of similar quality, you can mark them as a tie.',
        'reference_conversation_count' => 0
    ],
    'participants' => [
        [
                'kind' => 'original'
        ]
    ],
    'sample_size' => 123,
    'reference' => [
        'kind' => 'original'
    ]
  ]),
  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://distillation.training.wandb.ai/v1/evals"

	payload := strings.NewReader("{\n  \"name\": \"<string>\",\n  \"dataset_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n  \"spec\": {\n    \"type\": \"h2h_judge\",\n    \"judge_model_ref\": \"<string>\",\n    \"judge_prompt\": \"You are an intelligent and fair judge of chatbots. Evaluate the following two responses and choose which one is better. If the outputs are of similar quality, you can mark them as a tie.\",\n    \"reference_conversation_count\": 0\n  },\n  \"participants\": [\n    {\n      \"kind\": \"original\"\n    }\n  ],\n  \"sample_size\": 123,\n  \"reference\": {\n    \"kind\": \"original\"\n  }\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://distillation.training.wandb.ai/v1/evals")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"<string>\",\n  \"dataset_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n  \"spec\": {\n    \"type\": \"h2h_judge\",\n    \"judge_model_ref\": \"<string>\",\n    \"judge_prompt\": \"You are an intelligent and fair judge of chatbots. Evaluate the following two responses and choose which one is better. If the outputs are of similar quality, you can mark them as a tie.\",\n    \"reference_conversation_count\": 0\n  },\n  \"participants\": [\n    {\n      \"kind\": \"original\"\n    }\n  ],\n  \"sample_size\": 123,\n  \"reference\": {\n    \"kind\": \"original\"\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://distillation.training.wandb.ai/v1/evals")

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  \"name\": \"<string>\",\n  \"dataset_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n  \"spec\": {\n    \"type\": \"h2h_judge\",\n    \"judge_model_ref\": \"<string>\",\n    \"judge_prompt\": \"You are an intelligent and fair judge of chatbots. Evaluate the following two responses and choose which one is better. If the outputs are of similar quality, you can mark them as a tie.\",\n    \"reference_conversation_count\": 0\n  },\n  \"participants\": [\n    {\n      \"kind\": \"original\"\n    }\n  ],\n  \"sample_size\": 123,\n  \"reference\": {\n    \"kind\": \"original\"\n  }\n}"

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

{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "dataset_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "name": "<string>",
  "spec": {
    "type": "h2h_judge",
    "judge_model_ref": "openai/gpt-5.6-sol",
    "judge_prompt": "<string>"
  },
  "participants": [
    {
      "kind": "original"
    }
  ],
  "sample_size": 123,
  "status": "queued",
  "progress": {
    "total": 123,
    "queued": 123,
    "running": 123,
    "completed": 123,
    "failed": 123
  },
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "reference": {
    "kind": "original"
  },
  "results": {},
  "failure_summary": {}
}

{
  "error": {
    "message": "Task 'missing' not found in entity 'your-team'",
    "type": "not_found"
  }
}