{
  "schemaVersion": "1.2.0",
  "resultId": "builderbench-2026-11-11-carbon",
  "slug": "2026-11-11-carbon",
  "title": "BuilderBench v3: Gemini 4 Carbon",
  "runDate": "2026-11-11",
  "displayDate": "11 November 2026",
  "timezone": "Australia/Perth",
  "status": "cleared_for_web",
  "benchmarkVersion": "v3",
  "packVersion": "3.1.0",
  "packSha256": "9a540100713f16b8954a277913df0a83cf4bd94430c04e1b668915b5cd3a8586",
  "methodologyVersion": "v3",
  "scope": "One owner-finalized partial personal assessment of one Gemini 4 Carbon run through the BuilderBench API harness on pack 3.1.0. This is not a universal model ranking or a statistical claim.",
  "durationSeconds": 14400,
  "scoringWeights": {
    "quality": 70,
    "autonomy": 20,
    "proactivity": 10
  },
  "settings": {
    "reasoning": "Extra High (xhigh)",
    "speed": "Standard",
    "billing": "The paid Gemini API (Gemini 4 Carbon)"
  },
  "review": {
    "reviewer": "Lennox Saint",
    "sampleSizePerSetup": 1,
    "scoresLocked": true,
    "identitiesRevealed": true,
    "scoreDigestSha256": "f325658ad3f3b572df0aca55c3d1f47bd7712848207f19dbb437217466a90a0b",
    "assessment": "Owner-finalized partial personal assessment",
    "conditions": {
      "mode": "named",
      "detail": "Named review: one setup ran, and its name was shown. The owner locked the scores in the review deck on 12 November 2026 as a partial personal assessment. Unfinished tasks were listed on the lock screen and stay disclosed."
    }
  },
  "candidates": [
    {
      "name": "Gemini 4 Carbon",
      "harness": "BuilderBench API harness",
      "modelVersion": null,
      "harnessVersion": null,
      "quality": 49.48,
      "autonomy": 48,
      "proactivity": 48,
      "overall": 49.04,
      "tasks": [
        {
          "label": "Writing",
          "score": 37.4,
          "weight": 10,
          "cost": {
            "apiEquivalentEstimateUsd": 0.681275,
            "coverage": "partial"
          }
        },
        {
          "label": "Landing page",
          "score": 38,
          "weight": 10,
          "cost": {
            "apiEquivalentEstimateUsd": 4.3208122,
            "coverage": "recorded"
          }
        },
        {
          "label": "App lead magnet",
          "score": 49,
          "weight": 20,
          "cost": {
            "apiEquivalentEstimateUsd": 4.923198,
            "coverage": "partial"
          }
        },
        {
          "label": "Video editing",
          "score": 36.33,
          "weight": 10,
          "cost": {
            "apiEquivalentEstimateUsd": 10.443599,
            "coverage": "partial"
          }
        },
        {
          "label": "Motion",
          "score": 48.5,
          "weight": 5,
          "cost": {
            "apiEquivalentEstimateUsd": 3.6951713,
            "coverage": "partial"
          }
        },
        {
          "label": "Thumbnails",
          "score": 44.6,
          "weight": 10,
          "cost": {
            "apiEquivalentEstimateUsd": 2.405599,
            "coverage": "partial"
          }
        },
        {
          "label": "Browser + computer",
          "score": 40,
          "weight": 10,
          "cost": {
            "apiEquivalentEstimateUsd": 4.38783105,
            "coverage": "partial"
          }
        },
        {
          "label": "Research",
          "score": 69.5,
          "weight": 10,
          "cost": {
            "apiEquivalentEstimateUsd": 1.2090384,
            "coverage": "recorded"
          }
        },
        {
          "label": "Automation",
          "score": 76,
          "weight": 10,
          "cost": {
            "apiEquivalentEstimateUsd": 1.7896868,
            "coverage": "recorded"
          }
        },
        {
          "label": "Founder conversations",
          "score": 61.5,
          "weight": 5,
          "cost": {
            "apiEquivalentEstimateUsd": 0.9345646,
            "coverage": "recorded"
          }
        }
      ],
      "cost": {
        "actualIncrementalSpendUsd": null,
        "apiEquivalentEstimateUsd": 34.79077535,
        "coverage": "Partial API-equivalent estimate: 112 of 123 saved execution records priced from provider-reported estimates. Unpriced records are not included.",
        "pricedRecords": {
          "priced": 112,
          "total": 123
        },
        "estimate": {
          "status": "partial",
          "method": "Provider-reported estimates for recorded execution usage, dated 14 October and 11 November 2026.",
          "pricedAt": "2026-11-11"
        }
      },
      "apiPricing": {
        "status": "verified",
        "unit": "per 1M tokens",
        "processing": "Standard",
        "checkedAt": "2026-11-11",
        "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing",
        "sourceLabel": "Google Gemini API pricing: Gemini 4 Carbon",
        "tiers": [
          {
            "label": "Introductory, through 30 Nov 2026",
            "inputUsd": 2,
            "cacheReadUsd": 0.1,
            "outputUsd": 10
          }
        ],
        "notes": "From 1 December 2026: $4.00 input, $0.20 cache read and $20.00 output. Output includes thinking tokens. Cache reads are implicit; explicit cache writes are unsupported. 1M unified context with no separate context-tier premium listed. Not available on the free tier. API use is billed separately from Google subscriptions."
      },
      "nativeRatings": [
        {
          "lane": "browser",
          "score": 30
        },
        {
          "lane": "computer",
          "score": 50
        },
        {
          "lane": "advice",
          "score": 77
        },
        {
          "lane": "planning",
          "score": 46
        }
      ]
    }
  ],
  "costNote": "API-equivalent estimates price recorded execution usage only. They are not bills. Gemini 4 Carbon keeps provider-reported estimates for 112 of 123 saved records, so its figure is partial. Actual incremental spend is unknown.",
  "methodologyNote": "The ratings saved in the review deck were finalized by the owner as a partial personal assessment and locked on 12 November 2026. Quality is the weighted task score. v1 to v3 use 70% quality, 20% autonomy and 10% proactivity.",
  "limitations": [
    "This is one owner-finalized partial personal assessment of one run of one setup. It is not a universal ranking and it is not statistically conclusive.",
    "Finalized ratings do not mean every task or recording passed verification. The original execution and its evidence are incomplete.",
    "The runner failed and execution did not complete normally. Completed work was kept for partial review.",
    "The run hit Google timeouts and per-task deadlines, so some revisions and deliverables are missing. Missing work is not scored as zero; the owner scored what was delivered.",
    "Gemini 4 Carbon's cost is a partial API-equivalent estimate, not a bill: 112 of 123 saved records are priced. Actual incremental spend is unknown.",
    "The score belongs to the full setup: model, harness, tools and settings.",
    "Pack 3.1.0 scores compare only with other pack 3.1.0 results.",
    "The build window was four hours.",
    "The picture on this page is a plain score card drawn from the published numbers. The run's own result graphic has not been made yet."
  ],
  "assets": {
    "resultGraphic": {
      "src": "/builderbench/2026-11-11-carbon/carbon-score-card.png",
      "sha256": "095c1bc364eff3284832a38da432a4bb17f58d35bad4d742aa9b056316e67561",
      "width": 1672,
      "height": 941,
      "alt": "BuilderBench by the LAB score card: Gemini 4 Carbon with the BuilderBench API harness scored 49.04 out of 100 on pack 3.1.0, 11 November 2026. Quality 49.48, autonomy 48, proactivity 48. Task scores: writing 37.4, landing page 38, app lead magnet 49, video editing 36.33, motion 48.5, thumbnails 44.6, browser + computer 40, research 69.5, automation 76, founder conversations 61.5. Owner-finalized partial personal assessment of one run. API estimate US$34.79 from partial recorded usage, not a bill."
    }
  },
  "sourceResultsSha256": "efcd814fa0b99553deb469816e053178ca7d78b222fb43b9c9e66aa3216e38b4",
  "integrity": {
    "algorithm": "sha256",
    "digest": "be34ce98f7ac8e2991d630ba86f03d9dbf5fe91c56d3126288951031bb6ba2aa"
  }
}
