{
  "generatedAt": "2026-08-29",
  "baseline": "claude-opus-5",
  "headline": {
    "coreCostMultiple": "26.5×",
    "coreCostMultipleLabel": "cheaper at identical correctness",
    "realWorldMultiple": "≈15×",
    "realWorldSavedPct": "~93%"
  },
  "suites": {
    "core": {
      "title": "Core suite — 10 coding tasks × 3 trials",
      "note": "Both engines solved everything, so this measures cost at equal correctness. 26.5× cheaper — in fewer turns, fewer tool calls, and 19 minutes less wall clock. The one regression is time to first token: a routed turn pays for classification and dispatch before anything streams.",
      "columns": [
        "",
        "auto-model-router",
        "Claude Opus 5"
      ],
      "rows": [
        [
          "Tasks solved",
          "30 / 30",
          "30 / 30"
        ],
        [
          "Total cost",
          "$0.63",
          "$16.61"
        ],
        [
          "Cost per solved task",
          "$0.0209",
          "$0.5538"
        ],
        [
          "Turns to finish",
          "278",
          "303"
        ],
        [
          "Tool calls",
          "265",
          "337"
        ],
        [
          "Wall clock",
          "2 057 s",
          "3 185 s"
        ],
        [
          "Median time to first token",
          "5 776 ms",
          "1 490 ms"
        ]
      ],
      "winnerCol": 1
    },
    "ladder": {
      "title": "Difficulty ladder — 7 rungs, run twice",
      "note": "A second suite of deliberately escalating difficulty, ending in npm semver range semantics and a minimal diff with a specified tie-break. At the top of the ladder the engines separate.",
      "columns": [
        "",
        "auto-model-router",
        "Claude Opus 5"
      ],
      "rows": [
        [
          "Run 1",
          "5 / 7 · $0.30",
          "5 / 7 · $6.25"
        ],
        [
          "Run 2",
          "5 / 7 · $0.46",
          "6 / 7 · $6.60"
        ]
      ],
      "winnerCol": 1
    },
    "routed": {
      "title": "What it routed to",
      "note": "Across 464 routed turns in all five runs. Tier escalation converts to a costlier model roughly one-for-one; the escalation target is chosen live from trust and latency history, so it differs between runs on the same catalog.",
      "columns": [
        "Model",
        "Turns",
        "Input price",
        "Role"
      ],
      "rows": [
        [
          "z-ai/glm-5.3-flash",
          "389 (84%)",
          "$0.07 / MTok",
          "default"
        ],
        [
          "google/gemini-3.7-flash",
          "56 (12%)",
          "$0.75 / MTok",
          "escalation target"
        ],
        [
          "x-ai/grok-4.6",
          "18 (4%)",
          "$2.00 / MTok",
          "escalation target"
        ]
      ]
    },
    "realWorld": {
      "title": "Real-world — a week on the live ledger",
      "note": "6 918 billed turns across 299 conversations, 7 days, 410:1 input-to-output, 68% cache hit — the identical token stream repriced against a single Opus 5 model with its own cache namespace. ≈15× cheaper, ~93% saved: a four-figure monthly bill becomes a three-figure one.",
      "columns": [
        "",
        "auto-model-router",
        "Claude Opus 5 (single-model)"
      ],
      "rows": [
        [
          "Spend over the week",
          "$61.69",
          "$921.20"
        ],
        [
          "Per turn",
          "$0.0089",
          "$0.133"
        ],
        [
          "Extrapolated / month",
          "$263",
          "$3 932"
        ]
      ],
      "winnerCol": 1
    }
  },
  "ledgerSnapshot": null
}