{
  "model": "gpt-6-sol",
  "date": "2026-09-23",
  "status": "integrated",
  "expectedRuns": 10,
  "completedRuns": 10,
  "method": "One fresh GPT-6 Sol Codex subagent per active prompt. Each received only its canonical prompt path as a creative brief and a dedicated output path. No reference implementation, screenshots, or other model artifacts were supplied.",
  "isolation": "Instruction-based separation in a shared filesystem, not an access-control sandbox or independent attestation of file access.",
  "evaluation": "Static artifact validation and run-specific checks are recorded in each VALIDATION.md. Registry ingestion alone is not a qualitative pass or aggregate score.",
  "runs": [
    {
      "benchmark": "starfall-arena",
      "track": "core",
      "agent": "/root/sol_starfall",
      "context": "fresh",
      "referenceMaterialProvided": false,
      "prompt": "benchmarks/prompts/12-starfall-arena.md",
      "promptSha256": "50d1e4dd79f17c0b5ff7256a04bca2747493ce3636fa430db0237ff194c2eb36",
      "artifactSha256": "314932bc624dde9e29fba1634540184b0f16ee3a9c78806ba1951503ca39af5c",
      "files": [
        {
          "path": "VALIDATION.md",
          "sha256": "3dc022b1afea8d8fc13e0a70efea97afd72d09371814a4ff366e05f98e4dc9fb"
        },
        {
          "path": "index.html",
          "sha256": "314932bc624dde9e29fba1634540184b0f16ee3a9c78806ba1951503ca39af5c"
        }
      ],
      "validationReport": "/benchmarks/starfall-arena/gpt-6-sol/VALIDATION.md",
      "entry": "/benchmarks/starfall-arena/gpt-6-sol/index.html",
      "manifest": "/benchmarks/starfall-arena/gpt-6-sol/manifest.json"
    },
    {
      "benchmark": "low-poly-tower-defense",
      "track": "core",
      "agent": "/root/sol_tower",
      "context": "fresh",
      "referenceMaterialProvided": false,
      "prompt": "benchmarks/prompts/14-low-poly-tower-defense.md",
      "promptSha256": "3afadb6cc349189cfca6570e4e64352c242881cf87b15315245338fc64cf9e45",
      "artifactSha256": "d87e398caba1044e8df1545fcdbfd83d82a3d52fce4527d978f60c45c8467ffc",
      "files": [
        {
          "path": "VALIDATION.md",
          "sha256": "13d4d0f44b744ef1eef8c38638f812926cb85a855ed40c10fb6e43218eb16eff"
        },
        {
          "path": "index.html",
          "sha256": "d87e398caba1044e8df1545fcdbfd83d82a3d52fce4527d978f60c45c8467ffc"
        }
      ],
      "validationReport": "/benchmarks/low-poly-tower-defense/gpt-6-sol/VALIDATION.md",
      "entry": "/benchmarks/low-poly-tower-defense/gpt-6-sol/index.html",
      "manifest": "/benchmarks/low-poly-tower-defense/gpt-6-sol/manifest.json"
    },
    {
      "benchmark": "neon-drift",
      "track": "core",
      "agent": "/root/sol_neon",
      "context": "fresh",
      "referenceMaterialProvided": false,
      "prompt": "benchmarks/prompts/13-neon-drift.md",
      "promptSha256": "52425362117e2baaf69eb73b55b68223eeae9b485d9a8f2c0ef2ba2e708e7738",
      "artifactSha256": "6dad9ca80f48ee7d8dd73f38ed912adc1d31e635ab32c013a8b611d6550c295e",
      "files": [
        {
          "path": "VALIDATION.md",
          "sha256": "ab377bb8421492a936756d4682527a819cfc905901f2dab6c4b8bd3f107c7385"
        },
        {
          "path": "index.html",
          "sha256": "6dad9ca80f48ee7d8dd73f38ed912adc1d31e635ab32c013a8b611d6550c295e"
        }
      ],
      "validationReport": "/benchmarks/neon-drift/gpt-6-sol/VALIDATION.md",
      "entry": "/benchmarks/neon-drift/gpt-6-sol/index.html",
      "manifest": "/benchmarks/neon-drift/gpt-6-sol/manifest.json"
    },
    {
      "benchmark": "ember-glider",
      "track": "core",
      "agent": "/root/sol_ember",
      "context": "fresh",
      "referenceMaterialProvided": false,
      "prompt": "benchmarks/prompts/15-ember-glider.md",
      "promptSha256": "4c8d400bfae941324ed383aa454844adc1a90a8f786411ea2a50bf5e1c5e89e9",
      "artifactSha256": "5028d3e26ff8d9d9844952439198a7abb7f4231d201f00f7806f9ee3f3ce13dd",
      "files": [
        {
          "path": "VALIDATION.md",
          "sha256": "4c720f3f22159ee3012eaa2ca126fadac9d8d9145ec67d8d02bcaeb77506aecc"
        },
        {
          "path": "index.html",
          "sha256": "5028d3e26ff8d9d9844952439198a7abb7f4231d201f00f7806f9ee3f3ce13dd"
        }
      ],
      "validationReport": "/benchmarks/ember-glider/gpt-6-sol/VALIDATION.md",
      "entry": "/benchmarks/ember-glider/gpt-6-sol/index.html",
      "manifest": "/benchmarks/ember-glider/gpt-6-sol/manifest.json"
    },
    {
      "benchmark": "mechanical-watch-simulator",
      "track": "core",
      "agent": "/root/sol_watch",
      "context": "fresh",
      "referenceMaterialProvided": false,
      "prompt": "benchmarks/prompts/10-mechanical-watch-simulator.md",
      "promptSha256": "07c00af9ad23d44166b32b09ca0298d1c127b023b3b7f389274e5297050d112e",
      "artifactSha256": "d47f1eb66b9ad57c3520f1296de9c2653632e9c6d63196131241d3ab974b15d8",
      "files": [
        {
          "path": "VALIDATION.md",
          "sha256": "ba00fc6e6ef3c129cb10baac6c2c55b2a67b274d7a761a4af72d74fc4b1ad048"
        },
        {
          "path": "index.html",
          "sha256": "d47f1eb66b9ad57c3520f1296de9c2653632e9c6d63196131241d3ab974b15d8"
        }
      ],
      "validationReport": "/benchmarks/mechanical-watch-simulator/gpt-6-sol/VALIDATION.md",
      "entry": "/benchmarks/mechanical-watch-simulator/gpt-6-sol/index.html",
      "manifest": "/benchmarks/mechanical-watch-simulator/gpt-6-sol/manifest.json"
    },
    {
      "benchmark": "stormwind-trebuchet-simulator",
      "track": "core",
      "agent": "/root/sol_trebuchet",
      "context": "fresh",
      "referenceMaterialProvided": false,
      "prompt": "benchmarks/prompts/11-stormwind-trebuchet-simulator.md",
      "promptSha256": "9faf5823a18c8cad050066b98c01e3301357784c7fd54005f984753e626a8a76",
      "artifactSha256": "ae8508e9c0cb6663514ec70baedbdbfcec477356a27e1cb32fb77297ada931ea",
      "files": [
        {
          "path": "VALIDATION.md",
          "sha256": "293f3ca57f986d84da7fa64d1c0832819bae901bc8b9c54f81dbc6ff7d781393"
        },
        {
          "path": "index.html",
          "sha256": "ae8508e9c0cb6663514ec70baedbdbfcec477356a27e1cb32fb77297ada931ea"
        }
      ],
      "validationReport": "/benchmarks/stormwind-trebuchet-simulator/gpt-6-sol/VALIDATION.md",
      "entry": "/benchmarks/stormwind-trebuchet-simulator/gpt-6-sol/index.html",
      "manifest": "/benchmarks/stormwind-trebuchet-simulator/gpt-6-sol/manifest.json"
    },
    {
      "benchmark": "helms-deep",
      "track": "core",
      "agent": "/root/sol_helms",
      "context": "fresh",
      "referenceMaterialProvided": false,
      "prompt": "benchmarks/prompts/06-helms-deep.md",
      "promptSha256": "0a7c8c01558998c09342ecd7bea55fa12b227f84a5fd3da87c17e93f53745e8c",
      "artifactSha256": "566caa339899835bd342a1c80935bb5f93d96c60b5c29a53cfb7fb69771bbb2f",
      "files": [
        {
          "path": "VALIDATION.md",
          "sha256": "75bf177eb9f670626162df96644d62717d8fb5360b3bf10316cdbbd07a90b0c1"
        },
        {
          "path": "index.html",
          "sha256": "566caa339899835bd342a1c80935bb5f93d96c60b5c29a53cfb7fb69771bbb2f"
        }
      ],
      "validationReport": "/benchmarks/helms-deep/gpt-6-sol/VALIDATION.md",
      "entry": "/benchmarks/helms-deep/gpt-6-sol/index.html",
      "manifest": "/benchmarks/helms-deep/gpt-6-sol/manifest.json"
    },
    {
      "benchmark": "hogwarts-broom-flight-simulator",
      "track": "core",
      "agent": "/root/sol_hogwarts",
      "context": "fresh",
      "referenceMaterialProvided": false,
      "prompt": "benchmarks/prompts/07-hogwarts-broom-flight-simulator.md",
      "promptSha256": "d8a7287c80fd5cf9f1f5b85e414076cfd839e5e38f2defb64f46d1e9a423562a",
      "artifactSha256": "293b768c64b1c03fd19e82fa013fd943c6d5be4d9d7800120557d09eabf9d069",
      "files": [
        {
          "path": "VALIDATION.md",
          "sha256": "783297fd7e63717cebeabbdbb02ce8f2475f9b21e61dba87d3d3a201ed21398d"
        },
        {
          "path": "index.html",
          "sha256": "293b768c64b1c03fd19e82fa013fd943c6d5be4d9d7800120557d09eabf9d069"
        }
      ],
      "validationReport": "/benchmarks/hogwarts-broom-flight-simulator/gpt-6-sol/VALIDATION.md",
      "entry": "/benchmarks/hogwarts-broom-flight-simulator/gpt-6-sol/index.html",
      "manifest": "/benchmarks/hogwarts-broom-flight-simulator/gpt-6-sol/manifest.json"
    },
    {
      "benchmark": "yingzao-fashi-assembly",
      "track": "specialist",
      "agent": "/root/sol_yingzao",
      "context": "fresh",
      "referenceMaterialProvided": false,
      "prompt": "benchmarks/prompts/09-yingzao-fashi-assembly.md",
      "promptSha256": "5ffad45769267f358cd1f21333d8b426af224cb53ee11897b92a92ce993db29e",
      "artifactSha256": "ab651e4b4fea26493996c18c919eefb8b82f8cf95c82c5e689eaab316a87ee7e",
      "files": [
        {
          "path": "VALIDATION.md",
          "sha256": "dbe2130753e4d864e43aa6f1773fe9a8a03948533ab96462cd1412e3ef313f47"
        },
        {
          "path": "index.html",
          "sha256": "ab651e4b4fea26493996c18c919eefb8b82f8cf95c82c5e689eaab316a87ee7e"
        }
      ],
      "validationReport": "/benchmarks/yingzao-fashi-assembly/gpt-6-sol/VALIDATION.md",
      "entry": "/benchmarks/yingzao-fashi-assembly/gpt-6-sol/index.html",
      "manifest": "/benchmarks/yingzao-fashi-assembly/gpt-6-sol/manifest.json"
    },
    {
      "benchmark": "city-scroll-journey",
      "track": "specialist",
      "agent": "/root/sol_city",
      "context": "fresh",
      "referenceMaterialProvided": false,
      "prompt": "benchmarks/prompts/16-city-scroll-journey.md",
      "promptSha256": "287577ab9b81ef7fbe717323d3263e282e59fc0672e837b025128ad0f4ad24e6",
      "artifactSha256": "ecb121f4663b13af88653a1da50381f258f1d2fa578170b787c23335f104d462",
      "files": [
        {
          "path": "GENERATION_PROMPTS.md",
          "sha256": "e64a7a601d2ae44faca0544d2e7034d98799a38184f90dbd2a4500337731bc21"
        },
        {
          "path": "VALIDATION.md",
          "sha256": "784d3fa394ccaea1e8c77549c3fc2e12d65cde558791b52a129c0c1309352a96"
        },
        {
          "path": "index.html",
          "sha256": "ecb121f4663b13af88653a1da50381f258f1d2fa578170b787c23335f104d462"
        },
        {
          "path": "media/egg-tart.svg",
          "sha256": "faffb88e1bdd1bb47a235e63b659b8510cf5a9676cf3835e9996e5723596ac19"
        },
        {
          "path": "media/ferry-poster.jpg",
          "sha256": "cbfe124eea36eefde0ac781907cab2db54d4d3a1f4f157937e64b194b4802de5"
        },
        {
          "path": "media/ferry.mp4",
          "sha256": "95155310bd8eeac606c10d888e67fc11f3753dfbc5159463ed0b280233879e12"
        },
        {
          "path": "media/harbor-poster.jpg",
          "sha256": "6d8ca24d908d7c8122655143cf1fda25bb2b232b3e20776f29221d54ee4f5baf"
        },
        {
          "path": "media/harbor.mp4",
          "sha256": "ba5a0d676b5464a4a79000c1f1119c18ba0e8091825b2f93ed5f3ae971aa106b"
        },
        {
          "path": "media/market-poster.jpg",
          "sha256": "5aeaeee39bef7c15b086265e20f3a6ce1079cc9b7a83949f2f2975af0f44f0c9"
        },
        {
          "path": "media/market.mp4",
          "sha256": "5be19a6e1b34372dfddd7837fd92c29f6da2d7996500ebd60eccd27409c7a47f"
        },
        {
          "path": "media/milk-tea.svg",
          "sha256": "a8c4029cf328d9d77bada7fcd2ac1b3b2235c85a12f9b57d71ffe88ea59030af"
        },
        {
          "path": "media/tram-poster.jpg",
          "sha256": "afb29b9908c604a45060f923cfe96d7b30083ce4fb33e3d981fbaaaa31d1e75a"
        },
        {
          "path": "media/tram.mp4",
          "sha256": "2f2ecf86f1dddffd8fde1be0348a4cecb27c8d780b4d9e8ea97f05519bda9c10"
        },
        {
          "path": "media/wonton.svg",
          "sha256": "6f7d7e5690f9ea7101dccfe853c7c9a5c31300109dd287c85e413a4967c26718"
        }
      ],
      "validationReport": "/benchmarks/city-scroll-journey/gpt-6-sol/VALIDATION.md",
      "entry": "/benchmarks/city-scroll-journey/gpt-6-sol/index.html",
      "manifest": "/benchmarks/city-scroll-journey/gpt-6-sol/manifest.json"
    }
  ]
}
