{
  "schemaVersion": 1,
  "benchmarkVersion": "1.0.3",
  "exportedAt": "2026-07-15T02:55:51.177Z",
  "model": {
    "order": 6,
    "slug": "minimax-m3",
    "company": "MiniMax",
    "model": "MiniMax-M3",
    "openRouterModelId": "minimax/minimax-m3",
    "expectedCanonicalSlug": "minimax/minimax-m3-20260531",
    "harnessModel": "openrouter/minimax/minimax-m3",
    "variant": null,
    "cohort": "primary",
    "substitution": null
  },
  "route": "minimax-m3",
  "candidateCode": "C-7527",
  "record": {
    "runId": "minimax-m3",
    "modelSlug": "minimax-m3",
    "candidateCode": "C-7527",
    "runPosition": 3,
    "gateway": "OpenRouter",
    "requestedModelId": "minimax/minimax-m3",
    "expectedCanonicalSlug": "minimax/minimax-m3-20260531",
    "harnessModel": "openrouter/minimax/minimax-m3",
    "variant": null,
    "resolvedModelId": "minimax/minimax-m3",
    "resolvedCanonicalSlug": "minimax/minimax-m3-20260531",
    "startedAt": "2026-07-14T07:59:56.307Z",
    "finishedAt": "2026-07-14T08:05:18.699Z",
    "status": "completed",
    "promptSha256": "4fc686ce41533a72803ab11dd474f80c474666ea4154ead0fa0c90366042197f",
    "starterSha256": "6b745060ca29856fbeae84ea915909e83d6e7e7f05711aacf78918e2da5748a8",
    "elapsedMs": 322383,
    "inputTokens": 19343,
    "outputTokens": 16446,
    "cachedTokens": 733632,
    "reportedCostUsd": 0.07200162,
    "exitCode": 0,
    "agentStepsObserved": 40,
    "interventions": 0
  },
  "evaluation": {
    "evaluatedAt": "2026-07-14T08:05:22.263Z",
    "modelSlug": "minimax-m3",
    "installPassed": true,
    "buildPassed": true,
    "journeyPassed": false,
    "hardGatePassed": false,
    "automatedScore": 18,
    "automatedMaximum": 60,
    "passedChecks": [
      {
        "id": "F01",
        "title": "[F01|5][GATE] loads the correct substantial slice",
        "points": 5,
        "gate": true
      },
      {
        "id": "R01-mobile",
        "title": "[R01-mobile|3][GATE] no horizontal overflow at 360px",
        "points": 3,
        "gate": true
      },
      {
        "id": "R01-tablet",
        "title": "[R01-tablet|3][GATE] no horizontal overflow at 768px",
        "points": 3,
        "gate": true
      },
      {
        "id": "R01-desktop",
        "title": "[R01-desktop|2][GATE] no horizontal overflow at 1440px",
        "points": 2,
        "gate": true
      },
      {
        "id": "R03",
        "title": "[R03|2] images are local and load successfully when used",
        "points": 2,
        "gate": false
      },
      {
        "id": "A03",
        "title": "[A03|3] reduced motion suppresses long animations and transitions",
        "points": 3,
        "gate": false
      }
    ],
    "failedChecks": [
      {
        "id": "F02A",
        "title": "[F02A|6][GATE] filtering controls cards, URL state and direct loading",
        "points": 6,
        "gate": true
      },
      {
        "id": "F02B",
        "title": "[F02B|2] browser back and forward restore filter state",
        "points": 2,
        "gate": false
      },
      {
        "id": "F03",
        "title": "[F03|4][GATE] a keyboard-operable service button reveals supplied detail",
        "points": 4,
        "gate": true
      },
      {
        "id": "F04",
        "title": "[F04|4][GATE] dialog traps focus, closes with Escape and returns focus",
        "points": 4,
        "gate": true
      },
      {
        "id": "F05",
        "title": "[F05|4][GATE] the native-select form has errors and deterministic success",
        "points": 4,
        "gate": true
      },
      {
        "id": "R02",
        "title": "[R02|5] long copy is not clamped or clipped and missing media has a fallback",
        "points": 5,
        "gate": false
      },
      {
        "id": "R04",
        "title": "[R04|5] mobile navigation is present and keyboard usable",
        "points": 5,
        "gate": false
      },
      {
        "id": "A01",
        "title": "[A01|8][GATE] base page has no serious or critical axe violations",
        "points": 8,
        "gate": true
      },
      {
        "id": "A02",
        "title": "[A02|4][GATE] whole page remains accessible while the modal is open",
        "points": 4,
        "gate": true
      }
    ],
    "manualVisualScore": 3,
    "manualCodeScore": 3.5,
    "verificationScore": 2,
    "efficiencyScore": 5,
    "totalScore": 31.5,
    "capped": false,
    "validEvaluation": true,
    "infrastructureFailures": [],
    "evidenceWarnings": [],
    "manualReviews": [
      {
        "candidateCode": "C-7527",
        "reviewer": "R1",
        "visual": 2.5,
        "code": 3,
        "confidence": "high"
      },
      {
        "candidateCode": "C-7527",
        "reviewer": "R2",
        "visual": 3.5,
        "code": 4,
        "confidence": "high"
      }
    ],
    "thirdReviewRequired": false,
    "objectiveScoreEvidence": {
      "verification": {
        "ranCheck": true,
        "ranBuild": false,
        "progressTruthful": false
      },
      "efficiency": {
        "completedWithoutIntervention": true,
        "elapsedMs": 322383,
        "cleanExit": true,
        "reportedCostUsd": 0.07200162
      }
    },
    "rawScore": 31.5
  },
  "source": {
    "sha256": "1c7337709f3ba52c2fc99a33807848cd6963e96c9404116ba398938c88791357",
    "archive": "/r0/downloads/minimax-m3-source.tar.gz",
    "archiveSha256": "1b653d2bd64331a21ad010d610f476247df6c78ae1428a7001597dd81cc5d4eb",
    "exclusions": [
      "node_modules",
      "dist",
      ".git",
      ".opencode-state",
      "credential-bearing .env files"
    ]
  },
  "build": {
    "sha256": "3ac33ab448cffae9e2c6c07a54ba7a321a7a076f9db8c6d32995eebb11151a76",
    "publicPath": "/r0/minimax-m3/",
    "adaptations": [
      "npm run build -- --base=/r0/minimax-m3/",
      "Namespaced root /assets/ references in generated deployment files: assets/index-D1jmAY2e.js"
    ]
  },
  "evidenceHashes": {
    "screenshots/360.png": "ecfbbf446ff9c0206cae484cca9dd35c62f76c18cce4ac60c4d31e5a2295756f",
    "screenshots/768.png": "61fc6f14cbfd66d1424a9c3472f2ce7cdcb356c18057b1e6edab634cd047d9d9",
    "screenshots/1440.png": "7e04333de34c7785a845cee80b9828b61ad09747cc101af4a214e40cd84a2589",
    "interaction.webm": "f5d60dafba36c18923c102b8bff2ebf36c615b4644ac3d47f56e90a60fdc0ac5",
    "diff.patch": "9cca725243769a553a9b7465d3b0ab0adf7807c4b3f634d2fce4b78061bf92b6"
  },
  "reviewDisclosure": "Visual and code scores were produced by two independent blind AI reviewer agents without model identities or access to each other’s scores."
}