{
  "benchmark_version": "1.0.0-pilot",
  "edition": "2026-08-13",
  "scope": "pilot-evaluations",
  "repetitions": 1,
  "transport_attempt_count": 216,
  "response_count": 216,
  "request_failure_count": 0,
  "total_cost": 0.8526301749999993,
  "models": {
    "holo3-122b-a10b": {
      "transport_attempt_count": 24,
      "response_count": 24,
      "request_failure_count": 0,
      "layout_defect": {
        "transport_attempt_count": 12,
        "request_failure_count": 0,
        "metrics": {
          "balancedAccuracy": 0.5833333333333334,
          "recall": 0.16666666666666666,
          "specificity": 1,
          "falsePositiveRate": 0,
          "categoryAccuracy": 0,
          "meanLocalizationIoU": 0,
          "schemaValidRate": 0.6666666666666666
        },
        "attempts": [
          {
            "attempt_id": "23dbea438273d8c60080705a",
            "model": "holo3-122b-a10b",
            "case_id": "commerce-catalog-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 1873.75,
            "cost": 0.000623,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "98eedfb60592ddd767661484",
            "model": "holo3-122b-a10b",
            "case_id": "commerce-catalog-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "invalid_response",
            "wall_time_ms": 4552.994,
            "cost": 0.00176,
            "schemaValid": false,
            "classificationCorrect": false,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": false,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": true
          },
          {
            "attempt_id": "af9680af2a2b30e1cfe62d2a",
            "model": "holo3-122b-a10b",
            "case_id": "analytics-dashboard-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 1418.961,
            "cost": 0.00062,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "c0b53ef3936728b3b10f6408",
            "model": "holo3-122b-a10b",
            "case_id": "analytics-dashboard-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "invalid_response",
            "wall_time_ms": 4570.704,
            "cost": 0.00176,
            "schemaValid": false,
            "classificationCorrect": false,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": false,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": true
          },
          {
            "attempt_id": "29cd939395d0b0c8a9ec457e",
            "model": "holo3-122b-a10b",
            "case_id": "iot-control-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 1475.156,
            "cost": 0.000629,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "ed5f82ba0bfafcdedf064486",
            "model": "holo3-122b-a10b",
            "case_id": "iot-control-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "invalid_response",
            "wall_time_ms": 4420.451,
            "cost": 0.00176,
            "schemaValid": false,
            "classificationCorrect": false,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": false,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": true
          },
          {
            "attempt_id": "b4ed337c5b0dfb848a40e741",
            "model": "holo3-122b-a10b",
            "case_id": "banking-ios/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 1328.103,
            "cost": 0.0002498,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "945a7ee6b2d3b911c2d65106",
            "model": "holo3-122b-a10b",
            "case_id": "banking-ios/defect/layout-defect",
            "track": "layout-defect",
            "status": "invalid_response",
            "wall_time_ms": 4317.047,
            "cost": 0.0013808000000000002,
            "schemaValid": false,
            "classificationCorrect": false,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": false,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": true
          },
          {
            "attempt_id": "c9837f269d3d418d5b357479",
            "model": "holo3-122b-a10b",
            "case_id": "flight-pass-ios/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 1217.647,
            "cost": 0.0002408,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "f82d7b078a89be5e2cbc0cff",
            "model": "holo3-122b-a10b",
            "case_id": "flight-pass-ios/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 1689.261,
            "cost": 0.0003788,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "e35dde7f4cec515799722e51",
            "model": "holo3-122b-a10b",
            "case_id": "smart-home-android/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 1282.939,
            "cost": 0.0002498,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "73419010cf1d718544eb27d5",
            "model": "holo3-122b-a10b",
            "case_id": "smart-home-android/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 1170.958,
            "cost": 0.0002498,
            "schemaValid": true,
            "classificationCorrect": false,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": false,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": true
          }
        ]
      },
      "element_presence": {
        "transport_attempt_count": 12,
        "request_failure_count": 0,
        "metrics": {
          "balancedAccuracy": 1,
          "presentRecall": 1,
          "absentSpecificity": 1,
          "falsePositiveRate": 0,
          "schemaValidRate": 1
        },
        "attempts": [
          {
            "attempt_id": "82f52aee9a6318687b644fff",
            "model": "holo3-122b-a10b",
            "case_id": "commerce-catalog-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 1409.851,
            "cost": 0.0005532,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "d375a82286cfdcdf35596afc",
            "model": "holo3-122b-a10b",
            "case_id": "commerce-catalog-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 1522.357,
            "cost": 0.0005536,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "9a3a6ca6ea142285590ab1af",
            "model": "holo3-122b-a10b",
            "case_id": "analytics-dashboard-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 1434.018,
            "cost": 0.0005532,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "b872d094269b8cd9a50e5d07",
            "model": "holo3-122b-a10b",
            "case_id": "analytics-dashboard-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 1302.458,
            "cost": 0.0005532,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "b35c845ad6e490f874777e08",
            "model": "holo3-122b-a10b",
            "case_id": "iot-control-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 1376.836,
            "cost": 0.0005532,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "434bc36bb13c248923fab61d",
            "model": "holo3-122b-a10b",
            "case_id": "iot-control-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 1599.989,
            "cost": 0.0005532,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "0d804b64c43859ba20a4abc8",
            "model": "holo3-122b-a10b",
            "case_id": "banking-ios/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 1321.134,
            "cost": 0.0001736,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "21f2b498a9c5025fd59d039f",
            "model": "holo3-122b-a10b",
            "case_id": "banking-ios/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 1099.849,
            "cost": 0.000174,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "937711a8e1100792088da246",
            "model": "holo3-122b-a10b",
            "case_id": "flight-pass-ios/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 1074.002,
            "cost": 0.000174,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "b63bc44fc862ae5a1eab0c2a",
            "model": "holo3-122b-a10b",
            "case_id": "flight-pass-ios/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 1109.622,
            "cost": 0.000174,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "4e15c6acf5384d53609344b1",
            "model": "holo3-122b-a10b",
            "case_id": "smart-home-android/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 1108.179,
            "cost": 0.000174,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "e3618fb2f10ed143f74e5e32",
            "model": "holo3-122b-a10b",
            "case_id": "smart-home-android/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 1110.242,
            "cost": 0.00017439999999999998,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          }
        ]
      },
      "operations": {
        "latency_p50_ms": 1324.6185,
        "latency_p95_ms": 1698.4854500000001,
        "mean_latency_ms": 1346.2655999999997,
        "total_cost": 0.014265400000000001
      }
    },
    "openai/gpt-5.6-luna": {
      "transport_attempt_count": 24,
      "response_count": 24,
      "request_failure_count": 0,
      "layout_defect": {
        "transport_attempt_count": 12,
        "request_failure_count": 0,
        "metrics": {
          "balancedAccuracy": 0.8333333333333333,
          "recall": 0.6666666666666666,
          "specificity": 1,
          "falsePositiveRate": 0,
          "categoryAccuracy": 0.5,
          "meanLocalizationIoU": 0.219202510648658,
          "schemaValidRate": 0.9166666666666666
        },
        "attempts": [
          {
            "attempt_id": "f8cc5c5e56a3bb41a76a4d86",
            "model": "openai/gpt-5.6-luna",
            "case_id": "commerce-catalog-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 7298.096,
            "cost": 0.00025285,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "9315262a63d0dc567ae9d206",
            "model": "openai/gpt-5.6-luna",
            "case_id": "commerce-catalog-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 9782.626,
            "cost": 0.00035485,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.13181144553248025,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "fc3d545a2a9e30eb74f3a117",
            "model": "openai/gpt-5.6-luna",
            "case_id": "analytics-dashboard-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 8330.8,
            "cost": 0.00025285,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "2e53f85317345dc6c7a1c352",
            "model": "openai/gpt-5.6-luna",
            "case_id": "analytics-dashboard-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 8718.106,
            "cost": 0.00035305,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.20541592423945443,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "0d3d1d07f8e14c14f12cbae2",
            "model": "openai/gpt-5.6-luna",
            "case_id": "iot-control-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 8005.939,
            "cost": 0.00027925,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "eddcad7dcc9916e1ddbcd892",
            "model": "openai/gpt-5.6-luna",
            "case_id": "iot-control-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 9559.982,
            "cost": 0.00035965,
            "schemaValid": true,
            "classificationCorrect": false,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": false,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": true
          },
          {
            "attempt_id": "85bfe8a16fadb5ca1bef5098",
            "model": "openai/gpt-5.6-luna",
            "case_id": "banking-ios/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 7352.379,
            "cost": 0.0001182,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "769a8de81eafbd54d6387e66",
            "model": "openai/gpt-5.6-luna",
            "case_id": "banking-ios/defect/layout-defect",
            "track": "layout-defect",
            "status": "invalid_response",
            "wall_time_ms": 11652.957,
            "cost": 0.0003144,
            "schemaValid": false,
            "classificationCorrect": false,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": false,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": true
          },
          {
            "attempt_id": "d9d87126e530426b7ae0b863",
            "model": "openai/gpt-5.6-luna",
            "case_id": "flight-pass-ios/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 4323.162,
            "cost": 0.0001152,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "9e197a0acb3e9624515e476c",
            "model": "openai/gpt-5.6-luna",
            "case_id": "flight-pass-ios/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 9528.536,
            "cost": 0.0001914,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.9779876941200134,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "71dd3f60d8ffbc6f8830cef7",
            "model": "openai/gpt-5.6-luna",
            "case_id": "smart-home-android/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 6596.039,
            "cost": 0.0000912,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "6ee5ff182a36784fa3dada05",
            "model": "openai/gpt-5.6-luna",
            "case_id": "smart-home-android/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 9128.588,
            "cost": 0.0001836,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          }
        ]
      },
      "element_presence": {
        "transport_attempt_count": 12,
        "request_failure_count": 0,
        "metrics": {
          "balancedAccuracy": 1,
          "presentRecall": 1,
          "absentSpecificity": 1,
          "falsePositiveRate": 0,
          "schemaValidRate": 1
        },
        "attempts": [
          {
            "attempt_id": "34825aaa1cec6224e7087d26",
            "model": "openai/gpt-5.6-luna",
            "case_id": "commerce-catalog-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7112.97,
            "cost": 0.0002197,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "b764c1871acc14856c91a105",
            "model": "openai/gpt-5.6-luna",
            "case_id": "commerce-catalog-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 5481.131,
            "cost": 0.000219825,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "358f282fde5f403dc41c3603",
            "model": "openai/gpt-5.6-luna",
            "case_id": "analytics-dashboard-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7526.864,
            "cost": 0.0002197,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "5c7fdc54884428de07c4221d",
            "model": "openai/gpt-5.6-luna",
            "case_id": "analytics-dashboard-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7646.455,
            "cost": 0.0002197,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "1a329a52d2ef5fab1bdbfaf4",
            "model": "openai/gpt-5.6-luna",
            "case_id": "iot-control-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8630.29,
            "cost": 0.0002197,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "7f5c72c6ff0d82536092de47",
            "model": "openai/gpt-5.6-luna",
            "case_id": "iot-control-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7668.405,
            "cost": 0.0002197,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "49b91d24cf7b6078e54eabb9",
            "model": "openai/gpt-5.6-luna",
            "case_id": "banking-ios/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8112.903,
            "cost": 0.0000629,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "bc6ab462dfbbfb00928a27fd",
            "model": "openai/gpt-5.6-luna",
            "case_id": "banking-ios/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7271.038,
            "cost": 0.000063,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "16b9bdce56ecf883904e5384",
            "model": "openai/gpt-5.6-luna",
            "case_id": "flight-pass-ios/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7121.389,
            "cost": 0.000063,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "5cd9c12d94d9aaabc936d1f1",
            "model": "openai/gpt-5.6-luna",
            "case_id": "flight-pass-ios/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 6330.061,
            "cost": 0.000063,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "fd0e8cfcc380c6695b4b2d9b",
            "model": "openai/gpt-5.6-luna",
            "case_id": "smart-home-android/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8284.082,
            "cost": 0.000063,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "5dd9f776499192d285ff1ed9",
            "model": "openai/gpt-5.6-luna",
            "case_id": "smart-home-android/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8260.611,
            "cost": 0.0000631,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          }
        ]
      },
      "operations": {
        "latency_p50_ms": 7668.405,
        "latency_p95_ms": 9556.8374,
        "mean_latency_ms": 7742.193565217391,
        "total_cost": 0.0045628249999999995
      }
    },
    "openai/gpt-5.4": {
      "transport_attempt_count": 24,
      "response_count": 24,
      "request_failure_count": 0,
      "layout_defect": {
        "transport_attempt_count": 12,
        "request_failure_count": 0,
        "metrics": {
          "balancedAccuracy": 0.9166666666666667,
          "recall": 0.8333333333333334,
          "specificity": 1,
          "falsePositiveRate": 0,
          "categoryAccuracy": 0.6666666666666666,
          "meanLocalizationIoU": 0.13327797281219558,
          "schemaValidRate": 1
        },
        "attempts": [
          {
            "attempt_id": "5dda3f38acfba8ed470aea11",
            "model": "openai/gpt-5.4",
            "case_id": "commerce-catalog-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 7301.393,
            "cost": 0.0055625,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "4f9d5c6b471ec3f12152c00e",
            "model": "openai/gpt-5.4",
            "case_id": "commerce-catalog-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 9238.64,
            "cost": 0.0067625,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.4140664588641983,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "19e5cdf799b61e0ab960e60f",
            "model": "openai/gpt-5.4",
            "case_id": "analytics-dashboard-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 8272.883,
            "cost": 0.0054425,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "c35632b52a83cb3bfc9f29d7",
            "model": "openai/gpt-5.4",
            "case_id": "analytics-dashboard-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 11760.102,
            "cost": 0.0077525,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.2190424893564988,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "61f2ad8823ba8fb7168e922f",
            "model": "openai/gpt-5.4",
            "case_id": "iot-control-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 9037.365,
            "cost": 0.0057725,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "6dba9ec0d3e6b368d406fd44",
            "model": "openai/gpt-5.4",
            "case_id": "iot-control-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 9934.977,
            "cost": 0.0073175,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.078287237373925,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "18f8dfeb518b7f01aaa76a6f",
            "model": "openai/gpt-5.4",
            "case_id": "banking-ios/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 7071.076,
            "cost": 0.003195,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "5b4fd679dd4ffc113a32d583",
            "model": "openai/gpt-5.4",
            "case_id": "banking-ios/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 7748.332,
            "cost": 0.004155,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.08827165127855152,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "62d0cd89b0f64e6a8e124fc7",
            "model": "openai/gpt-5.4",
            "case_id": "flight-pass-ios/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 7200.492,
            "cost": 0.002895,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "0cdd24e0b8f6c6e7c71f7e4b",
            "model": "openai/gpt-5.4",
            "case_id": "flight-pass-ios/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 12153.954,
            "cost": 0.007695,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "e004b8f680ac06a585d464bf",
            "model": "openai/gpt-5.4",
            "case_id": "smart-home-android/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 9202.109,
            "cost": 0.002625,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "275dd6d318cd7774c54a4a9b",
            "model": "openai/gpt-5.4",
            "case_id": "smart-home-android/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 9301.874,
            "cost": 0.003315,
            "schemaValid": true,
            "classificationCorrect": false,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": false,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": true
          }
        ]
      },
      "element_presence": {
        "transport_attempt_count": 12,
        "request_failure_count": 0,
        "metrics": {
          "balancedAccuracy": 1,
          "presentRecall": 1,
          "absentSpecificity": 1,
          "falsePositiveRate": 0,
          "schemaValidRate": 1
        },
        "attempts": [
          {
            "attempt_id": "eea7c5fda441bd436808dd08",
            "model": "openai/gpt-5.4",
            "case_id": "commerce-catalog-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8700.934,
            "cost": 0.0044375,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "07ad888e3e7253984f74455f",
            "model": "openai/gpt-5.4",
            "case_id": "commerce-catalog-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 4591.945,
            "cost": 0.004785,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "1c31d8fdb59e256f6f9cc860",
            "model": "openai/gpt-5.4",
            "case_id": "analytics-dashboard-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8174.375,
            "cost": 0.0047675,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "e19942a3670affb2beac5fac",
            "model": "openai/gpt-5.4",
            "case_id": "analytics-dashboard-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7281.739,
            "cost": 0.0046775,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "69c29ca06f3d89d3e2a48fb4",
            "model": "openai/gpt-5.4",
            "case_id": "iot-control-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 4810.253,
            "cost": 0.0044375,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "6b6a9b3cc3d33723d7db03f2",
            "model": "openai/gpt-5.4",
            "case_id": "iot-control-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 6925.881,
            "cost": 0.0048875,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "bfede36450c2a5fed0d705e5",
            "model": "openai/gpt-5.4",
            "case_id": "banking-ios/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8255.532,
            "cost": 0.0018125,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "14b4ab752b925e35f2302eed",
            "model": "openai/gpt-5.4",
            "case_id": "banking-ios/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7998.913,
            "cost": 0.001965,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "c6cdea4c28d15bc5687e7a39",
            "model": "openai/gpt-5.4",
            "case_id": "flight-pass-ios/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7684.661,
            "cost": 0.001575,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "22ae65009b8b5c3e7ba877f1",
            "model": "openai/gpt-5.4",
            "case_id": "flight-pass-ios/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 9972.044,
            "cost": 0.001815,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "0dbc0b0fb0bacfea6eaed75c",
            "model": "openai/gpt-5.4",
            "case_id": "smart-home-android/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8331.486,
            "cost": 0.001575,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "c0574e413700de2344729f33",
            "model": "openai/gpt-5.4",
            "case_id": "smart-home-android/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7911.794,
            "cost": 0.0021475,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          }
        ]
      },
      "operations": {
        "latency_p50_ms": 8214.9535,
        "latency_p95_ms": 11491.893299999998,
        "mean_latency_ms": 8285.948083333333,
        "total_cost": 0.10137249999999998
      }
    },
    "google/gemini-3.6-flash": {
      "transport_attempt_count": 24,
      "response_count": 24,
      "request_failure_count": 0,
      "layout_defect": {
        "transport_attempt_count": 12,
        "request_failure_count": 0,
        "metrics": {
          "balancedAccuracy": 0.75,
          "recall": 0.8333333333333334,
          "specificity": 0.6666666666666666,
          "falsePositiveRate": 0.33333333333333337,
          "categoryAccuracy": 0.6666666666666666,
          "meanLocalizationIoU": 0.2223137768622411,
          "schemaValidRate": 0.75
        },
        "attempts": [
          {
            "attempt_id": "34e87b10ae241ca13200199f",
            "model": "google/gemini-3.6-flash",
            "case_id": "commerce-catalog-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 7308.114,
            "cost": 0.0025965,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "79c3cc048b654e14ab9e6fdc",
            "model": "google/gemini-3.6-flash",
            "case_id": "commerce-catalog-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 9657.513,
            "cost": 0.0043365,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.20590071454340703,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "9ddd651309f8eee78f42ff5f",
            "model": "google/gemini-3.6-flash",
            "case_id": "analytics-dashboard-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "invalid_response",
            "wall_time_ms": 6056.023,
            "cost": 0.004809,
            "schemaValid": false,
            "classificationCorrect": false,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": false,
            "falsePositive": true,
            "falseNegative": false
          },
          {
            "attempt_id": "5a8537c8615516fe39918d2d",
            "model": "google/gemini-3.6-flash",
            "case_id": "analytics-dashboard-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "invalid_response",
            "wall_time_ms": 9062.234,
            "cost": 0.004719,
            "schemaValid": false,
            "classificationCorrect": false,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": false,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": true
          },
          {
            "attempt_id": "36e338f3f3ee50886d4d2e16",
            "model": "google/gemini-3.6-flash",
            "case_id": "iot-control-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "invalid_response",
            "wall_time_ms": 8942.137,
            "cost": 0.0047265,
            "schemaValid": false,
            "classificationCorrect": false,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": false,
            "falsePositive": true,
            "falseNegative": false
          },
          {
            "attempt_id": "453294dab965d412a6322695",
            "model": "google/gemini-3.6-flash",
            "case_id": "iot-control-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 9320.95,
            "cost": 0.003174,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.078287237373925,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "ebe861bdb53a1036f1e98434",
            "model": "google/gemini-3.6-flash",
            "case_id": "banking-ios/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 7251.691,
            "cost": 0.0028455,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "af8deffb570e4e1776742500",
            "model": "google/gemini-3.6-flash",
            "case_id": "banking-ios/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 8585.545,
            "cost": 0.004503,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.0657051964418146,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "f6948db6e2359d841e9f12bf",
            "model": "google/gemini-3.6-flash",
            "case_id": "flight-pass-ios/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 6411.38,
            "cost": 0.0023805,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "f9d9ef3217847cc13cd11d3a",
            "model": "google/gemini-3.6-flash",
            "case_id": "flight-pass-ios/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 9482.401,
            "cost": 0.004638,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.9839895128143,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "03faf8feb701364f33b493c3",
            "model": "google/gemini-3.6-flash",
            "case_id": "smart-home-android/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 9457.611,
            "cost": 0.0028455,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "537e6e849f2b5667c05c8c80",
            "model": "google/gemini-3.6-flash",
            "case_id": "smart-home-android/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 9583.21,
            "cost": 0.0044355,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          }
        ]
      },
      "element_presence": {
        "transport_attempt_count": 12,
        "request_failure_count": 0,
        "metrics": {
          "balancedAccuracy": 1,
          "presentRecall": 1,
          "absentSpecificity": 1,
          "falsePositiveRate": 0,
          "schemaValidRate": 1
        },
        "attempts": [
          {
            "attempt_id": "dd769b62c22493395d2d4baa",
            "model": "google/gemini-3.6-flash",
            "case_id": "commerce-catalog-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8254.57,
            "cost": 0.002163,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "37f6948c22c3e0365ff9e276",
            "model": "google/gemini-3.6-flash",
            "case_id": "commerce-catalog-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 5011.479,
            "cost": 0.0027945,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "284d76274e5a8460208e1707",
            "model": "google/gemini-3.6-flash",
            "case_id": "analytics-dashboard-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7915.806,
            "cost": 0.002253,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "5bec835cd6a58245c804a3f2",
            "model": "google/gemini-3.6-flash",
            "case_id": "analytics-dashboard-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8310.038,
            "cost": 0.0025755,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "db1c87215a301699f6cb5242",
            "model": "google/gemini-3.6-flash",
            "case_id": "iot-control-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 9200.898,
            "cost": 0.0021555,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "ff9093973d24d90783027d05",
            "model": "google/gemini-3.6-flash",
            "case_id": "iot-control-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 6307.315,
            "cost": 0.0025005,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "72b9b940e03431814ff03cf5",
            "model": "google/gemini-3.6-flash",
            "case_id": "banking-ios/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8327.333,
            "cost": 0.0020805,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "f80a9bc3aa49b3e8b4965173",
            "model": "google/gemini-3.6-flash",
            "case_id": "banking-ios/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8036.131,
            "cost": 0.002547,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "80a073573fa7f0e0ddc0766c",
            "model": "google/gemini-3.6-flash",
            "case_id": "flight-pass-ios/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 6078.112,
            "cost": 0.001752,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "bf07578350636091e2947f98",
            "model": "google/gemini-3.6-flash",
            "case_id": "flight-pass-ios/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8841.406,
            "cost": 0.002517,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "beb3900301c227f0e27ec3c3",
            "model": "google/gemini-3.6-flash",
            "case_id": "smart-home-android/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8834.448,
            "cost": 0.002172,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "b43b887d73ea510971727f37",
            "model": "google/gemini-3.6-flash",
            "case_id": "smart-home-android/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8690.337,
            "cost": 0.002601,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          }
        ]
      },
      "operations": {
        "latency_p50_ms": 8327.333,
        "latency_p95_ms": 9583.21,
        "mean_latency_ms": 8136.489904761905,
        "total_cost": 0.07412099999999999
      }
    },
    "anthropic/claude-opus-5": {
      "transport_attempt_count": 24,
      "response_count": 24,
      "request_failure_count": 0,
      "layout_defect": {
        "transport_attempt_count": 12,
        "request_failure_count": 0,
        "metrics": {
          "balancedAccuracy": 0.8333333333333333,
          "recall": 0.6666666666666666,
          "specificity": 1,
          "falsePositiveRate": 0,
          "categoryAccuracy": 0.6666666666666666,
          "meanLocalizationIoU": 0.053348574541154846,
          "schemaValidRate": 0.8333333333333334
        },
        "attempts": [
          {
            "attempt_id": "a6dfc302cc1f1e63384113af",
            "model": "anthropic/claude-opus-5",
            "case_id": "commerce-catalog-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 8640.232,
            "cost": 0.01396,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "45a436303fb3e818c2357e1f",
            "model": "anthropic/claude-opus-5",
            "case_id": "commerce-catalog-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 11455.621,
            "cost": 0.015935,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.16942182810769355,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "6d93b14400feb757d679cab2",
            "model": "anthropic/claude-opus-5",
            "case_id": "analytics-dashboard-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 8913.445,
            "cost": 0.01396,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "fe210fc271998c8a6166adb3",
            "model": "anthropic/claude-opus-5",
            "case_id": "analytics-dashboard-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 11068.927,
            "cost": 0.015285,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "131cf1055fcfe74b7bd638c7",
            "model": "anthropic/claude-opus-5",
            "case_id": "iot-control-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 9985.665,
            "cost": 0.01396,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "dd02679c3c6eac323668c9eb",
            "model": "anthropic/claude-opus-5",
            "case_id": "iot-control-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 8622.326,
            "cost": 0.01546,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.08138298218650988,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "5f23de78283205381241a3d7",
            "model": "anthropic/claude-opus-5",
            "case_id": "banking-ios/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 9865.904,
            "cost": 0.007525,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "e47d1b27a08f21fd2ea4bfca",
            "model": "anthropic/claude-opus-5",
            "case_id": "banking-ios/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 10405.002,
            "cost": 0.00885,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.06928663695272562,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "271146782886eef39c06d51d",
            "model": "anthropic/claude-opus-5",
            "case_id": "flight-pass-ios/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 8973.582,
            "cost": 0.007525,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "6047c7c882a3e573aecfdc00",
            "model": "anthropic/claude-opus-5",
            "case_id": "flight-pass-ios/defect/layout-defect",
            "track": "layout-defect",
            "status": "invalid_response",
            "wall_time_ms": 12337.571,
            "cost": 0.0089,
            "schemaValid": false,
            "classificationCorrect": false,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": false,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": true
          },
          {
            "attempt_id": "3b3e52c7842066b934f642f8",
            "model": "anthropic/claude-opus-5",
            "case_id": "smart-home-android/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 10636.102,
            "cost": 0.007525,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "e373213baee0b23257b80714",
            "model": "anthropic/claude-opus-5",
            "case_id": "smart-home-android/defect/layout-defect",
            "track": "layout-defect",
            "status": "invalid_response",
            "wall_time_ms": 10922.257,
            "cost": 0.00915,
            "schemaValid": false,
            "classificationCorrect": false,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": false,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": true
          }
        ]
      },
      "element_presence": {
        "transport_attempt_count": 12,
        "request_failure_count": 0,
        "metrics": {
          "balancedAccuracy": 1,
          "presentRecall": 1,
          "absentSpecificity": 1,
          "falsePositiveRate": 0,
          "schemaValidRate": 1
        },
        "attempts": [
          {
            "attempt_id": "7da42aa73289eff4010b4b06",
            "model": "anthropic/claude-opus-5",
            "case_id": "commerce-catalog-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 9809.575,
            "cost": 0.010675,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "07a8bda22378b8e9e960e14a",
            "model": "anthropic/claude-opus-5",
            "case_id": "commerce-catalog-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8167.925,
            "cost": 0.01069,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "538cd973558b3dd29c40d9a3",
            "model": "anthropic/claude-opus-5",
            "case_id": "analytics-dashboard-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 9464.25,
            "cost": 0.01069,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "12f6971b263539a37c8049d5",
            "model": "anthropic/claude-opus-5",
            "case_id": "analytics-dashboard-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 9885.499,
            "cost": 0.010685,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "4dbb5eae4167fe394e0bbb14",
            "model": "anthropic/claude-opus-5",
            "case_id": "iot-control-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8356.66,
            "cost": 0.01068,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "c158ac432f91a843dc593fad",
            "model": "anthropic/claude-opus-5",
            "case_id": "iot-control-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 9739.201,
            "cost": 0.01069,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "25952f78ef62e01a0da82e3b",
            "model": "anthropic/claude-opus-5",
            "case_id": "banking-ios/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 9925.548,
            "cost": 0.00427,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "643eddbf60607e23d15a131f",
            "model": "anthropic/claude-opus-5",
            "case_id": "banking-ios/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 9991.768,
            "cost": 0.004275,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "f147992c92e2fb4689dd8dc6",
            "model": "anthropic/claude-opus-5",
            "case_id": "flight-pass-ios/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 10174.298,
            "cost": 0.004265,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "9f86dfc054064006faf0f37d",
            "model": "anthropic/claude-opus-5",
            "case_id": "flight-pass-ios/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 11074.312,
            "cost": 0.00428,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "890e3a1f0fea53b5b8cd61c4",
            "model": "anthropic/claude-opus-5",
            "case_id": "smart-home-android/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 9521.605,
            "cost": 0.004265,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "451d92e94e14c6cbb8c56ac9",
            "model": "anthropic/claude-opus-5",
            "case_id": "smart-home-android/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 12069.287,
            "cost": 0.00428,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          }
        ]
      },
      "operations": {
        "latency_p50_ms": 9875.7015,
        "latency_p95_ms": 11436.55555,
        "mean_latency_ms": 9852.124272727275,
        "total_cost": 0.22777999999999998
      }
    },
    "x-ai/grok-4.5": {
      "transport_attempt_count": 24,
      "response_count": 24,
      "request_failure_count": 0,
      "layout_defect": {
        "transport_attempt_count": 12,
        "request_failure_count": 0,
        "metrics": {
          "balancedAccuracy": 1,
          "recall": 1,
          "specificity": 1,
          "falsePositiveRate": 0,
          "categoryAccuracy": 0.6666666666666666,
          "meanLocalizationIoU": 0.20701244492353535,
          "schemaValidRate": 1
        },
        "attempts": [
          {
            "attempt_id": "9684eae2ae921a2137022d03",
            "model": "x-ai/grok-4.5",
            "case_id": "commerce-catalog-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 8667.634,
            "cost": 0.004074,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "f73909e6e51af755618010c8",
            "model": "x-ai/grok-4.5",
            "case_id": "commerce-catalog-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 8632.286,
            "cost": 0.0040904,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "7c36cf9c68baff7251c0b08f",
            "model": "x-ai/grok-4.5",
            "case_id": "analytics-dashboard-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 6673.149,
            "cost": 0.0038384,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "53803a2cda26fed087b9d034",
            "model": "x-ai/grok-4.5",
            "case_id": "analytics-dashboard-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 7653.396,
            "cost": 0.0040664,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.2849715735723838,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "c7c6336fdc47dbc4ba3b3a57",
            "model": "x-ai/grok-4.5",
            "case_id": "iot-control-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 7772.557,
            "cost": 0.0038384,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "8c0e83283af1bcbd05155f15",
            "model": "x-ai/grok-4.5",
            "case_id": "iot-control-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 8655.981,
            "cost": 0.0040604,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.0744680882752378,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "1a54eb0d19be7ca1402abd5b",
            "model": "x-ai/grok-4.5",
            "case_id": "banking-ios/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 7073.121,
            "cost": 0.0012776,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "30b925069f52475d9597a8f9",
            "model": "x-ai/grok-4.5",
            "case_id": "banking-ios/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 6177.766,
            "cost": 0.0021584,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.191231137859705,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "8c7cc0b84e0be1e78d2ab4b9",
            "model": "x-ai/grok-4.5",
            "case_id": "flight-pass-ios/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 7793.393,
            "cost": 0.0012776,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "8a061fee728ccf33c2ed72e5",
            "model": "x-ai/grok-4.5",
            "case_id": "flight-pass-ios/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 6350.449,
            "cost": 0.0014336,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "f3e119969d8f636c75a2ee44",
            "model": "x-ai/grok-4.5",
            "case_id": "smart-home-android/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 7817.824,
            "cost": 0.0012776,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "ab31d0cace0338940018d643",
            "model": "x-ai/grok-4.5",
            "case_id": "smart-home-android/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 5505.525,
            "cost": 0.0015656,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.6914038698338856,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          }
        ]
      },
      "element_presence": {
        "transport_attempt_count": 12,
        "request_failure_count": 0,
        "metrics": {
          "balancedAccuracy": 1,
          "presentRecall": 1,
          "absentSpecificity": 1,
          "falsePositiveRate": 0,
          "schemaValidRate": 1
        },
        "attempts": [
          {
            "attempt_id": "d2760d9f298681f58ae12ac9",
            "model": "x-ai/grok-4.5",
            "case_id": "commerce-catalog-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7726.759,
            "cost": 0.0031884,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "03f1a457b90630015d276253",
            "model": "x-ai/grok-4.5",
            "case_id": "commerce-catalog-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 6260.456,
            "cost": 0.0031904,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "08588bcdfd8ca5a6069b463b",
            "model": "x-ai/grok-4.5",
            "case_id": "analytics-dashboard-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7430.204,
            "cost": 0.0031884,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "d7f196a91be605afe4cfd4f2",
            "model": "x-ai/grok-4.5",
            "case_id": "analytics-dashboard-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7623.849,
            "cost": 0.0031884,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "90ce84aaff541a48712b4203",
            "model": "x-ai/grok-4.5",
            "case_id": "iot-control-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7425.814,
            "cost": 0.0031884,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "b53cc1f8ca7a9790fe238632",
            "model": "x-ai/grok-4.5",
            "case_id": "iot-control-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 4719.088,
            "cost": 0.0031884,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "17af2215037821cce8e7dfe7",
            "model": "x-ai/grok-4.5",
            "case_id": "banking-ios/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8915.689,
            "cost": 0.0012784,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "713c91a6dc59e9bc8b367538",
            "model": "x-ai/grok-4.5",
            "case_id": "banking-ios/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8453.132,
            "cost": 0.0012804,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "f67e384d87d30b555581110e",
            "model": "x-ai/grok-4.5",
            "case_id": "flight-pass-ios/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7409.033,
            "cost": 0.0012804,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "67bd5af6b7f5683529598531",
            "model": "x-ai/grok-4.5",
            "case_id": "flight-pass-ios/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8266.412,
            "cost": 0.0012804,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "6df6037a1a61f2adcdac0c8d",
            "model": "x-ai/grok-4.5",
            "case_id": "smart-home-android/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7821.943,
            "cost": 0.0012804,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "d7049a89854b893c9962127e",
            "model": "x-ai/grok-4.5",
            "case_id": "smart-home-android/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7994.068,
            "cost": 0.0012824,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          }
        ]
      },
      "operations": {
        "latency_p50_ms": 7690.077499999999,
        "latency_p95_ms": 8665.88605,
        "mean_latency_ms": 7450.813666666666,
        "total_cost": 0.0597732
      }
    },
    "anthropic/claude-sonnet-5": {
      "transport_attempt_count": 24,
      "response_count": 24,
      "request_failure_count": 0,
      "layout_defect": {
        "transport_attempt_count": 12,
        "request_failure_count": 0,
        "metrics": {
          "balancedAccuracy": 0.8333333333333334,
          "recall": 0.8333333333333334,
          "specificity": 0.8333333333333334,
          "falsePositiveRate": 0.16666666666666663,
          "categoryAccuracy": 0.6666666666666666,
          "meanLocalizationIoU": 0.07062669728909692,
          "schemaValidRate": 0.9166666666666666
        },
        "attempts": [
          {
            "attempt_id": "51892af080675f38c33b555b",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "commerce-catalog-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 12126.283,
            "cost": 0.005934,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "3af99d831d2b99bfbabdc19a",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "commerce-catalog-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 11343.544,
            "cost": 0.006174,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.22458948111819296,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "c6a44b560690cdb8d73b58d1",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "analytics-dashboard-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 8670.418,
            "cost": 0.005964,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "cbc4564c4ccdc819e5d63cfb",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "analytics-dashboard-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 11243.435,
            "cost": 0.006134,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.1282066210795356,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "203ec760c6140d3cbbb8e12f",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "iot-control-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 9569.148,
            "cost": 0.005934,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "718ad1e68ce290c1887004a5",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "iot-control-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 10760.483,
            "cost": 0.006224,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.07096408153685295,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "14975f1c86cf7695e0f36dd3",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "banking-ios/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 10247.324,
            "cost": 0.00354,
            "schemaValid": true,
            "classificationCorrect": false,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": false,
            "falsePositive": true,
            "falseNegative": false
          },
          {
            "attempt_id": "1316605dc2d2dcddee0d2b74",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "banking-ios/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 10577.129,
            "cost": 0.00357,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "d3fef3ffc4238e01546b08de",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "flight-pass-ios/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 10538.047,
            "cost": 0.00303,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "aafe9a5e8c9f8da7d3cc5212",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "flight-pass-ios/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 10046.405,
            "cost": 0.00354,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "0f0d281d9bb5b615d03543f5",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "smart-home-android/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 10275.663,
            "cost": 0.00309,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "cb4f93c56144bb3369801136",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "smart-home-android/defect/layout-defect",
            "track": "layout-defect",
            "status": "invalid_response",
            "wall_time_ms": 10868.543,
            "cost": 0.00375,
            "schemaValid": false,
            "classificationCorrect": false,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": false,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": true
          }
        ]
      },
      "element_presence": {
        "transport_attempt_count": 12,
        "request_failure_count": 0,
        "metrics": {
          "balancedAccuracy": 1,
          "presentRecall": 1,
          "absentSpecificity": 1,
          "falsePositiveRate": 0,
          "schemaValidRate": 1
        },
        "attempts": [
          {
            "attempt_id": "cb60feac6b4ba3afcbbe94cc",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "commerce-catalog-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 6599.364,
            "cost": 0.00427,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "eb319fd25dbecb5aa14e6a35",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "commerce-catalog-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7768.595,
            "cost": 0.004276,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "c60c499a69037b0356a0394d",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "analytics-dashboard-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 9993.651,
            "cost": 0.004276,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "285c94357f03739dc0cad665",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "analytics-dashboard-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 12364.155,
            "cost": 0.004274,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "861ad8a9242eadc11904a4bb",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "iot-control-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 10463.62,
            "cost": 0.004272,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "1a124269ad06ef1fb54cf068",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "iot-control-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 9327.416,
            "cost": 0.004276,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "b1c1f5f4f9b9aa5afe03c6a7",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "banking-ios/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 10321.208,
            "cost": 0.001708,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "f1f4a0244fa48e7d6cbddadb",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "banking-ios/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 6226.777,
            "cost": 0.00171,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "bb5fbf1764dc2abe2597b5ff",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "flight-pass-ios/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 10023.742,
            "cost": 0.001706,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "f245091f154ec5db50e97992",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "flight-pass-ios/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 10540.43,
            "cost": 0.001712,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "a1c87fee91c6585e0d8d0214",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "smart-home-android/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8790.522,
            "cost": 0.001706,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "25c18e4bf34eb7cf5debe5ce",
            "model": "anthropic/claude-sonnet-5",
            "case_id": "smart-home-android/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8847.319,
            "cost": 0.001712,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          }
        ]
      },
      "operations": {
        "latency_p50_ms": 10247.324,
        "latency_p95_ms": 12048.0091,
        "mean_latency_ms": 9854.985999999999,
        "total_cost": 0.09278200000000002
      }
    },
    "openai/gpt-5.6-sol": {
      "transport_attempt_count": 24,
      "response_count": 24,
      "request_failure_count": 0,
      "layout_defect": {
        "transport_attempt_count": 12,
        "request_failure_count": 0,
        "metrics": {
          "balancedAccuracy": 0.9166666666666667,
          "recall": 0.8333333333333334,
          "specificity": 1,
          "falsePositiveRate": 0,
          "categoryAccuracy": 0.6666666666666666,
          "meanLocalizationIoU": 0.13597855676708906,
          "schemaValidRate": 0.9166666666666666
        },
        "attempts": [
          {
            "attempt_id": "7f1f1b58d15f3d8457cf94ef",
            "model": "openai/gpt-5.6-sol",
            "case_id": "commerce-catalog-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 26990.258,
            "cost": 0.0128825,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "d57234eb05a8495e4d166545",
            "model": "openai/gpt-5.6-sol",
            "case_id": "commerce-catalog-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 15883.207,
            "cost": 0.0183125,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.21339640230006862,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "1872a35c3f6e62c408bd4263",
            "model": "openai/gpt-5.6-sol",
            "case_id": "analytics-dashboard-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 8530.296,
            "cost": 0.0127625,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "a5623af528986deaadba7c5d",
            "model": "openai/gpt-5.6-sol",
            "case_id": "analytics-dashboard-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 12683.176,
            "cost": 0.0180125,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.16538528823397272,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "db0ef4151ec2f4d617f2c35f",
            "model": "openai/gpt-5.6-sol",
            "case_id": "iot-control-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 7260.095,
            "cost": 0.0127625,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "dd69b131aadc3ddc33c5e026",
            "model": "openai/gpt-5.6-sol",
            "case_id": "iot-control-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 9010.398,
            "cost": 0.0152525,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.07793617352919888,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "db14c2a3e48a43ac058545e9",
            "model": "openai/gpt-5.6-sol",
            "case_id": "banking-ios/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 8289.187,
            "cost": 0.00717,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "4d6a7c6c3adfc139854a4e8a",
            "model": "openai/gpt-5.6-sol",
            "case_id": "banking-ios/defect/layout-defect",
            "track": "layout-defect",
            "status": "invalid_response",
            "wall_time_ms": 16929.268,
            "cost": null,
            "schemaValid": false,
            "classificationCorrect": false,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": false,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": true
          },
          {
            "attempt_id": "0f89ca408a0e1d30b3d0db07",
            "model": "openai/gpt-5.6-sol",
            "case_id": "flight-pass-ios/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 7858.907,
            "cost": 0.00549,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "23dee18e03a0787a00d7136a",
            "model": "openai/gpt-5.6-sol",
            "case_id": "flight-pass-ios/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 10065.858,
            "cost": 0.00873,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.3591534765392941,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "b081865995a6042e60ea52e7",
            "model": "openai/gpt-5.6-sol",
            "case_id": "smart-home-android/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 8109.62,
            "cost": 0.00468,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "30cb4837a2e98e07ad5272b1",
            "model": "openai/gpt-5.6-sol",
            "case_id": "smart-home-android/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 11319.316,
            "cost": 0.01224,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          }
        ]
      },
      "element_presence": {
        "transport_attempt_count": 12,
        "request_failure_count": 0,
        "metrics": {
          "balancedAccuracy": 1,
          "presentRecall": 1,
          "absentSpecificity": 1,
          "falsePositiveRate": 0,
          "schemaValidRate": 1
        },
        "attempts": [
          {
            "attempt_id": "137cef6f524cc9ed9259773a",
            "model": "openai/gpt-5.6-sol",
            "case_id": "commerce-catalog-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7959.302,
            "cost": 0.010985,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "9c896fd99a14dcc3ab8d8f5c",
            "model": "openai/gpt-5.6-sol",
            "case_id": "commerce-catalog-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 9134.733,
            "cost": 0.01099125,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "7c60507ca04920d6c79df659",
            "model": "openai/gpt-5.6-sol",
            "case_id": "analytics-dashboard-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8530.849,
            "cost": 0.010985,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "411c7b7115a7035fde6474bf",
            "model": "openai/gpt-5.6-sol",
            "case_id": "analytics-dashboard-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 7123.589,
            "cost": 0.010985,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "b060361ecd6aa258ea4b9d0d",
            "model": "openai/gpt-5.6-sol",
            "case_id": "iot-control-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 5414.139,
            "cost": 0.010985,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "0dec76a5e4fb03bf07766769",
            "model": "openai/gpt-5.6-sol",
            "case_id": "iot-control-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8099.473,
            "cost": 0.010985,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "f5514620b351f99dfa073996",
            "model": "openai/gpt-5.6-sol",
            "case_id": "banking-ios/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 6423.032,
            "cost": 0.003145,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "4dc6e8a0048e81a3037eadbb",
            "model": "openai/gpt-5.6-sol",
            "case_id": "banking-ios/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 5694.539,
            "cost": 0.00315,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "d68fcfc3e5077385496e0445",
            "model": "openai/gpt-5.6-sol",
            "case_id": "flight-pass-ios/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8960.142,
            "cost": 0.00315,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "82ac7c6eba210fcd6277b923",
            "model": "openai/gpt-5.6-sol",
            "case_id": "flight-pass-ios/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 9159.443,
            "cost": 0.00315,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "b9c98c68c64ea8bc0404a2bc",
            "model": "openai/gpt-5.6-sol",
            "case_id": "smart-home-android/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8183.404,
            "cost": 0.00315,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "0b85112b02652bab0859b0e1",
            "model": "openai/gpt-5.6-sol",
            "case_id": "smart-home-android/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 8846.465,
            "cost": 0.003155,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          }
        ]
      },
      "operations": {
        "latency_p50_ms": 8530.296,
        "latency_p95_ms": 15563.203899999997,
        "mean_latency_ms": 9544.757739130435,
        "total_cost": 0.21311124999999995
      }
    },
    "google/gemini-3.1-pro-preview": {
      "transport_attempt_count": 24,
      "response_count": 24,
      "request_failure_count": 0,
      "layout_defect": {
        "transport_attempt_count": 12,
        "request_failure_count": 0,
        "metrics": {
          "balancedAccuracy": 0.9166666666666667,
          "recall": 1,
          "specificity": 0.8333333333333334,
          "falsePositiveRate": 0.16666666666666663,
          "categoryAccuracy": 0.6666666666666666,
          "meanLocalizationIoU": 0.1141406732420196,
          "schemaValidRate": 1
        },
        "attempts": [
          {
            "attempt_id": "dbb1224c6a8603010693b457",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "commerce-catalog-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 31207.038,
            "cost": 0.002896,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "82c16d3ab1cfd7c0abd8aef1",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "commerce-catalog-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 24132.01,
            "cost": 0.003184,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.21205210926928125,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "8c5577363deccef80939306f",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "analytics-dashboard-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 43125.249,
            "cost": 0.002764,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "f6fac02b56376c21363a7caa",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "analytics-dashboard-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 32339.94,
            "cost": 0.003184,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "3155a15cb6cffac17167af18",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "iot-control-desktop/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 22268.843,
            "cost": 0.00274,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "ff3ace4c36db5b4fe0cb24a7",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "iot-control-desktop/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 37136.277,
            "cost": 0.003232,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.07710106711068371,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "96f93dadbc257bb929e52f38",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "banking-ios/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 11053.616,
            "cost": 0.003072,
            "schemaValid": true,
            "classificationCorrect": false,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": false,
            "falsePositive": true,
            "falseNegative": false
          },
          {
            "attempt_id": "4cc51f2bb24aa42571e6d1d6",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "banking-ios/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 9759.045,
            "cost": 0.003204,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.2321704154885678,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "e699b175f65bf04d4cf0c215",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "flight-pass-ios/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 10479.734,
            "cost": 0.002724,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "3502e9ec3615d01afa2cd779",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "flight-pass-ios/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 17761.134,
            "cost": 0.003336,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": false,
            "localizationIoU": 0,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "c900e421a6e69566375c9a00",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "smart-home-android/clean/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 11714.36,
            "cost": 0.002844,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": null,
            "localizationIoU": null,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "36c734f69993d86c86059751",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "smart-home-android/defect/layout-defect",
            "track": "layout-defect",
            "status": "success",
            "wall_time_ms": 10053.838,
            "cost": 0.00336,
            "schemaValid": true,
            "classificationCorrect": true,
            "categoryCorrect": true,
            "localizationIoU": 0.1635204475835848,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          }
        ]
      },
      "element_presence": {
        "transport_attempt_count": 12,
        "request_failure_count": 0,
        "metrics": {
          "balancedAccuracy": 0.9166666666666667,
          "presentRecall": 1,
          "absentSpecificity": 0.8333333333333334,
          "falsePositiveRate": 0.16666666666666663,
          "schemaValidRate": 1
        },
        "attempts": [
          {
            "attempt_id": "a6d412a000fb970857a79da1",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "commerce-catalog-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 10763.305,
            "cost": 0.002374,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "4ace901303e1cc179815deef",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "commerce-catalog-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 39191.65,
            "cost": 0.002376,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "a7c02fc1673383aaab7c549e",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "analytics-dashboard-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 10793.531,
            "cost": 0.002374,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "15c41bc62cf07ec55e0e0352",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "analytics-dashboard-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 9867.611,
            "cost": 0.002374,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "3ba9d221cf164beb95f73990",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "iot-control-desktop/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 26308.922,
            "cost": 0.002374,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "61ffc71ea0f4e80b16dd35ad",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "iot-control-desktop/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 12431.461,
            "cost": 0.002374,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "ff68133ff277ff9119fae86f",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "banking-ios/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 10084.288,
            "cost": 0.002344,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "dd128840d10536cc41637fe3",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "banking-ios/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 12430.502,
            "cost": 0.002346,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "8857bd4723e61d08a11d4f81",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "flight-pass-ios/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 9940.935,
            "cost": 0.002346,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "61ad6193bcc7842cbb71bdf4",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "flight-pass-ios/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 10303.591,
            "cost": 0.002346,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": false,
            "predictedFound": false,
            "truePositive": false,
            "trueNegative": true,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "f61c77980ceda559784f8320",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "smart-home-android/clean/element-presence/present",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 15902.815,
            "cost": 0.002346,
            "schemaValid": true,
            "classificationCorrect": true,
            "expectedFound": true,
            "predictedFound": true,
            "truePositive": true,
            "trueNegative": false,
            "falsePositive": false,
            "falseNegative": false
          },
          {
            "attempt_id": "74e913ac5ed35220b7eb5115",
            "model": "google/gemini-3.1-pro-preview",
            "case_id": "smart-home-android/clean/element-presence/absent",
            "track": "element-presence",
            "status": "success",
            "wall_time_ms": 12132.225,
            "cost": 0.002348,
            "schemaValid": true,
            "classificationCorrect": false,
            "expectedFound": false,
            "predictedFound": true,
            "truePositive": false,
            "trueNegative": false,
            "falsePositive": true,
            "falseNegative": false
          }
        ]
      },
      "operations": {
        "latency_p50_ms": 12281.3635,
        "latency_p95_ms": 38883.34405,
        "mean_latency_ms": 18382.579999999998,
        "total_cost": 0.06486199999999999
      }
    }
  }
}
