{
  "generatedAt": "2026-06-12T12:03:16.950Z",
  "redaction": {
    "isRedacted": true,
    "reason": "This public artifact is aggregated from private historical like.photo Studio replay data. Product images, generated images, prompts, product identities, per-battle rows, and raw judge outputs are intentionally withheld.",
    "hiddenFields": [
      "product images",
      "generated candidate images",
      "generation prompts",
      "product identities",
      "per-battle rows",
      "raw judge outputs"
    ]
  },
  "sample": {
    "productCount": 50,
    "taskCount": 50,
    "taskTypes": [
      "infographic (27)",
      "lifestyle (23)"
    ],
    "source": "private historical like.photo Studio replay batch",
    "baselineModel": "nano-banana-2",
    "challengerModel": "gpt-image-2"
  },
  "agreement": {
    "observedAgreement": 0.9230769230769231,
    "fleissKappa": null,
    "unanimousBattles": 18,
    "totalBattles": 39,
    "ratersPerBattle": 4.6,
    "note": "36/39 quorum stable pairs reached a strict eligible-judge majority; 3 tied or withheld"
  },
  "suite": {
    "id": "private-replay-nano-banana-2-vs-gpt-image-2",
    "version": "20260531-batch50",
    "title": "Private Replay: Nano Banana 2 vs GPT Image 2",
    "description": "Redacted aggregate benchmark from 50 historical like.photo Studio replay tasks. Results compare frozen nano-banana-2 generations against regenerated gpt-image-2 challengers using the same replay prompt and reference-image inputs.",
    "battlePolicy": "round-robin-same-task-with-swaps-v1"
  },
  "products": [
    {
      "id": "private-replay-01",
      "name": "Private replay product 01",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-02",
      "name": "Private replay product 02",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-03",
      "name": "Private replay product 03",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-04",
      "name": "Private replay product 04",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-05",
      "name": "Private replay product 05",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-06",
      "name": "Private replay product 06",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-07",
      "name": "Private replay product 07",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-08",
      "name": "Private replay product 08",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-09",
      "name": "Private replay product 09",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-10",
      "name": "Private replay product 10",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-11",
      "name": "Private replay product 11",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-12",
      "name": "Private replay product 12",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-13",
      "name": "Private replay product 13",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-14",
      "name": "Private replay product 14",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-15",
      "name": "Private replay product 15",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-16",
      "name": "Private replay product 16",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-17",
      "name": "Private replay product 17",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-18",
      "name": "Private replay product 18",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-19",
      "name": "Private replay product 19",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-20",
      "name": "Private replay product 20",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-21",
      "name": "Private replay product 21",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-22",
      "name": "Private replay product 22",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-23",
      "name": "Private replay product 23",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-24",
      "name": "Private replay product 24",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-25",
      "name": "Private replay product 25",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-26",
      "name": "Private replay product 26",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-27",
      "name": "Private replay product 27",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-28",
      "name": "Private replay product 28",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-29",
      "name": "Private replay product 29",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-30",
      "name": "Private replay product 30",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-31",
      "name": "Private replay product 31",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-32",
      "name": "Private replay product 32",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-33",
      "name": "Private replay product 33",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-34",
      "name": "Private replay product 34",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-35",
      "name": "Private replay product 35",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-36",
      "name": "Private replay product 36",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-37",
      "name": "Private replay product 37",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-38",
      "name": "Private replay product 38",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-39",
      "name": "Private replay product 39",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-40",
      "name": "Private replay product 40",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-41",
      "name": "Private replay product 41",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-42",
      "name": "Private replay product 42",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-43",
      "name": "Private replay product 43",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-44",
      "name": "Private replay product 44",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-45",
      "name": "Private replay product 45",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-46",
      "name": "Private replay product 46",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-47",
      "name": "Private replay product 47",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-48",
      "name": "Private replay product 48",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-49",
      "name": "Private replay product 49",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    },
    {
      "id": "private-replay-50",
      "name": "Private replay product 50",
      "referenceImages": [],
      "criticalAttributes": [],
      "candidates": []
    }
  ],
  "battleCount": 100,
  "judgeRuns": [
    {
      "judgeId": "anthropic_claude-fable-5_v2",
      "judgeModel": "anthropic/claude-fable-5",
      "judgePromptVersion": "pairwise-product-v2-multiaxis",
      "judgmentCount": 100,
      "totalCostCents": 1338,
      "meanLatencyMs": 9190,
      "flipConsistency": 0.82,
      "positionBRate": 0.45,
      "positionBiasFlagged": false,
      "biasReason": "stable-pair filter used; 41/50 swap-consistent pairs, 9 pairs withheld from stable judge ranking",
      "consensusEligible": true,
      "ranking": [
        {
          "generator": "gpt-image-2",
          "wins": 25,
          "losses": 16,
          "battles": 41,
          "winRate": 0.6097560975609756,
          "strength": 1.2195121951219512,
          "btScore": 39
        },
        {
          "generator": "nano-banana-2",
          "wins": 16,
          "losses": 25,
          "battles": 41,
          "winRate": 0.3902439024390244,
          "strength": 0.7804878048780488,
          "btScore": -39
        }
      ],
      "axisRankings": [
        {
          "axis": "productIdentity",
          "label": "Product identity",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 54,
              "losses": 46,
              "battles": 100,
              "winRate": 0.54,
              "strength": 1.08,
              "btScore": 14
            },
            {
              "generator": "nano-banana-2",
              "wins": 46,
              "losses": 54,
              "battles": 100,
              "winRate": 0.46,
              "strength": 0.92,
              "btScore": -14
            }
          ]
        },
        {
          "axis": "taskFit",
          "label": "Task fit",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 62,
              "losses": 38,
              "battles": 100,
              "winRate": 0.62,
              "strength": 1.24,
              "btScore": 43
            },
            {
              "generator": "nano-banana-2",
              "wins": 38,
              "losses": 62,
              "battles": 100,
              "winRate": 0.38,
              "strength": 0.76,
              "btScore": -43
            }
          ]
        },
        {
          "axis": "commercialPreference",
          "label": "Commercial preference",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 56,
              "losses": 44,
              "battles": 100,
              "winRate": 0.56,
              "strength": 1.12,
              "btScore": 21
            },
            {
              "generator": "nano-banana-2",
              "wins": 44,
              "losses": 56,
              "battles": 100,
              "winRate": 0.44,
              "strength": 0.88,
              "btScore": -21
            }
          ]
        },
        {
          "axis": "overall",
          "label": "Overall",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 59,
              "losses": 41,
              "battles": 100,
              "winRate": 0.59,
              "strength": 1.18,
              "btScore": 32
            },
            {
              "generator": "nano-banana-2",
              "wins": 41,
              "losses": 59,
              "battles": 100,
              "winRate": 0.41,
              "strength": 0.82,
              "btScore": -32
            }
          ]
        }
      ],
      "stableAxisRankings": [
        {
          "axis": "productIdentity",
          "label": "Product identity",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 24,
              "losses": 20,
              "battles": 44,
              "winRate": 0.5454545454545454,
              "strength": 1.0909090909090908,
              "btScore": 16
            },
            {
              "generator": "nano-banana-2",
              "wins": 20,
              "losses": 24,
              "battles": 44,
              "winRate": 0.45454545454545453,
              "strength": 0.9090909090909091,
              "btScore": -16
            }
          ]
        },
        {
          "axis": "taskFit",
          "label": "Task fit",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 27,
              "losses": 15,
              "battles": 42,
              "winRate": 0.6428571428571429,
              "strength": 1.2857142857142858,
              "btScore": 51
            },
            {
              "generator": "nano-banana-2",
              "wins": 15,
              "losses": 27,
              "battles": 42,
              "winRate": 0.35714285714285715,
              "strength": 0.7142857142857143,
              "btScore": -51
            }
          ]
        },
        {
          "axis": "commercialPreference",
          "label": "Commercial preference",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 23,
              "losses": 17,
              "battles": 40,
              "winRate": 0.575,
              "strength": 1.15,
              "btScore": 26
            },
            {
              "generator": "nano-banana-2",
              "wins": 17,
              "losses": 23,
              "battles": 40,
              "winRate": 0.425,
              "strength": 0.85,
              "btScore": -26
            }
          ]
        },
        {
          "axis": "overall",
          "label": "Overall",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 25,
              "losses": 16,
              "battles": 41,
              "winRate": 0.6097560975609756,
              "strength": 1.2195121951219512,
              "btScore": 39
            },
            {
              "generator": "nano-banana-2",
              "wins": 16,
              "losses": 25,
              "battles": 41,
              "winRate": 0.3902439024390244,
              "strength": 0.7804878048780488,
              "btScore": -39
            }
          ]
        }
      ]
    },
    {
      "judgeId": "google_gemini-3.5-flash_v2",
      "judgeModel": "google/gemini-3.5-flash",
      "judgePromptVersion": "pairwise-product-v2-multiaxis",
      "judgmentCount": 100,
      "totalCostCents": 200,
      "meanLatencyMs": 8532,
      "flipConsistency": 0.7,
      "positionBRate": 0.41,
      "positionBiasFlagged": false,
      "biasReason": "stable-pair filter used; 35/50 swap-consistent pairs, 15 pairs withheld from stable judge ranking",
      "consensusEligible": true,
      "ranking": [
        {
          "generator": "gpt-image-2",
          "wins": 25,
          "losses": 10,
          "battles": 35,
          "winRate": 0.7142857142857143,
          "strength": 1.4285714285714286,
          "btScore": 80
        },
        {
          "generator": "nano-banana-2",
          "wins": 10,
          "losses": 25,
          "battles": 35,
          "winRate": 0.2857142857142857,
          "strength": 0.5714285714285714,
          "btScore": -80
        }
      ],
      "axisRankings": [
        {
          "axis": "productIdentity",
          "label": "Product identity",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 64,
              "losses": 36,
              "battles": 100,
              "winRate": 0.64,
              "strength": 1.28,
              "btScore": 50
            },
            {
              "generator": "nano-banana-2",
              "wins": 36,
              "losses": 64,
              "battles": 100,
              "winRate": 0.36,
              "strength": 0.72,
              "btScore": -50
            }
          ]
        },
        {
          "axis": "taskFit",
          "label": "Task fit",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 68,
              "losses": 32,
              "battles": 100,
              "winRate": 0.68,
              "strength": 1.36,
              "btScore": 65
            },
            {
              "generator": "nano-banana-2",
              "wins": 32,
              "losses": 68,
              "battles": 100,
              "winRate": 0.32,
              "strength": 0.64,
              "btScore": -65
            }
          ]
        },
        {
          "axis": "commercialPreference",
          "label": "Commercial preference",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 65,
              "losses": 35,
              "battles": 100,
              "winRate": 0.65,
              "strength": 1.3,
              "btScore": 54
            },
            {
              "generator": "nano-banana-2",
              "wins": 35,
              "losses": 65,
              "battles": 100,
              "winRate": 0.35,
              "strength": 0.7,
              "btScore": -54
            }
          ]
        },
        {
          "axis": "overall",
          "label": "Overall",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 65,
              "losses": 35,
              "battles": 100,
              "winRate": 0.65,
              "strength": 1.3,
              "btScore": 54
            },
            {
              "generator": "nano-banana-2",
              "wins": 35,
              "losses": 65,
              "battles": 100,
              "winRate": 0.35,
              "strength": 0.7,
              "btScore": -54
            }
          ]
        }
      ],
      "stableAxisRankings": [
        {
          "axis": "productIdentity",
          "label": "Product identity",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 23,
              "losses": 9,
              "battles": 32,
              "winRate": 0.71875,
              "strength": 1.4375,
              "btScore": 81
            },
            {
              "generator": "nano-banana-2",
              "wins": 9,
              "losses": 23,
              "battles": 32,
              "winRate": 0.28125,
              "strength": 0.5625,
              "btScore": -81
            }
          ]
        },
        {
          "axis": "taskFit",
          "label": "Task fit",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 26,
              "losses": 8,
              "battles": 34,
              "winRate": 0.7647058823529411,
              "strength": 1.5294117647058822,
              "btScore": 102
            },
            {
              "generator": "nano-banana-2",
              "wins": 8,
              "losses": 26,
              "battles": 34,
              "winRate": 0.23529411764705882,
              "strength": 0.47058823529411764,
              "btScore": -102
            }
          ]
        },
        {
          "axis": "commercialPreference",
          "label": "Commercial preference",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 25,
              "losses": 10,
              "battles": 35,
              "winRate": 0.7142857142857143,
              "strength": 1.4285714285714286,
              "btScore": 80
            },
            {
              "generator": "nano-banana-2",
              "wins": 10,
              "losses": 25,
              "battles": 35,
              "winRate": 0.2857142857142857,
              "strength": 0.5714285714285714,
              "btScore": -80
            }
          ]
        },
        {
          "axis": "overall",
          "label": "Overall",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 25,
              "losses": 10,
              "battles": 35,
              "winRate": 0.7142857142857143,
              "strength": 1.4285714285714286,
              "btScore": 80
            },
            {
              "generator": "nano-banana-2",
              "wins": 10,
              "losses": 25,
              "battles": 35,
              "winRate": 0.2857142857142857,
              "strength": 0.5714285714285714,
              "btScore": -80
            }
          ]
        }
      ]
    },
    {
      "judgeId": "minimax_minimax-m3_v2",
      "judgeModel": "minimax/minimax-m3",
      "judgePromptVersion": "pairwise-product-v2-multiaxis",
      "judgmentCount": 100,
      "totalCostCents": 104,
      "meanLatencyMs": 11262,
      "flipConsistency": 0.66,
      "positionBRate": 0.43,
      "positionBiasFlagged": false,
      "biasReason": "stable-pair filter used; 33/50 swap-consistent pairs, 17 pairs withheld from stable judge ranking",
      "consensusEligible": true,
      "ranking": [
        {
          "generator": "gpt-image-2",
          "wins": 24,
          "losses": 9,
          "battles": 33,
          "winRate": 0.7272727272727273,
          "strength": 1.4545454545454546,
          "btScore": 85
        },
        {
          "generator": "nano-banana-2",
          "wins": 9,
          "losses": 24,
          "battles": 33,
          "winRate": 0.2727272727272727,
          "strength": 0.5454545454545454,
          "btScore": -85
        }
      ],
      "axisRankings": [
        {
          "axis": "productIdentity",
          "label": "Product identity",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 56,
              "losses": 44,
              "battles": 100,
              "winRate": 0.56,
              "strength": 1.12,
              "btScore": 21
            },
            {
              "generator": "nano-banana-2",
              "wins": 44,
              "losses": 56,
              "battles": 100,
              "winRate": 0.44,
              "strength": 0.88,
              "btScore": -21
            }
          ]
        },
        {
          "axis": "taskFit",
          "label": "Task fit",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 66,
              "losses": 34,
              "battles": 100,
              "winRate": 0.66,
              "strength": 1.32,
              "btScore": 58
            },
            {
              "generator": "nano-banana-2",
              "wins": 34,
              "losses": 66,
              "battles": 100,
              "winRate": 0.34,
              "strength": 0.68,
              "btScore": -58
            }
          ]
        },
        {
          "axis": "commercialPreference",
          "label": "Commercial preference",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 67,
              "losses": 33,
              "battles": 100,
              "winRate": 0.67,
              "strength": 1.34,
              "btScore": 62
            },
            {
              "generator": "nano-banana-2",
              "wins": 33,
              "losses": 67,
              "battles": 100,
              "winRate": 0.33,
              "strength": 0.66,
              "btScore": -62
            }
          ]
        },
        {
          "axis": "overall",
          "label": "Overall",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 65,
              "losses": 35,
              "battles": 100,
              "winRate": 0.65,
              "strength": 1.3,
              "btScore": 54
            },
            {
              "generator": "nano-banana-2",
              "wins": 35,
              "losses": 65,
              "battles": 100,
              "winRate": 0.35,
              "strength": 0.7,
              "btScore": -54
            }
          ]
        }
      ],
      "stableAxisRankings": [
        {
          "axis": "productIdentity",
          "label": "Product identity",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 19,
              "losses": 13,
              "battles": 32,
              "winRate": 0.59375,
              "strength": 1.1875,
              "btScore": 33
            },
            {
              "generator": "nano-banana-2",
              "wins": 13,
              "losses": 19,
              "battles": 32,
              "winRate": 0.40625,
              "strength": 0.8125,
              "btScore": -33
            }
          ]
        },
        {
          "axis": "taskFit",
          "label": "Task fit",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 22,
              "losses": 6,
              "battles": 28,
              "winRate": 0.7857142857142857,
              "strength": 1.5714285714285714,
              "btScore": 113
            },
            {
              "generator": "nano-banana-2",
              "wins": 6,
              "losses": 22,
              "battles": 28,
              "winRate": 0.21428571428571427,
              "strength": 0.42857142857142855,
              "btScore": -113
            }
          ]
        },
        {
          "axis": "commercialPreference",
          "label": "Commercial preference",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 25,
              "losses": 8,
              "battles": 33,
              "winRate": 0.7575757575757576,
              "strength": 1.5151515151515151,
              "btScore": 99
            },
            {
              "generator": "nano-banana-2",
              "wins": 8,
              "losses": 25,
              "battles": 33,
              "winRate": 0.24242424242424243,
              "strength": 0.48484848484848486,
              "btScore": -99
            }
          ]
        },
        {
          "axis": "overall",
          "label": "Overall",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 24,
              "losses": 9,
              "battles": 33,
              "winRate": 0.7272727272727273,
              "strength": 1.4545454545454546,
              "btScore": 85
            },
            {
              "generator": "nano-banana-2",
              "wins": 9,
              "losses": 24,
              "battles": 33,
              "winRate": 0.2727272727272727,
              "strength": 0.5454545454545454,
              "btScore": -85
            }
          ]
        }
      ]
    },
    {
      "judgeId": "openai_gpt-5.5_v2",
      "judgeModel": "openai/gpt-5.5",
      "judgePromptVersion": "pairwise-product-v2-multiaxis",
      "judgmentCount": 100,
      "totalCostCents": 719,
      "meanLatencyMs": 5525,
      "flipConsistency": 0.88,
      "positionBRate": 0.46,
      "positionBiasFlagged": false,
      "biasReason": "stable-pair filter used; 44/50 swap-consistent pairs, 6 pairs withheld from stable judge ranking",
      "consensusEligible": true,
      "ranking": [
        {
          "generator": "gpt-image-2",
          "wins": 40,
          "losses": 4,
          "battles": 44,
          "winRate": 0.9090909090909091,
          "strength": 1.8181818181818181,
          "btScore": 200
        },
        {
          "generator": "nano-banana-2",
          "wins": 4,
          "losses": 40,
          "battles": 44,
          "winRate": 0.09090909090909091,
          "strength": 0.18181818181818182,
          "btScore": -200
        }
      ],
      "axisRankings": [
        {
          "axis": "productIdentity",
          "label": "Product identity",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 74,
              "losses": 26,
              "battles": 100,
              "winRate": 0.74,
              "strength": 1.48,
              "btScore": 91
            },
            {
              "generator": "nano-banana-2",
              "wins": 26,
              "losses": 74,
              "battles": 100,
              "winRate": 0.26,
              "strength": 0.52,
              "btScore": -91
            }
          ]
        },
        {
          "axis": "taskFit",
          "label": "Task fit",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 88,
              "losses": 12,
              "battles": 100,
              "winRate": 0.88,
              "strength": 1.76,
              "btScore": 173
            },
            {
              "generator": "nano-banana-2",
              "wins": 12,
              "losses": 88,
              "battles": 100,
              "winRate": 0.12,
              "strength": 0.24,
              "btScore": -173
            }
          ]
        },
        {
          "axis": "commercialPreference",
          "label": "Commercial preference",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 86,
              "losses": 14,
              "battles": 100,
              "winRate": 0.86,
              "strength": 1.72,
              "btScore": 158
            },
            {
              "generator": "nano-banana-2",
              "wins": 14,
              "losses": 86,
              "battles": 100,
              "winRate": 0.14,
              "strength": 0.28,
              "btScore": -158
            }
          ]
        },
        {
          "axis": "overall",
          "label": "Overall",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 86,
              "losses": 14,
              "battles": 100,
              "winRate": 0.86,
              "strength": 1.72,
              "btScore": 158
            },
            {
              "generator": "nano-banana-2",
              "wins": 14,
              "losses": 86,
              "battles": 100,
              "winRate": 0.14,
              "strength": 0.28,
              "btScore": -158
            }
          ]
        }
      ],
      "stableAxisRankings": [
        {
          "axis": "productIdentity",
          "label": "Product identity",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 31,
              "losses": 7,
              "battles": 38,
              "winRate": 0.8157894736842105,
              "strength": 1.631578947368421,
              "btScore": 129
            },
            {
              "generator": "nano-banana-2",
              "wins": 7,
              "losses": 31,
              "battles": 38,
              "winRate": 0.18421052631578946,
              "strength": 0.3684210526315789,
              "btScore": -129
            }
          ]
        },
        {
          "axis": "taskFit",
          "label": "Task fit",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 42,
              "losses": 4,
              "battles": 46,
              "winRate": 0.9130434782608695,
              "strength": 1.826086956521739,
              "btScore": 204
            },
            {
              "generator": "nano-banana-2",
              "wins": 4,
              "losses": 42,
              "battles": 46,
              "winRate": 0.08695652173913043,
              "strength": 0.17391304347826086,
              "btScore": -204
            }
          ]
        },
        {
          "axis": "commercialPreference",
          "label": "Commercial preference",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 41,
              "losses": 5,
              "battles": 46,
              "winRate": 0.8913043478260869,
              "strength": 1.7826086956521738,
              "btScore": 183
            },
            {
              "generator": "nano-banana-2",
              "wins": 5,
              "losses": 41,
              "battles": 46,
              "winRate": 0.10869565217391304,
              "strength": 0.21739130434782608,
              "btScore": -183
            }
          ]
        },
        {
          "axis": "overall",
          "label": "Overall",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 40,
              "losses": 4,
              "battles": 44,
              "winRate": 0.9090909090909091,
              "strength": 1.8181818181818181,
              "btScore": 200
            },
            {
              "generator": "nano-banana-2",
              "wins": 4,
              "losses": 40,
              "battles": 44,
              "winRate": 0.09090909090909091,
              "strength": 0.18181818181818182,
              "btScore": -200
            }
          ]
        }
      ]
    },
    {
      "judgeId": "qwen_qwen3.7-plus_v2",
      "judgeModel": "qwen/qwen3.7-plus",
      "judgePromptVersion": "pairwise-product-v2-multiaxis",
      "judgmentCount": 100,
      "totalCostCents": 100,
      "meanLatencyMs": 5915,
      "flipConsistency": 0.58,
      "positionBRate": 0.39,
      "positionBiasFlagged": false,
      "biasReason": "stable-pair filter used; 29/50 swap-consistent pairs, 21 pairs withheld from stable judge ranking",
      "consensusEligible": true,
      "ranking": [
        {
          "generator": "gpt-image-2",
          "wins": 20,
          "losses": 9,
          "battles": 29,
          "winRate": 0.6896551724137931,
          "strength": 1.3793103448275863,
          "btScore": 69
        },
        {
          "generator": "nano-banana-2",
          "wins": 9,
          "losses": 20,
          "battles": 29,
          "winRate": 0.3103448275862069,
          "strength": 0.6206896551724138,
          "btScore": -69
        }
      ],
      "axisRankings": [
        {
          "axis": "productIdentity",
          "label": "Product identity",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 59,
              "losses": 41,
              "battles": 100,
              "winRate": 0.59,
              "strength": 1.18,
              "btScore": 32
            },
            {
              "generator": "nano-banana-2",
              "wins": 41,
              "losses": 59,
              "battles": 100,
              "winRate": 0.41,
              "strength": 0.82,
              "btScore": -32
            }
          ]
        },
        {
          "axis": "taskFit",
          "label": "Task fit",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 62,
              "losses": 38,
              "battles": 100,
              "winRate": 0.62,
              "strength": 1.24,
              "btScore": 43
            },
            {
              "generator": "nano-banana-2",
              "wins": 38,
              "losses": 62,
              "battles": 100,
              "winRate": 0.38,
              "strength": 0.76,
              "btScore": -43
            }
          ]
        },
        {
          "axis": "commercialPreference",
          "label": "Commercial preference",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 62,
              "losses": 38,
              "battles": 100,
              "winRate": 0.62,
              "strength": 1.24,
              "btScore": 43
            },
            {
              "generator": "nano-banana-2",
              "wins": 38,
              "losses": 62,
              "battles": 100,
              "winRate": 0.38,
              "strength": 0.76,
              "btScore": -43
            }
          ]
        },
        {
          "axis": "overall",
          "label": "Overall",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 61,
              "losses": 39,
              "battles": 100,
              "winRate": 0.61,
              "strength": 1.22,
              "btScore": 39
            },
            {
              "generator": "nano-banana-2",
              "wins": 39,
              "losses": 61,
              "battles": 100,
              "winRate": 0.39,
              "strength": 0.78,
              "btScore": -39
            }
          ]
        }
      ],
      "stableAxisRankings": [
        {
          "axis": "productIdentity",
          "label": "Product identity",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 19,
              "losses": 10,
              "battles": 29,
              "winRate": 0.6551724137931034,
              "strength": 1.3103448275862069,
              "btScore": 56
            },
            {
              "generator": "nano-banana-2",
              "wins": 10,
              "losses": 19,
              "battles": 29,
              "winRate": 0.3448275862068966,
              "strength": 0.6896551724137931,
              "btScore": -56
            }
          ]
        },
        {
          "axis": "taskFit",
          "label": "Task fit",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 20,
              "losses": 8,
              "battles": 28,
              "winRate": 0.7142857142857143,
              "strength": 1.4285714285714286,
              "btScore": 80
            },
            {
              "generator": "nano-banana-2",
              "wins": 8,
              "losses": 20,
              "battles": 28,
              "winRate": 0.2857142857142857,
              "strength": 0.5714285714285714,
              "btScore": -80
            }
          ]
        },
        {
          "axis": "commercialPreference",
          "label": "Commercial preference",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 20,
              "losses": 8,
              "battles": 28,
              "winRate": 0.7142857142857143,
              "strength": 1.4285714285714286,
              "btScore": 80
            },
            {
              "generator": "nano-banana-2",
              "wins": 8,
              "losses": 20,
              "battles": 28,
              "winRate": 0.2857142857142857,
              "strength": 0.5714285714285714,
              "btScore": -80
            }
          ]
        },
        {
          "axis": "overall",
          "label": "Overall",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 20,
              "losses": 9,
              "battles": 29,
              "winRate": 0.6896551724137931,
              "strength": 1.3793103448275863,
              "btScore": 69
            },
            {
              "generator": "nano-banana-2",
              "wins": 9,
              "losses": 20,
              "battles": 29,
              "winRate": 0.3103448275862069,
              "strength": 0.6206896551724138,
              "btScore": -69
            }
          ]
        }
      ]
    },
    {
      "judgeId": "xiaomi_mimo-v2.5_v2",
      "judgeModel": "xiaomi/mimo-v2.5",
      "judgePromptVersion": "pairwise-product-v2-multiaxis",
      "judgmentCount": 100,
      "totalCostCents": 106,
      "meanLatencyMs": 9107,
      "flipConsistency": 0.58,
      "positionBRate": 0.35,
      "positionBiasFlagged": false,
      "biasReason": "stable-pair filter used; 29/50 swap-consistent pairs, 21 pairs withheld from stable judge ranking",
      "consensusEligible": true,
      "ranking": [
        {
          "generator": "gpt-image-2",
          "wins": 15,
          "losses": 14,
          "battles": 29,
          "winRate": 0.5172413793103449,
          "strength": 1.0344827586206897,
          "btScore": 6
        },
        {
          "generator": "nano-banana-2",
          "wins": 14,
          "losses": 15,
          "battles": 29,
          "winRate": 0.4827586206896552,
          "strength": 0.9655172413793104,
          "btScore": -6
        }
      ],
      "axisRankings": [
        {
          "axis": "productIdentity",
          "label": "Product identity",
          "stats": [
            {
              "generator": "nano-banana-2",
              "wins": 52,
              "losses": 48,
              "battles": 100,
              "winRate": 0.52,
              "strength": 1.04,
              "btScore": 7
            },
            {
              "generator": "gpt-image-2",
              "wins": 48,
              "losses": 52,
              "battles": 100,
              "winRate": 0.48,
              "strength": 0.96,
              "btScore": -7
            }
          ]
        },
        {
          "axis": "taskFit",
          "label": "Task fit",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 53,
              "losses": 47,
              "battles": 100,
              "winRate": 0.53,
              "strength": 1.06,
              "btScore": 10
            },
            {
              "generator": "nano-banana-2",
              "wins": 47,
              "losses": 53,
              "battles": 100,
              "winRate": 0.47,
              "strength": 0.94,
              "btScore": -10
            }
          ]
        },
        {
          "axis": "commercialPreference",
          "label": "Commercial preference",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 51,
              "losses": 49,
              "battles": 100,
              "winRate": 0.51,
              "strength": 1.02,
              "btScore": 3
            },
            {
              "generator": "nano-banana-2",
              "wins": 49,
              "losses": 51,
              "battles": 100,
              "winRate": 0.49,
              "strength": 0.98,
              "btScore": -3
            }
          ]
        },
        {
          "axis": "overall",
          "label": "Overall",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 51,
              "losses": 49,
              "battles": 100,
              "winRate": 0.51,
              "strength": 1.02,
              "btScore": 3
            },
            {
              "generator": "nano-banana-2",
              "wins": 49,
              "losses": 51,
              "battles": 100,
              "winRate": 0.49,
              "strength": 0.98,
              "btScore": -3
            }
          ]
        }
      ],
      "stableAxisRankings": [
        {
          "axis": "productIdentity",
          "label": "Product identity",
          "stats": [
            {
              "generator": "nano-banana-2",
              "wins": 16,
              "losses": 14,
              "battles": 30,
              "winRate": 0.5333333333333333,
              "strength": 1.0666666666666667,
              "btScore": 12
            },
            {
              "generator": "gpt-image-2",
              "wins": 14,
              "losses": 16,
              "battles": 30,
              "winRate": 0.4666666666666667,
              "strength": 0.9333333333333333,
              "btScore": -12
            }
          ]
        },
        {
          "axis": "taskFit",
          "label": "Task fit",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 14,
              "losses": 11,
              "battles": 25,
              "winRate": 0.56,
              "strength": 1.12,
              "btScore": 21
            },
            {
              "generator": "nano-banana-2",
              "wins": 11,
              "losses": 14,
              "battles": 25,
              "winRate": 0.44,
              "strength": 0.88,
              "btScore": -21
            }
          ]
        },
        {
          "axis": "commercialPreference",
          "label": "Commercial preference",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 14,
              "losses": 13,
              "battles": 27,
              "winRate": 0.5185185185185185,
              "strength": 1.037037037037037,
              "btScore": 6
            },
            {
              "generator": "nano-banana-2",
              "wins": 13,
              "losses": 14,
              "battles": 27,
              "winRate": 0.48148148148148145,
              "strength": 0.9629629629629629,
              "btScore": -6
            }
          ]
        },
        {
          "axis": "overall",
          "label": "Overall",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 15,
              "losses": 14,
              "battles": 29,
              "winRate": 0.5172413793103449,
              "strength": 1.0344827586206897,
              "btScore": 6
            },
            {
              "generator": "nano-banana-2",
              "wins": 14,
              "losses": 15,
              "battles": 29,
              "winRate": 0.4827586206896552,
              "strength": 0.9655172413793104,
              "btScore": -6
            }
          ]
        }
      ]
    },
    {
      "judgeId": "z-ai_glm-4.6v_v2",
      "judgeModel": "z-ai/glm-4.6v",
      "judgePromptVersion": "pairwise-product-v2-multiaxis",
      "judgmentCount": 100,
      "totalCostCents": 100,
      "meanLatencyMs": 11950,
      "flipConsistency": 0.24,
      "positionBRate": 0.14,
      "positionBiasFlagged": true,
      "biasReason": "stable-pair filter used; 12/50 swap-consistent pairs, 38 pairs withheld from stable judge ranking; position bias: B selected 14%",
      "consensusEligible": false,
      "ranking": [
        {
          "generator": "gpt-image-2",
          "wins": 10,
          "losses": 2,
          "battles": 12,
          "winRate": 0.8333333333333334,
          "strength": 1.6666666666666667,
          "btScore": 140
        },
        {
          "generator": "nano-banana-2",
          "wins": 2,
          "losses": 10,
          "battles": 12,
          "winRate": 0.16666666666666666,
          "strength": 0.3333333333333333,
          "btScore": -140
        }
      ],
      "axisRankings": [
        {
          "axis": "productIdentity",
          "label": "Product identity",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 55,
              "losses": 45,
              "battles": 100,
              "winRate": 0.55,
              "strength": 1.1,
              "btScore": 17
            },
            {
              "generator": "nano-banana-2",
              "wins": 45,
              "losses": 55,
              "battles": 100,
              "winRate": 0.45,
              "strength": 0.9,
              "btScore": -17
            }
          ]
        },
        {
          "axis": "taskFit",
          "label": "Task fit",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 58,
              "losses": 42,
              "battles": 100,
              "winRate": 0.58,
              "strength": 1.16,
              "btScore": 28
            },
            {
              "generator": "nano-banana-2",
              "wins": 42,
              "losses": 58,
              "battles": 100,
              "winRate": 0.42,
              "strength": 0.84,
              "btScore": -28
            }
          ]
        },
        {
          "axis": "commercialPreference",
          "label": "Commercial preference",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 58,
              "losses": 42,
              "battles": 100,
              "winRate": 0.58,
              "strength": 1.16,
              "btScore": 28
            },
            {
              "generator": "nano-banana-2",
              "wins": 42,
              "losses": 58,
              "battles": 100,
              "winRate": 0.42,
              "strength": 0.84,
              "btScore": -28
            }
          ]
        },
        {
          "axis": "overall",
          "label": "Overall",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 58,
              "losses": 42,
              "battles": 100,
              "winRate": 0.58,
              "strength": 1.16,
              "btScore": 28
            },
            {
              "generator": "nano-banana-2",
              "wins": 42,
              "losses": 58,
              "battles": 100,
              "winRate": 0.42,
              "strength": 0.84,
              "btScore": -28
            }
          ]
        }
      ],
      "stableAxisRankings": [
        {
          "axis": "productIdentity",
          "label": "Product identity",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 5,
              "losses": 0,
              "battles": 5,
              "winRate": 1,
              "strength": 1.999000499750125,
              "btScore": 660
            },
            {
              "generator": "nano-banana-2",
              "wins": 0,
              "losses": 5,
              "battles": 5,
              "winRate": 0,
              "strength": 0.0009995002498750627,
              "btScore": -660
            }
          ]
        },
        {
          "axis": "taskFit",
          "label": "Task fit",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 10,
              "losses": 2,
              "battles": 12,
              "winRate": 0.8333333333333334,
              "strength": 1.6666666666666667,
              "btScore": 140
            },
            {
              "generator": "nano-banana-2",
              "wins": 2,
              "losses": 10,
              "battles": 12,
              "winRate": 0.16666666666666666,
              "strength": 0.3333333333333333,
              "btScore": -140
            }
          ]
        },
        {
          "axis": "commercialPreference",
          "label": "Commercial preference",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 10,
              "losses": 2,
              "battles": 12,
              "winRate": 0.8333333333333334,
              "strength": 1.6666666666666667,
              "btScore": 140
            },
            {
              "generator": "nano-banana-2",
              "wins": 2,
              "losses": 10,
              "battles": 12,
              "winRate": 0.16666666666666666,
              "strength": 0.3333333333333333,
              "btScore": -140
            }
          ]
        },
        {
          "axis": "overall",
          "label": "Overall",
          "stats": [
            {
              "generator": "gpt-image-2",
              "wins": 10,
              "losses": 2,
              "battles": 12,
              "winRate": 0.8333333333333334,
              "strength": 1.6666666666666667,
              "btScore": 140
            },
            {
              "generator": "nano-banana-2",
              "wins": 2,
              "losses": 10,
              "battles": 12,
              "winRate": 0.16666666666666666,
              "strength": 0.3333333333333333,
              "btScore": -140
            }
          ]
        }
      ]
    }
  ],
  "consensusRanking": [
    {
      "generator": "gpt-image-2",
      "wins": 27,
      "losses": 9,
      "battles": 36,
      "winRate": 0.75
    },
    {
      "generator": "nano-banana-2",
      "wins": 9,
      "losses": 27,
      "battles": 36,
      "winRate": 0.25
    }
  ],
  "consensusStableAxisRankings": [
    {
      "axis": "productIdentity",
      "label": "Product identity",
      "ranking": [
        {
          "generator": "gpt-image-2",
          "wins": 22,
          "losses": 11,
          "battles": 33,
          "winRate": 0.6666666666666666
        },
        {
          "generator": "nano-banana-2",
          "wins": 11,
          "losses": 22,
          "battles": 33,
          "winRate": 0.3333333333333333
        }
      ]
    },
    {
      "axis": "taskFit",
      "label": "Task fit",
      "ranking": [
        {
          "generator": "gpt-image-2",
          "wins": 28,
          "losses": 7,
          "battles": 35,
          "winRate": 0.8
        },
        {
          "generator": "nano-banana-2",
          "wins": 7,
          "losses": 28,
          "battles": 35,
          "winRate": 0.2
        }
      ]
    },
    {
      "axis": "commercialPreference",
      "label": "Commercial preference",
      "ranking": [
        {
          "generator": "gpt-image-2",
          "wins": 27,
          "losses": 10,
          "battles": 37,
          "winRate": 0.7297297297297297
        },
        {
          "generator": "nano-banana-2",
          "wins": 10,
          "losses": 27,
          "battles": 37,
          "winRate": 0.2702702702702703
        }
      ]
    },
    {
      "axis": "overall",
      "label": "Overall",
      "ranking": [
        {
          "generator": "gpt-image-2",
          "wins": 27,
          "losses": 9,
          "battles": 36,
          "winRate": 0.75
        },
        {
          "generator": "nano-banana-2",
          "wins": 9,
          "losses": 27,
          "battles": 36,
          "winRate": 0.25
        }
      ]
    }
  ],
  "taskTypeBreakdown": [
    {
      "taskType": "infographic",
      "taskCount": 27,
      "bothStablePairs": 21,
      "agreedStablePairs": 20,
      "disagreedStablePairs": 1,
      "ranking": [
        {
          "generator": "gpt-image-2",
          "wins": 17,
          "losses": 3,
          "battles": 20,
          "winRate": 0.85
        },
        {
          "generator": "nano-banana-2",
          "wins": 3,
          "losses": 17,
          "battles": 20,
          "winRate": 0.15
        }
      ]
    },
    {
      "taskType": "lifestyle",
      "taskCount": 23,
      "bothStablePairs": 18,
      "agreedStablePairs": 16,
      "disagreedStablePairs": 2,
      "ranking": [
        {
          "generator": "gpt-image-2",
          "wins": 10,
          "losses": 6,
          "battles": 16,
          "winRate": 0.625
        },
        {
          "generator": "nano-banana-2",
          "wins": 6,
          "losses": 10,
          "battles": 16,
          "winRate": 0.375
        }
      ]
    }
  ],
  "battles": []
}