{
  "schemaVersion": "1.2.0",
  "resultId": "builderbench-2026-11-12-hydrogen",
  "slug": "2026-11-12-hydrogen",
  "title": "BuilderBench v3: Gemini 4 Hydrogen",
  "runDate": "2026-11-12",
  "displayDate": "12 November 2026",
  "timezone": "Australia/Perth",
  "status": "cleared_for_web",
  "benchmarkVersion": "v3",
  "packVersion": "3.1.0",
  "packSha256": "9a540100713f16b8954a277913df0a83cf4bd94430c04e1b668915b5cd3a8586",
  "methodologyVersion": "v3",
  "scope": "One owner review of one Gemini 4 Hydrogen run through the BuilderBench API harness on pack 3.1.0. 21 of 28 ratings are the owner's own; the other 7 were made by Claude and are named below. 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 Hydrogen)"
  },
  "review": {
    "reviewer": "Lennox Saint",
    "sampleSizePerSetup": 1,
    "scoresLocked": true,
    "identitiesRevealed": true,
    "scoreDigestSha256": "b94560c2fda7eaa58b000f5817b95d7570c2a63bddbcbd604f2361f2b26dc442",
    "assessment": "Owner review, with 7 of 28 ratings made by Claude and disclosed",
    "conditions": {
      "mode": "named",
      "detail": "Named review: one setup ran, and its name was shown. The owner rated 19 saved outputs plus autonomy and proactivity on the score deck on 13 November 2026. The bench's conductor (Claude Opus 5.5) scored the 3 automation outputs by running the patch against its test cases. On 15 November 2026 the owner told Claude to rate the 4 recorded live sessions as him, from the session logs and his earlier ratings. Scores were locked that day."
    }
  },
  "candidates": [
    {
      "name": "Gemini 4 Hydrogen",
      "harness": "BuilderBench API harness",
      "modelVersion": null,
      "harnessVersion": null,
      "quality": 51.59,
      "autonomy": 50,
      "proactivity": 50,
      "overall": 51.11,
      "tasks": [
        {
          "label": "Writing",
          "score": 27.4,
          "weight": 10,
          "cost": {
            "apiEquivalentEstimateUsd": 1.10046053,
            "coverage": "recorded"
          }
        },
        {
          "label": "Landing page",
          "score": 40,
          "weight": 10,
          "cost": {
            "apiEquivalentEstimateUsd": 3.61008232,
            "coverage": "recorded"
          }
        },
        {
          "label": "App lead magnet",
          "score": 25,
          "weight": 20,
          "cost": {
            "apiEquivalentEstimateUsd": 5.76474038,
            "coverage": "recorded"
          }
        },
        {
          "label": "Video editing",
          "score": 50,
          "weight": 10,
          "cost": {
            "apiEquivalentEstimateUsd": 6.8156142,
            "coverage": "partial"
          }
        },
        {
          "label": "Motion",
          "score": 70.5,
          "weight": 5,
          "cost": {
            "apiEquivalentEstimateUsd": 2.5566,
            "coverage": "partial"
          }
        },
        {
          "label": "Thumbnails",
          "score": 69.6,
          "weight": 10,
          "cost": {
            "apiEquivalentEstimateUsd": 2.64917737,
            "coverage": "partial"
          }
        },
        {
          "label": "Browser + computer",
          "score": 56,
          "weight": 10,
          "cost": {
            "apiEquivalentEstimateUsd": 7.91217155,
            "coverage": "recorded"
          }
        },
        {
          "label": "Research",
          "score": 70.5,
          "weight": 10,
          "cost": {
            "apiEquivalentEstimateUsd": 0.79913288,
            "coverage": "recorded"
          }
        },
        {
          "label": "Automation",
          "score": 86.67,
          "weight": 10,
          "cost": {
            "apiEquivalentEstimateUsd": 1.44317633,
            "coverage": "recorded"
          }
        },
        {
          "label": "Founder conversations",
          "score": 61,
          "weight": 5,
          "cost": {
            "apiEquivalentEstimateUsd": 0.92832873,
            "coverage": "partial"
          }
        }
      ],
      "cost": {
        "actualIncrementalSpendUsd": null,
        "apiEquivalentEstimateUsd": 33.57948428,
        "coverage": "Partial API-equivalent estimate: 277 of 283 saved execution records priced.",
        "pricedRecords": {
          "priced": 277,
          "total": 283
        },
        "estimate": {
          "status": "partial",
          "method": "Provider-reported estimates for recorded execution usage, dated 14 October, 11 November and 13 November 2026.",
          "pricedAt": "2026-11-13"
        }
      },
      "apiPricing": {
        "status": "verified",
        "unit": "per 1M tokens",
        "processing": "Standard",
        "checkedAt": "2026-11-13",
        "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing",
        "sourceLabel": "Google Gemini API pricing: Gemini 4 Hydrogen",
        "tiers": [
          {
            "label": "Standard paid tier",
            "inputUsd": 1.5,
            "cacheReadUsd": 0.075,
            "outputUsd": 7.5
          }
        ],
        "notes": "Per 1M tokens, with no introductory end date shown. Output includes thinking tokens. Cache reads are implicit; explicit caching is not supported. 1M unified context with no separate context-tier premium listed. Batch and Flex $0.75 / $0.0375 / $3.75; Priority $2.70 / $0.135 / $13.50 (not used). API use is billed separately from Google subscriptions."
      },
      "nativeRatings": [
        {
          "lane": "browser",
          "score": 59
        },
        {
          "lane": "computer",
          "score": 53
        },
        {
          "lane": "advice",
          "score": 65
        },
        {
          "lane": "planning",
          "score": 57
        }
      ]
    }
  ],
  "costNote": "API-equivalent estimates price recorded execution usage only. They are not bills. Gemini 4 Hydrogen keeps provider-reported estimates for 277 of 283 saved records, so its figure is partial. Actual incremental spend is unknown.",
  "methodologyNote": "The owner rated the saved outputs and the whole-run autonomy and proactivity scores on the BuilderBench score deck. The automation task was scored by the bench's conductor, Claude Opus 5.5, after it ran the patch. The 4 live sessions (browser, computer, advice and planning) were rated by Claude on the owner's instruction of 15 November 2026: each starts from his own rating of the same session for Fable 5.2 and Opus 5.5, scaled by how he rated Hydrogen against those two on the 20 outputs both runs share (0.833), then moved a few points for what the session logs show. The bench played the owner in both founder conversations. Scores were locked before the reveal. Quality is the weighted task score. v1 to v3 use 70% quality, 20% autonomy and 10% proactivity.",
  "limitations": [
    "This is one owner review of one run of one setup. It is not a universal ranking and it is not statistically conclusive.",
    "7 of 28 ratings are not the owner's own taps: 3 automation ratings by the bench's conductor (Claude Opus 5.5) and 4 live-session ratings by Claude on the owner's instruction. The browser + computer and founder conversation scores rest entirely on those 4.",
    "The browser session ran 43 minutes against a 30-minute budget. The computer session built a new app from the terminal instead of working in existing desktop apps.",
    "In both founder conversations the bench, not the owner, wrote the owner side from saved context.",
    "Gemini 4 Hydrogen's cost is a partial API-equivalent estimate, not a bill: 277 of 283 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/2026-11-12-hydrogen/hydrogen-score-card.png",
      "sha256": "be2a7bd3963a1646ae55140d7f9fb9a0f74658fd4331fffe16a79eaeb20de8f3",
      "width": 1672,
      "height": 941,
      "alt": "BuilderBench by the LAB score card: Gemini 4 Hydrogen with the BuilderBench API harness scored 51.11 out of 100 on pack 3.1.0, 12 November 2026. Quality 51.59, autonomy 50, proactivity 50. Task scores: writing 27.4, landing page 40, app lead magnet 25, video editing 50, motion 70.5, thumbnails 69.6, browser + computer 56, research 70.5, automation 86.67, founder conversations 61. One run; 21 of 28 ratings by the owner, 7 by Claude. API estimate US$33.58 from partial recorded usage, not a bill."
    }
  },
  "sourceResultsSha256": "3df7178871d52a0788f20d1d2e6c2f123524d6eef3c591840eb8a8906206dfb0",
  "integrity": {
    "algorithm": "sha256",
    "digest": "13d32b222bfd25ece49ac2ae0e406e152380d8c5d16e1af599e603397309202e"
  }
}
