curl --request GET \
  --url https://api.calibrate.artpark.ai/agent-tests/benchmark/{task_id} \
  --header 'X-API-Key: <api-key>'

import requests

url = "https://api.calibrate.artpark.ai/agent-tests/benchmark/{task_id}"

headers = {"X-API-Key": "<api-key>"}

response = requests.get(url, headers=headers)

print(response.text)

{
  "task_id": "a3b2c1d0-e5f4-3210-abcd-ef1234567890",
  "name": "<string>",
  "status": "queued",
  "test_uuids": [
    "<string>"
  ],
  "parallel_models": true,
  "evaluators": [
    {
      "uuid": "<string>",
      "name": "<string>",
      "description": "<string>",
      "output_type": "binary",
      "output_config": {
        "scale": [
          {
            "color": "#e5484d",
            "name": "Wrong",
            "value": false
          },
          {
            "color": "#30a46c",
            "name": "Correct",
            "value": true
          }
        ]
      },
      "scale_min": 123,
      "scale_max": 123,
      "version_number": 123
    }
  ],
  "model_results": [
    {
      "model": "openai/gpt-4.1",
      "message": "<string>",
      "success": true,
      "total_tests": 123,
      "passed": 123,
      "failed": 123,
      "evaluator_summary": [
        {}
      ],
      "test_results": [
        {
          "test_case_id": "<string>",
          "name": "<string>",
          "test_uuid": "b1c2d3e4-f5a6-7890-bcde-f12345678901",
          "test_type": "response",
          "passed": true,
          "reasoning": "<string>",
          "output": {
            "response": "<string>",
            "tool_calls": [
              {
                "tool": "<string>",
                "arguments": {
                  "city": "Paris"
                },
                "output": "<unknown>"
              }
            ]
          },
          "test_case": {},
          "inputs": {},
          "judge_results": [
            {
              "evaluator_uuid": "<string>",
              "reasoning": "<string>",
              "match": true,
              "score": 123,
              "value_name": "<string>",
              "variable_values": {
                "criteria": "Is the reply correct and helpful?"
              }
            }
          ],
          "latency_ms": 123,
          "cost": 123,
          "unanswered": false,
          "not_run": false
        }
      ],
      "latency_ms": {},
      "cost": {},
      "total_tokens": {},
      "unanswered_tests": 123,
      "stopped_early": false
    }
  ],
  "leaderboard_summary": [
    {
      "cost": 0.0021,
      "failed": 2,
      "helpfulness": 0.92,
      "latency_p50": 480,
      "model": "openai/gpt-4.1",
      "passed": 8,
      "safety": 1
    },
    {
      "cost": 0.0034,
      "failed": 1,
      "helpfulness": 0.95,
      "latency_p50": 520,
      "model": "anthropic/claude-sonnet-4",
      "passed": 9,
      "safety": 1
    }
  ],
  "stopped_early": false,
  "aborted": false,
  "error": "<string>",
  "is_public": false,
  "share_token": "<string>"
}

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