{
  "generatedAt": "2026-07-10T08:40:13.648Z",
  "completedResults": 52,
  "passedResults": 52,
  "reviewedRuns": 52,
  "tasksCovered": 7,
  "plannedTasks": 29,
  "modelsCovered": 6,
  "modes": [
    "compact-pack",
    "no-cache",
    "raw-record"
  ],
  "completeTriples": 7,
  "evidenceVerdict": "partially reviewed evidence — coverage still thin",
  "modeStats": [
    {
      "mode": "no-cache",
      "runs": 17,
      "medianTokens": 1335,
      "meanTokens": 1762,
      "medianRubric": 3,
      "meanRubric": 3.01,
      "medianIterations": 1,
      "rubricDimensions": {
        "constraintAdherence": {
          "n": 17,
          "median": 3,
          "mean": 3.06
        },
        "contextEfficiency": {
          "n": 17,
          "median": 3,
          "mean": 3
        },
        "decisionQuality": {
          "n": 17,
          "median": 3,
          "mean": 3
        },
        "implementationQuality": {
          "n": 17,
          "median": 3,
          "mean": 3
        }
      }
    },
    {
      "mode": "raw-record",
      "runs": 17,
      "medianTokens": 3795,
      "meanTokens": 5810,
      "medianRubric": 3,
      "meanRubric": 3.03,
      "medianIterations": 1,
      "rubricDimensions": {
        "constraintAdherence": {
          "n": 17,
          "median": 3,
          "mean": 3.06
        },
        "contextEfficiency": {
          "n": 17,
          "median": 3,
          "mean": 2.94
        },
        "decisionQuality": {
          "n": 17,
          "median": 3,
          "mean": 3.06
        },
        "implementationQuality": {
          "n": 17,
          "median": 3,
          "mean": 3.06
        }
      }
    },
    {
      "mode": "compact-pack",
      "runs": 18,
      "medianTokens": 2570.5,
      "meanTokens": 2612,
      "medianRubric": 3.25,
      "meanRubric": 3.43,
      "medianIterations": 1,
      "rubricDimensions": {
        "constraintAdherence": {
          "n": 18,
          "median": 3,
          "mean": 3.28
        },
        "contextEfficiency": {
          "n": 18,
          "median": 4,
          "mean": 4.06
        },
        "decisionQuality": {
          "n": 18,
          "median": 3,
          "mean": 3.22
        },
        "implementationQuality": {
          "n": 18,
          "median": 3,
          "mean": 3.17
        }
      }
    }
  ],
  "modelStats": [
    {
      "model": "ollama-cloud/kimi-k2.7-code",
      "runs": 5,
      "tasks": 3,
      "modes": [
        "compact-pack",
        "no-cache",
        "raw-record"
      ],
      "medianTokens": 6000
    },
    {
      "model": "openai/gpt-4o-mini",
      "runs": 15,
      "tasks": 5,
      "modes": [
        "compact-pack",
        "no-cache",
        "raw-record"
      ],
      "medianTokens": 893
    },
    {
      "model": "openrouter/google/gemma-4-31b-it:free",
      "runs": 12,
      "tasks": 4,
      "modes": [
        "compact-pack",
        "no-cache",
        "raw-record"
      ],
      "medianTokens": 2109.5
    },
    {
      "model": "openrouter/nvidia/nemotron-3-super-120b-a12b:free",
      "runs": 9,
      "tasks": 3,
      "modes": [
        "compact-pack",
        "no-cache",
        "raw-record"
      ],
      "medianTokens": 2806
    },
    {
      "model": "openrouter/openai/gpt-oss-120b:free",
      "runs": 8,
      "tasks": 3,
      "modes": [
        "compact-pack",
        "no-cache",
        "raw-record"
      ],
      "medianTokens": 3255.5
    },
    {
      "model": "openrouter/openai/gpt-oss-20b:free",
      "runs": 3,
      "tasks": 1,
      "modes": [
        "compact-pack",
        "no-cache",
        "raw-record"
      ],
      "medianTokens": 2776
    }
  ]
}