{
  "name": "model-grocery-list",
  "type": "models",
  "archiveDate": "2026-10-25",
  "displayDate": "2026-11-04",
  "runDate": "2026-11-05",
  "model": "Multiple models",
  "customSkills": [],
  "capturedAt": "2026-11-05T03:55:01.510Z",
  "excluded": [
    "Qwen"
  ],
  "notes": "The display date and archive date are user-selected labels. Actual runs took place on 2026-11-05. Measurements cover the original run only. Later publication export work is excluded. Token costs exclude VM, subscription and other charges. Unknown native costs are not zero.",
  "results": [
    {
      "key": "openai-gpt-6-astra-codex",
      "harness": "codex",
      "harnessName": "Codex",
      "provider": "openai",
      "providerName": "OpenAI",
      "model": "gpt-6-astra",
      "name": "GPT-6 Astra",
      "backend": "Boat",
      "reasoning": "Medium",
      "status": "complete",
      "executionSeconds": 275.736,
      "totalSeconds": 282.461,
      "tokens": {
        "inputTokens": 43304,
        "outputTokens": 11981,
        "cacheReadTokens": 409904,
        "cacheWriteTokens": 0
      },
      "cost": {
        "pricedSubtotalUsd": "1.441994000000000000000000000000",
        "completeTotalUsd": "1.441994000000000000000000000000",
        "partial": false,
        "provisional": false
      },
      "originalPreview": "Published",
      "publicationCheck": "Add + persistence passed",
      "notes": "Agent reported 6 passing Chromium tests and syntax checks.",
      "files": {
        "index.html": "e550a834a4ee601467e22e8b7910d8f6dd2d9e395ce1047464449d4e108c0be6",
        "style.css": "b3afa26984cfd2711a037811162b3714fea76151c37950d92a99417f71ad7e5d",
        "app.js": "cd610d340b9d34c0f091ddf9bc13995a924f4443f28272f68894bcf3ec39e408"
      },
      "publicationTransforms": [
        "Published page title gains provider/model prefix."
      ],
      "recordedRun": {
        "createdAt": "2026-11-05T03:00:01.424Z",
        "executionStartedAt": "2026-11-05T03:00:08.149Z",
        "completedAt": "2026-11-05T03:04:43.885Z"
      },
      "screenshots": {
        "light": "openai-gpt-6-astra-codex.webp"
      }
    },
    {
      "key": "openai-gpt-6.1-sol-codex",
      "harness": "codex",
      "harnessName": "Codex",
      "provider": "openai",
      "providerName": "OpenAI",
      "model": "gpt-6.1-sol",
      "name": "GPT-6.1 Sol",
      "backend": "Boat",
      "reasoning": "Medium",
      "status": "complete",
      "executionSeconds": 244.448,
      "totalSeconds": 253.371,
      "tokens": {
        "inputTokens": 42051,
        "outputTokens": 13120,
        "cacheReadTokens": 464485,
        "cacheWriteTokens": 0
      },
      "cost": {
        "pricedSubtotalUsd": "0.261750500000000000000000000000",
        "completeTotalUsd": "0.261750500000000000000000000000",
        "partial": false,
        "provisional": false
      },
      "originalPreview": "Published",
      "publicationCheck": "Add + persistence passed",
      "notes": "Agent reported 27 passing browser checks and syntax checks.",
      "files": {
        "index.html": "1688ce6c20be1d1261a1248a7755647720599bde9379cbecc589079ecd8da7cc",
        "style.css": "04184ce7c75a2ac9f0917c9ee1aaf668f10cccc1172f50390b9ade70dd87ea0b",
        "app.js": "76c7ccb733d7797cdb66b436ce743f5b7b133cad65397e4105d392e97cbf2737"
      },
      "publicationTransforms": [
        "Published page title gains provider/model prefix."
      ],
      "recordedRun": {
        "createdAt": "2026-11-05T03:00:02.042Z",
        "executionStartedAt": "2026-11-05T03:00:10.965Z",
        "completedAt": "2026-11-05T03:04:15.413Z"
      },
      "screenshots": {
        "light": "openai-gpt-6.1-sol-codex.webp"
      }
    },
    {
      "key": "openai-gpt-5.6-sol-codex",
      "harness": "codex",
      "harnessName": "Codex",
      "provider": "openai",
      "providerName": "OpenAI",
      "model": "gpt-5.6-sol",
      "name": "GPT-5.6 Sol",
      "backend": "Boat",
      "reasoning": "Medium",
      "status": "complete",
      "executionSeconds": 140.719,
      "totalSeconds": 146.945,
      "tokens": {
        "inputTokens": 44379,
        "outputTokens": 13368,
        "cacheReadTokens": 489581,
        "cacheWriteTokens": 0
      },
      "cost": {
        "pricedSubtotalUsd": "0.640708400000000000000000000000",
        "completeTotalUsd": "0.640708400000000000000000000000",
        "partial": false,
        "provisional": false
      },
      "originalPreview": "Published",
      "publicationCheck": "Add + persistence passed",
      "notes": "Agent reported 5 passing Node tests and a Chrome interaction check. Google Fonts has a system-font fallback.",
      "files": {
        "index.html": "1511c1b37ecacc22dc3c48e4a9f711ef857c02f990d918964d77f4044a13a118",
        "styles.css": "4b8df55213ae559ce21835f790e346816d1a8d6149a79a2ccafd84640d5fb6f4",
        "app.js": "aaf968cfc27aa87ba5f2bb65260591b602fb3f683180f34efbd7fa3758248b23",
        "model.js": "042b8dda78ed356eb177b9f06b7fbe1ea20723cab63f148bad53aab93f215d45"
      },
      "publicationTransforms": [
        "Published page title gains provider/model prefix."
      ],
      "recordedRun": {
        "createdAt": "2026-11-05T03:00:02.675Z",
        "executionStartedAt": "2026-11-05T03:00:08.901Z",
        "completedAt": "2026-11-05T03:02:29.620Z"
      },
      "screenshots": {
        "light": "openai-gpt-5.6-sol-codex.webp"
      }
    },
    {
      "key": "anthropic-claude-fable-5-1-claude",
      "harness": "claude",
      "harnessName": "Claude Code",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "model": "claude-fable-5-1",
      "name": "Claude Fable 5.1",
      "backend": "Boat",
      "reasoning": "Medium",
      "status": "complete",
      "executionSeconds": 543.01,
      "totalSeconds": 551.714,
      "tokens": {
        "inputTokens": 2675,
        "outputTokens": 30288,
        "cacheReadTokens": 993243,
        "cacheWriteTokens": 65314
      },
      "cost": {
        "pricedSubtotalUsd": "2.585481850000000000000000000000",
        "completeTotalUsd": "2.585481850000000000000000000000",
        "partial": false,
        "provisional": false
      },
      "originalPreview": "Published",
      "publicationCheck": "Add + persistence passed",
      "notes": "Agent reported 6 passing Playwright tests and a successful typecheck/build. Recorded usage also includes claude-haiku-5-5.",
      "files": {
        "index.html": "079307f22b6b651081e7d5bc3a56f02b2b825b4772645d1fef325ae58719b12f",
        "assets/index-C1YmUnh-.js": "0e4d3d16cc993c8793e0100a88d2b37d601af06bae2ce40c922345677d076211",
        "assets/index-DjbE8FGt.css": "adfa71fe2235cfb6461c7cb758a58cee96f0a92e986370043b8834f7a45460cd"
      },
      "publicationTransforms": [
        "Rebased root asset /assets/index-C1YmUnh-.js to ./assets/index-C1YmUnh-.js",
        "Rebased root asset /assets/index-DjbE8FGt.css to ./assets/index-DjbE8FGt.css",
        "Published page title gains provider/model prefix."
      ],
      "recordedRun": {
        "createdAt": "2026-11-05T03:00:03.337Z",
        "executionStartedAt": "2026-11-05T03:00:12.041Z",
        "completedAt": "2026-11-05T03:09:15.051Z"
      },
      "screenshots": {
        "light": "anthropic-claude-fable-5-1-claude.webp",
        "dark": "anthropic-claude-fable-5-1-claude-dark.webp"
      }
    },
    {
      "key": "anthropic-opus-5-5-claude",
      "harness": "claude",
      "harnessName": "Claude Code",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "model": "opus-5-5",
      "name": "Claude Opus 5.5",
      "backend": "Boat",
      "reasoning": "Medium",
      "status": "complete",
      "executionSeconds": 451.113,
      "totalSeconds": 462.017,
      "tokens": {
        "inputTokens": 2022,
        "outputTokens": 36040,
        "cacheReadTokens": 1349592,
        "cacheWriteTokens": 68501
      },
      "cost": {
        "pricedSubtotalUsd": "1.333347600000000000000000000000",
        "completeTotalUsd": "1.333347600000000000000000000000",
        "partial": false,
        "provisional": false
      },
      "originalPreview": "Published",
      "publicationCheck": "Add + persistence passed",
      "notes": "Agent reported 8 passing unit tests, 12 passing browser tests and a successful typecheck/build. Recorded usage includes Claude Haiku 5.5.",
      "files": {
        "index.html": "2dc6f8358eb4e5a7e19fb3ed8af42f7c3910eee4a11a8e9aaedd9cc682f641b7",
        "favicon.svg": "70c89254158cc33f2d4a88c479d6cfc0f021822f092c4f51ffafe69124ea5515",
        "assets/index-D8Kd0lBh.js": "02a0fb46e33e751a3926663b17284b625a6c5e84162687f9cddae4f47d059926",
        "assets/index-yeps7lYV.css": "933f21da7cfe81f3455f65b8838357feb9ea026ae95793a89d848375141110e9"
      },
      "publicationTransforms": [
        "Rebased root asset /favicon.svg to ./favicon.svg",
        "Rebased root asset /assets/index-D8Kd0lBh.js to ./assets/index-D8Kd0lBh.js",
        "Rebased root asset /assets/index-yeps7lYV.css to ./assets/index-yeps7lYV.css",
        "Rebased root asset /favicon.svg to ./favicon.svg",
        "Published page title gains provider/model prefix."
      ],
      "recordedRun": {
        "createdAt": "2026-11-05T03:00:03.989Z",
        "executionStartedAt": "2026-11-05T03:00:14.893Z",
        "completedAt": "2026-11-05T03:07:46.006Z"
      },
      "screenshots": {
        "light": "anthropic-opus-5-5-claude.webp",
        "dark": "anthropic-opus-5-5-claude-dark.webp"
      }
    },
    {
      "key": "xai-grok-4.7-cursor",
      "harness": "cursor",
      "harnessName": "Cursor Cloud",
      "provider": "xai",
      "providerName": "xAI",
      "model": "grok-4.7",
      "name": "Grok 4.7",
      "backend": "Cursor Cloud",
      "reasoning": "Native default",
      "status": "complete",
      "executionSeconds": 1261.698,
      "totalSeconds": 1273.493,
      "tokens": null,
      "cost": {
        "pricedSubtotalUsd": null,
        "completeTotalUsd": null,
        "partial": true,
        "provisional": true
      },
      "originalPreview": "Published",
      "publicationCheck": "Add + persistence passed",
      "notes": "Agent reported 10 passing unit tests, typecheck/build and browser checks. Cursor native token cost is unavailable.",
      "files": {
        "index.html": "23de9e5a30a7b5eb2127758e9a0c140a826b880afbf60937e68f20fba08f5272",
        "assets/index-BX6suhVi.js": "fc9bf91cde931eec027a26fe13df6363e8dd8cb183a9874346690c332bb2819b",
        "assets/index-DR7PId3W.css": "15345fdaa9fc6726e07e707ba751bd65c088ef361fd8e83a785ed0a0de7475e1"
      },
      "publicationTransforms": [
        "Rebased root asset /assets/index-BX6suhVi.js to ./assets/index-BX6suhVi.js",
        "Rebased root asset /assets/index-DR7PId3W.css to ./assets/index-DR7PId3W.css",
        "Published page title gains provider/model prefix."
      ],
      "recordedRun": {
        "createdAt": "2026-11-05T03:00:04.619Z",
        "executionStartedAt": "2026-11-05T03:00:16.414Z",
        "completedAt": "2026-11-05T03:21:18.112Z"
      },
      "screenshots": {
        "light": "xai-grok-4.7-cursor.webp"
      }
    },
    {
      "key": "deepseek-deepseek-v4.1-flash-deepseek",
      "harness": "deepseek",
      "harnessName": "DeepSeek Harness",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "model": "deepseek-v4.1-flash",
      "name": "DeepSeek V4.1 Flash",
      "backend": "Boat",
      "reasoning": "Medium",
      "status": "complete",
      "executionSeconds": 152.392,
      "totalSeconds": 238.897,
      "tokens": {
        "inputTokens": 25545,
        "outputTokens": 45778,
        "cacheReadTokens": 1345024,
        "cacheWriteTokens": 0
      },
      "cost": {
        "pricedSubtotalUsd": "0.048248957000000000000000000000",
        "completeTotalUsd": "0.048248957000000000000000000000",
        "partial": false,
        "provisional": false
      },
      "originalPreview": "Published",
      "publicationCheck": "Add + persistence passed",
      "notes": "Agent reported 37 passing unit/DOM tests, syntax checks and a successful build. The DOM tests used happy-dom, not a real browser.",
      "files": {
        "index.html": "2cd1f5445a29b0ef1096605085eac31006384086e907b779c9e47e353dd0ba61",
        "assets/index-BqdnwIwt.js": "09778a8fda47210f72320e0d34207b845bf4ddb8fdc3cb9ad70b8056ca47e37e",
        "assets/index-BrCA2gdu.css": "23cdbb62faf1c3922e4b38e6ed6c273aab30d48086bbc338937f408e1e194504"
      },
      "publicationTransforms": [
        "Rebased root asset /assets/index-BqdnwIwt.js to ./assets/index-BqdnwIwt.js",
        "Rebased root asset /assets/index-BrCA2gdu.css to ./assets/index-BrCA2gdu.css",
        "Published page title gains provider/model prefix."
      ],
      "recordedRun": {
        "createdAt": "2026-11-05T03:00:05.291Z",
        "executionStartedAt": "2026-11-05T03:01:31.796Z",
        "completedAt": "2026-11-05T03:04:04.188Z"
      },
      "screenshots": {
        "light": "deepseek-deepseek-v4.1-flash-deepseek.webp",
        "dark": "deepseek-deepseek-v4.1-flash-deepseek-dark.webp"
      }
    },
    {
      "key": "moonshot-kimi-k3.1-pro-kimi",
      "harness": "kimi",
      "harnessName": "Kimi Code",
      "provider": "moonshot",
      "providerName": "Moonshot AI",
      "model": "kimi-k3.1-pro",
      "name": "Kimi K3.1 Pro",
      "backend": "Boat",
      "reasoning": "Low",
      "status": "complete",
      "executionSeconds": 909.652,
      "totalSeconds": 936.142,
      "tokens": {
        "inputTokens": 95849,
        "outputTokens": 16561,
        "cacheReadTokens": 983808,
        "cacheWriteTokens": 0
      },
      "cost": {
        "pricedSubtotalUsd": "0.554069600000000000000000000000",
        "completeTotalUsd": "0.554069600000000000000000000000",
        "partial": false,
        "provisional": false
      },
      "originalPreview": "Published",
      "publicationCheck": "Add + persistence passed",
      "notes": "Agent reported 21 passing Chrome checks and syntax checks. Kimi used low effort. Optional Google Fonts has a system fallback.",
      "files": {
        "index.html": "d14c662c4e633cae7fe7f57bfd63fd13ef43dd1e96b4814d51589ea5ee19f164",
        "styles.css": "6addeb65030e97b819259d6b39ad6450479a2076f0f4b689c1c2537768004b48",
        "app.js": "9ee2c0e5c9198685e76483ba359d54124e47f4a5daa7be0686a96b0fa1581233"
      },
      "publicationTransforms": [
        "Published page title gains provider/model prefix."
      ],
      "recordedRun": {
        "createdAt": "2026-11-05T03:00:06.852Z",
        "executionStartedAt": "2026-11-05T03:00:33.342Z",
        "completedAt": "2026-11-05T03:15:42.994Z"
      },
      "screenshots": {
        "light": "moonshot-kimi-k3.1-pro-kimi.webp"
      }
    },
    {
      "key": "z-ai-glm-5.3-zcode",
      "harness": "zcode",
      "harnessName": "ZCode",
      "provider": "z-ai",
      "providerName": "Z.ai",
      "model": "glm-5.3",
      "name": "GLM 5.3",
      "backend": "Boat",
      "reasoning": "Native default",
      "status": "complete",
      "executionSeconds": 1795.192,
      "totalSeconds": 1849.461,
      "tokens": {
        "inputTokens": 388479,
        "outputTokens": 186693,
        "cacheReadTokens": 10088064,
        "cacheWriteTokens": 0
      },
      "cost": {
        "pricedSubtotalUsd": "1.469865984000000000000000000000",
        "completeTotalUsd": "1.469865984000000000000000000000",
        "partial": false,
        "provisional": false
      },
      "originalPreview": "Published",
      "publicationCheck": "Add + persistence passed",
      "notes": "Agent reported completed app checks. Native reasoning default; generic Artos effort does not control ZCode. The agent used a visual-judge subagent despite the task's no-delegation instruction.",
      "files": {
        "index.html": "cd5c113e1e4fb161f5f958a0ee58a00e5c5aea2ec124c87831b0e810731dbce2",
        "styles.css": "aec0a5bf11773b6a1cb4cad8eadd120c82740859890b9b3fa867601112ff684f",
        "js/app.js": "2963b0734aa78d7d62f357031f7f40f40ccea20a94bf17dd7c32142f3ca1abd6",
        "js/logic.js": "90225b0e9be677801dcf93cb6c6c957f11344fa03e2367cbf176561c869ebca9",
        "js/storage.js": "97abb4ef40fe3d9505a39e9335430b08f8a4f3664b87f37a5da5fb43b179d6e3"
      },
      "publicationTransforms": [
        "Published page title gains provider/model prefix."
      ],
      "recordedRun": {
        "createdAt": "2026-11-05T03:00:07.453Z",
        "executionStartedAt": "2026-11-05T03:01:01.722Z",
        "completedAt": "2026-11-05T03:30:56.914Z"
      },
      "screenshots": {
        "light": "z-ai-glm-5.3-zcode.webp",
        "dark": "z-ai-glm-5.3-zcode-dark.webp"
      }
    },
    {
      "key": "google-gemini-4-argon-gemini",
      "harness": "gemini",
      "harnessName": "Gemini CLI",
      "provider": "google",
      "providerName": "Google",
      "model": "gemini-4-argon",
      "name": "Gemini 4 Argon",
      "backend": "Boat",
      "reasoning": "Native default",
      "status": "complete",
      "executionSeconds": 740.215,
      "totalSeconds": 771.339,
      "tokens": {
        "inputTokens": 159597,
        "outputTokens": 36433,
        "cacheReadTokens": 2056456,
        "cacheWriteTokens": 0
      },
      "cost": {
        "pricedSubtotalUsd": "0.889169600000000000000000000000",
        "completeTotalUsd": "0.889169600000000000000000000000",
        "partial": false,
        "provisional": false
      },
      "originalPreview": "Published",
      "publicationCheck": "Add + persistence passed",
      "notes": "Agent reported 6 passing unit/integration tests and a successful typecheck/build. Native reasoning default.",
      "files": {
        "index.html": "601c7459cee849557c25cb2ee9e522353e2a9c63b25bc7b6ebcbbb018e1ccfd7",
        "assets/index-D6hcZhmI.js": "b98e78a23ca28b87a0997eceaeb021ab72115b5ffde44bc4cd39d007020a586e",
        "assets/index-K5yqGaCE.css": "0ffc51d8b1a36c47df3ecdc59bd3843187f04c78c7899461c1287a3e28d54c4a"
      },
      "publicationTransforms": [
        "Rebased root asset /assets/index-D6hcZhmI.js to ./assets/index-D6hcZhmI.js",
        "Rebased root asset /assets/index-K5yqGaCE.css to ./assets/index-K5yqGaCE.css",
        "Published page title gains provider/model prefix."
      ],
      "recordedRun": {
        "createdAt": "2026-11-05T03:00:08.070Z",
        "executionStartedAt": "2026-11-05T03:00:39.194Z",
        "completedAt": "2026-11-05T03:12:59.409Z"
      },
      "screenshots": {
        "light": "google-gemini-4-argon-gemini.webp"
      }
    },
    {
      "key": "meta-muse-wonder-1.0-muse",
      "harness": "muse",
      "harnessName": "Muse Code",
      "provider": "meta",
      "providerName": "Meta",
      "model": "muse-wonder-1.0",
      "name": "Muse Wonder",
      "backend": "Boat",
      "reasoning": "Medium",
      "status": "complete",
      "executionSeconds": 256.922,
      "totalSeconds": 292.591,
      "tokens": {
        "inputTokens": 186812,
        "outputTokens": 31768,
        "cacheReadTokens": 2312290,
        "cacheWriteTokens": 0
      },
      "cost": {
        "pricedSubtotalUsd": "1.253715500000000000000000000000",
        "completeTotalUsd": "1.253715500000000000000000000000",
        "partial": false,
        "provisional": false
      },
      "originalPreview": "Published",
      "publicationCheck": "Add + persistence passed",
      "notes": "Agent reported 19 passing DOM-harness tests and syntax checks; no real-browser test. Usage includes Spark helpers.",
      "files": {
        "index.html": "3b7b813e3a526e1f37cff6bcc039537d38e5a03d799f01a38ef7d0f37bffa0e4",
        "styles.css": "2efe57d8c28c10089505076b21f23ed88157f9df509e970e8e4e42a17f10afa5",
        "app.js": "033776907978cd76d36b9a8f7c8816df9a7ff00b414ad9ff2ca271cebe2cb7de"
      },
      "publicationTransforms": [
        "Published page title gains provider/model prefix."
      ],
      "recordedRun": {
        "createdAt": "2026-11-05T03:00:08.612Z",
        "executionStartedAt": "2026-11-05T03:00:44.281Z",
        "completedAt": "2026-11-05T03:05:01.203Z"
      },
      "screenshots": {
        "light": "meta-muse-wonder-1.0-muse.webp"
      }
    },
    {
      "key": "cognition-normal-devin",
      "harness": "devin",
      "harnessName": "Devin Cloud",
      "provider": "cognition",
      "providerName": "Cognition",
      "model": "normal",
      "name": "Devin Normal",
      "backend": "Devin Cloud",
      "reasoning": "Normal mode",
      "status": "complete",
      "executionSeconds": 451.636,
      "totalSeconds": 493.3,
      "tokens": null,
      "cost": {
        "pricedSubtotalUsd": null,
        "completeTotalUsd": null,
        "partial": true,
        "provisional": true
      },
      "originalPreview": "Published",
      "publicationCheck": "Add + persistence passed",
      "notes": "Agent reported 9 passing unit tests, build/lint and 15 passing browser tests. Devin uses its own VM and agent mode. Token usage is unavailable.",
      "files": {
        "index.html": "b5a81a71dc374a4855f387f4d87cfb270b6c13ca81bdb8f2244b660f9c055265",
        "favicon.svg": "bd27b82da673f07dadf6e2e0672771a80b211eb839787af706c8e7d5b059677f",
        "assets/index-C4OLKnxy.js": "75f1deb99580297483d73132d1f96f2321208acf367b7b095ef11e5d189fa1fc",
        "assets/index-DpleaAWI.css": "cba49a786b4ca9d2137a7957aee52aa22d3bc19a6e11083018efaafba0127ed2"
      },
      "publicationTransforms": [
        "Rebased root asset /favicon.svg to ./favicon.svg",
        "Rebased root asset /assets/index-C4OLKnxy.js to ./assets/index-C4OLKnxy.js",
        "Rebased root asset /assets/index-DpleaAWI.css to ./assets/index-DpleaAWI.css",
        "Published page title gains provider/model prefix."
      ],
      "recordedRun": {
        "createdAt": "2026-11-05T03:00:09.228Z",
        "executionStartedAt": "2026-11-05T03:00:50.892Z",
        "completedAt": "2026-11-05T03:08:22.528Z"
      },
      "screenshots": {
        "light": "cognition-normal-devin.webp",
        "dark": "cognition-normal-devin-dark.webp"
      }
    }
  ]
}
