{
  "schemaVersion": 1,
  "model": "Kimi K3.1 Pro",
  "retrievedAt": "2026-10-24",
  "timezone": "Asia/Shanghai",
  "images": [
    {
      "id": "aa-intelligence-index",
      "sourcePage": "https://artificialanalysis.ai/articles/kimi-k3-1-pro-launch-benchmarks",
      "imageUrl": "https://cdn.sanity.io/images/6vfeftx9/articles/138fb6098ecf52a0fe46cbcaf4dae8cae9677edd-2464x1032.png",
      "copyright": "Artificial Analysis",
      "sourceDate": "2026-10-23",
      "localPath": "public/evaluations/kimi-k3-1-pro/assets/aa-intelligence-index.png",
      "publicPath": "/evaluations/kimi-k3-1-pro/assets/aa-intelligence-index.png",
      "bytes": 198509,
      "sha256": "49b16fbe81e8e713037b264071b33fbcdeb91905b52b08d19a31b8e1274d529a",
      "retrievedAt": "2026-10-24",
      "originalBytes": true,
      "width": 2464,
      "height": 1032,
      "format": "png",
      "path": "/evaluations/kimi-k3-1-pro/assets/aa-intelligence-index.png",
      "titleZh": "AA 智能指数",
      "titleEn": "AA Intelligence Index",
      "altZh": "AA 智能指数：Kimi K3.1 Pro 与其他模型对照",
      "altEn": "AA Intelligence Index: Kimi K3.1 Pro and peer models",
      "captionZh": "发布日指数 55，排名第 4；K3 为 44。",
      "captionEn": "Launch score 55, ranked fourth; K3 scored 44.",
      "sourceUrl": "https://artificialanalysis.ai/articles/kimi-k3-1-pro-launch-benchmarks",
      "originalUrl": "https://cdn.sanity.io/images/6vfeftx9/articles/138fb6098ecf52a0fe46cbcaf4dae8cae9677edd-2464x1032.png",
      "credit": "Artificial Analysis",
      "kind": "aa",
      "visuallyInspected": true,
      "visuallyInspectedAt": "2026-10-24",
      "inspectionMethod": "AI assistant inspected the full original chart including labels, legends and footnotes; qualitative visual review, not an independent human rating",
      "independentlyReproducedByTokrace": false,
      "sourcePublishedAt": "2026-10-23",
      "sourceDateBasis": "Displayed article publication date"
    },
    {
      "id": "aa-agentic-benchmarks",
      "sourcePage": "https://artificialanalysis.ai/articles/kimi-k3-1-pro-launch-benchmarks",
      "imageUrl": "https://cdn.sanity.io/images/6vfeftx9/articles/b9057382a9420d84f8de928577c714c79cde67c8-2464x3016.png",
      "copyright": "Artificial Analysis",
      "sourceDate": "2026-10-23",
      "localPath": "public/evaluations/kimi-k3-1-pro/assets/aa-agentic-benchmarks.png",
      "publicPath": "/evaluations/kimi-k3-1-pro/assets/aa-agentic-benchmarks.png",
      "bytes": 1988983,
      "sha256": "b149faa1126e60edf87e1f2b504485cd3ca05870bdd23957e165db1973e7731f",
      "retrievedAt": "2026-10-24",
      "originalBytes": true,
      "width": 2464,
      "height": 3016,
      "format": "png",
      "path": "/evaluations/kimi-k3-1-pro/assets/aa-agentic-benchmarks.png",
      "titleZh": "AA Agent 任务：终端、GDPval 与 Briefcase",
      "titleEn": "AA agent benchmarks: terminal, GDPval and Briefcase",
      "altZh": "AA Agent 任务：终端、GDPval 与 Briefcase：Kimi K3.1 Pro 与其他模型对照",
      "altEn": "AA agent benchmarks: terminal, GDPval and Briefcase: Kimi K3.1 Pro and peer models",
      "captionZh": "AA 的终端与知识工作任务原图。",
      "captionEn": "Original AA charts for terminal and knowledge-work tasks.",
      "sourceUrl": "https://artificialanalysis.ai/articles/kimi-k3-1-pro-launch-benchmarks",
      "originalUrl": "https://cdn.sanity.io/images/6vfeftx9/articles/b9057382a9420d84f8de928577c714c79cde67c8-2464x3016.png",
      "credit": "Artificial Analysis",
      "kind": "aa",
      "visuallyInspected": true,
      "visuallyInspectedAt": "2026-10-24",
      "inspectionMethod": "AI assistant inspected the full original chart including labels, legends and footnotes; qualitative visual review, not an independent human rating",
      "independentlyReproducedByTokrace": false,
      "sourcePublishedAt": "2026-10-23",
      "sourceDateBasis": "Displayed article publication date"
    },
    {
      "id": "aa-omniscience",
      "sourcePage": "https://artificialanalysis.ai/articles/kimi-k3-1-pro-launch-benchmarks",
      "imageUrl": "https://cdn.sanity.io/images/6vfeftx9/articles/67dae7c3e071e59bd86a27eefc3dee071669dbfe-2464x3160.png",
      "copyright": "Artificial Analysis",
      "sourceDate": "2026-10-23",
      "localPath": "public/evaluations/kimi-k3-1-pro/assets/aa-omniscience.png",
      "publicPath": "/evaluations/kimi-k3-1-pro/assets/aa-omniscience.png",
      "bytes": 1661505,
      "sha256": "d564381cef0f5bf567eb8a04893e6189dc791275ca7064f8f338e8b7a7119b91",
      "retrievedAt": "2026-10-24",
      "originalBytes": true,
      "width": 2464,
      "height": 3160,
      "format": "png",
      "path": "/evaluations/kimi-k3-1-pro/assets/aa-omniscience.png",
      "titleZh": "AA 知识可靠性与幻觉",
      "titleEn": "AA knowledge reliability and hallucination",
      "altZh": "AA 知识可靠性与幻觉：Kimi K3.1 Pro 与其他模型对照",
      "altEn": "AA knowledge reliability and hallucination: Kimi K3.1 Pro and peer models",
      "captionZh": "AA-Omniscience 指数、准确率和幻觉率。",
      "captionEn": "AA-Omniscience index, accuracy and hallucination rate.",
      "sourceUrl": "https://artificialanalysis.ai/articles/kimi-k3-1-pro-launch-benchmarks",
      "originalUrl": "https://cdn.sanity.io/images/6vfeftx9/articles/67dae7c3e071e59bd86a27eefc3dee071669dbfe-2464x3160.png",
      "credit": "Artificial Analysis",
      "kind": "aa",
      "visuallyInspected": true,
      "visuallyInspectedAt": "2026-10-24",
      "inspectionMethod": "AI assistant inspected the full original chart including labels, legends and footnotes; qualitative visual review, not an independent human rating",
      "independentlyReproducedByTokrace": false,
      "sourcePublishedAt": "2026-10-23",
      "sourceDateBasis": "Displayed article publication date"
    },
    {
      "id": "aa-cost-and-output-tokens",
      "sourcePage": "https://artificialanalysis.ai/articles/kimi-k3-1-pro-launch-benchmarks",
      "imageUrl": "https://cdn.sanity.io/images/6vfeftx9/articles/bf1b0c4f670a82e3af52e3d9ccd4a6109c2c7c8f-2464x2288.png",
      "copyright": "Artificial Analysis",
      "sourceDate": "2026-10-23",
      "localPath": "public/evaluations/kimi-k3-1-pro/assets/aa-cost-and-output-tokens.png",
      "publicPath": "/evaluations/kimi-k3-1-pro/assets/aa-cost-and-output-tokens.png",
      "bytes": 1223476,
      "sha256": "0b040a0f79a10b6076e1524b7ccc37f558018d44f75f02da796aa33086b93629",
      "retrievedAt": "2026-10-24",
      "originalBytes": true,
      "width": 2464,
      "height": 2288,
      "format": "png",
      "path": "/evaluations/kimi-k3-1-pro/assets/aa-cost-and-output-tokens.png",
      "titleZh": "AA 每任务成本",
      "titleEn": "AA cost per task",
      "altZh": "AA 每任务成本：Kimi K3.1 Pro 与其他模型对照",
      "altEn": "AA cost per task: Kimi K3.1 Pro and peer models",
      "captionZh": "AA 智能指数任务加权成本，含推理与缓存。",
      "captionEn": "Weighted Intelligence Index task cost, including reasoning and caching.",
      "sourceUrl": "https://artificialanalysis.ai/articles/kimi-k3-1-pro-launch-benchmarks",
      "originalUrl": "https://cdn.sanity.io/images/6vfeftx9/articles/bf1b0c4f670a82e3af52e3d9ccd4a6109c2c7c8f-2464x2288.png",
      "credit": "Artificial Analysis",
      "kind": "aa",
      "visuallyInspected": true,
      "visuallyInspectedAt": "2026-10-24",
      "inspectionMethod": "AI assistant inspected the full original chart including labels, legends and footnotes; qualitative visual review, not an independent human rating",
      "independentlyReproducedByTokrace": false,
      "sourcePublishedAt": "2026-10-23",
      "sourceDateBasis": "Displayed article publication date"
    },
    {
      "id": "aa-parameters",
      "sourcePage": "https://artificialanalysis.ai/articles/kimi-k3-1-pro-launch-benchmarks",
      "imageUrl": "https://cdn.sanity.io/images/6vfeftx9/articles/03d372ef5d4d8cd41915c09eccd3d1b9d0651934-2464x2384.png",
      "copyright": "Artificial Analysis",
      "sourceDate": "2026-10-23",
      "localPath": "public/evaluations/kimi-k3-1-pro/assets/aa-parameters.png",
      "publicPath": "/evaluations/kimi-k3-1-pro/assets/aa-parameters.png",
      "bytes": 876931,
      "sha256": "bfdb2f87e56f4c99863621534d6c86e72f24487281242795550ba3cf788449ec",
      "retrievedAt": "2026-10-24",
      "originalBytes": true,
      "width": 2464,
      "height": 2384,
      "format": "png",
      "path": "/evaluations/kimi-k3-1-pro/assets/aa-parameters.png",
      "titleZh": "AA 智能与参数规模",
      "titleEn": "AA intelligence versus parameter count",
      "altZh": "AA 智能与参数规模：Kimi K3.1 Pro 与其他模型对照",
      "altEn": "AA intelligence versus parameter count: Kimi K3.1 Pro and peer models",
      "captionZh": "AA 总参数及激活参数规模对照。",
      "captionEn": "AA comparisons by total and active parameter count.",
      "sourceUrl": "https://artificialanalysis.ai/articles/kimi-k3-1-pro-launch-benchmarks",
      "originalUrl": "https://cdn.sanity.io/images/6vfeftx9/articles/03d372ef5d4d8cd41915c09eccd3d1b9d0651934-2464x2384.png",
      "credit": "Artificial Analysis",
      "kind": "aa",
      "visuallyInspected": true,
      "visuallyInspectedAt": "2026-10-24",
      "inspectionMethod": "AI assistant inspected the full original chart including labels, legends and footnotes; qualitative visual review, not an independent human rating",
      "independentlyReproducedByTokrace": false,
      "sourcePublishedAt": "2026-10-23",
      "sourceDateBasis": "Displayed article publication date"
    },
    {
      "id": "aa-individual-evals",
      "sourcePage": "https://artificialanalysis.ai/articles/kimi-k3-1-pro-launch-benchmarks",
      "imageUrl": "https://cdn.sanity.io/images/6vfeftx9/articles/59b7803d72b26a64b0fb0087e23a2d162352c9b6-4096x3544.png",
      "copyright": "Artificial Analysis",
      "sourceDate": "2026-10-23",
      "localPath": "public/evaluations/kimi-k3-1-pro/assets/aa-individual-evals.png",
      "publicPath": "/evaluations/kimi-k3-1-pro/assets/aa-individual-evals.png",
      "bytes": 3958105,
      "sha256": "254db54776573fc8c86bbbe1ea23ca7bd7d10226ee9e26fe50b289241f3dec88",
      "retrievedAt": "2026-10-24",
      "originalBytes": true,
      "width": 4096,
      "height": 3544,
      "format": "png",
      "path": "/evaluations/kimi-k3-1-pro/assets/aa-individual-evals.png",
      "titleZh": "AA 分项评测总览",
      "titleEn": "AA individual evaluation results",
      "altZh": "AA 分项评测总览：Kimi K3.1 Pro 与其他模型对照",
      "altEn": "AA individual evaluation results: Kimi K3.1 Pro and peer models",
      "captionZh": "AA 11 个分项指标的原始总览。",
      "captionEn": "Original overview of eleven AA evaluation metrics.",
      "sourceUrl": "https://artificialanalysis.ai/articles/kimi-k3-1-pro-launch-benchmarks",
      "originalUrl": "https://cdn.sanity.io/images/6vfeftx9/articles/59b7803d72b26a64b0fb0087e23a2d162352c9b6-4096x3544.png",
      "credit": "Artificial Analysis",
      "kind": "aa",
      "visuallyInspected": true,
      "visuallyInspectedAt": "2026-10-24",
      "inspectionMethod": "AI assistant inspected the full original chart including labels, legends and footnotes; qualitative visual review, not an independent human rating",
      "independentlyReproducedByTokrace": false,
      "sourcePublishedAt": "2026-10-23",
      "sourceDateBasis": "Displayed article publication date"
    },
    {
      "id": "official-benchmark-overview",
      "sourcePage": "https://www.kimi.ai/blog/kimi-k3-1-pro",
      "imageUrl": "https://statics.kimi.ai/kimi-blogs/kimi-k3-1/20261023/benchmark-overview-v6.webp",
      "copyright": "Moonshot AI / Kimi",
      "sourceDate": "2026-10-23",
      "localPath": "public/evaluations/kimi-k3-1-pro/assets/official-benchmark-overview.webp",
      "publicPath": "/evaluations/kimi-k3-1-pro/assets/official-benchmark-overview.webp",
      "bytes": 222632,
      "sha256": "48c52c615b98e722bdf1058e200db4cafde9078c122bc12fd8b3f380dafb64c0",
      "retrievedAt": "2026-10-24",
      "originalBytes": true,
      "width": 2194,
      "height": 2982,
      "format": "webp",
      "path": "/evaluations/kimi-k3-1-pro/assets/official-benchmark-overview.webp",
      "titleZh": "Kimi 官方 14 项 benchmark 总览",
      "titleEn": "Kimi official 14-benchmark overview",
      "altZh": "Kimi 官方 14 项 benchmark 总览：Kimi K3.1 Pro 与其他模型对照",
      "altEn": "Kimi official 14-benchmark overview: Kimi K3.1 Pro and peer models",
      "captionZh": "官方最大思考档结果；含多种工具与框架口径，本站未复现。",
      "captionEn": "Vendor results at maximum effort; mixed tools and harnesses, not reproduced by TOKRACE.",
      "sourceUrl": "https://www.kimi.ai/blog/kimi-k3-1-pro",
      "originalUrl": "https://statics.kimi.ai/kimi-blogs/kimi-k3-1/20261023/benchmark-overview-v6.webp",
      "credit": "Moonshot AI / Kimi",
      "kind": "official",
      "visuallyInspected": true,
      "visuallyInspectedAt": "2026-10-24",
      "inspectionMethod": "AI assistant inspected the full original chart including labels, legends and footnotes; qualitative visual review, not an independent human rating",
      "independentlyReproducedByTokrace": false,
      "sourcePublishedAt": null,
      "sourceDateBasis": "Launch date independently dated by Artificial Analysis and reflected in dated vendor asset paths; vendor blog does not display a publication date"
    },
    {
      "id": "official-benchcad",
      "sourcePage": "https://www.kimi.ai/blog/kimi-k3-1-pro",
      "imageUrl": "https://statics.kimi.ai/kimi-blogs/kimi-k3-1/20261023/benchcad-results-v2.webp",
      "copyright": "Moonshot AI / Kimi",
      "sourceDate": "2026-10-23",
      "localPath": "public/evaluations/kimi-k3-1-pro/assets/official-benchcad.webp",
      "publicPath": "/evaluations/kimi-k3-1-pro/assets/official-benchcad.webp",
      "bytes": 31664,
      "sha256": "d4429058a72e24541fcd70cbab2e3630e3e6b8696166fcfad235b5b1d85e9b57",
      "retrievedAt": "2026-10-24",
      "originalBytes": true,
      "width": 2400,
      "height": 593,
      "format": "webp",
      "path": "/evaluations/kimi-k3-1-pro/assets/official-benchcad.webp",
      "titleZh": "官方 BenchCAD：有工具与无工具",
      "titleEn": "Official BenchCAD: with and without tools",
      "altZh": "官方 BenchCAD：有工具与无工具：Kimi K3.1 Pro 与其他模型对照",
      "altEn": "Official BenchCAD: with and without tools: Kimi K3.1 Pro and peer models",
      "captionZh": "1,000 例子集的 Voxel IoU：有工具 92.7%，无工具 72.8%。",
      "captionEn": "Voxel IoU on a 1,000-case subset: 92.7% with tools, 72.8% without.",
      "sourceUrl": "https://www.kimi.ai/blog/kimi-k3-1-pro",
      "originalUrl": "https://statics.kimi.ai/kimi-blogs/kimi-k3-1/20261023/benchcad-results-v2.webp",
      "credit": "Moonshot AI / Kimi",
      "kind": "official",
      "visuallyInspected": true,
      "visuallyInspectedAt": "2026-10-24",
      "inspectionMethod": "AI assistant inspected the full original chart including labels, legends and footnotes; qualitative visual review, not an independent human rating",
      "independentlyReproducedByTokrace": false,
      "sourcePublishedAt": null,
      "sourceDateBasis": "Launch date independently dated by Artificial Analysis and reflected in dated vendor asset paths; vendor blog does not display a publication date"
    },
    {
      "id": "official-finance-productivity",
      "sourcePage": "https://www.kimi.ai/blog/kimi-k3-1-pro",
      "imageUrl": "https://statics.kimi.ai/kimi-blogs/kimi-k3-1/20261023/finance-productivity-v4.webp",
      "copyright": "Moonshot AI / Kimi",
      "sourceDate": "2026-10-23",
      "localPath": "public/evaluations/kimi-k3-1-pro/assets/official-finance-productivity.webp",
      "publicPath": "/evaluations/kimi-k3-1-pro/assets/official-finance-productivity.webp",
      "bytes": 46718,
      "sha256": "6ff3663b2c71098223a0f29c2169d3f4e3482bb82dc59cca6e341d09294a00fe",
      "retrievedAt": "2026-10-24",
      "originalBytes": true,
      "width": 2400,
      "height": 702,
      "format": "webp",
      "path": "/evaluations/kimi-k3-1-pro/assets/official-finance-productivity.webp",
      "titleZh": "官方金融任务评测",
      "titleEn": "Official finance workflow benchmarks",
      "altZh": "官方金融任务评测：Kimi K3.1 Pro 与其他模型对照",
      "altEn": "Official finance workflow benchmarks: Kimi K3.1 Pro and peer models",
      "captionZh": "OfficeQA Pro v2 为 64.4；Frontier Finance 为 58.6。",
      "captionEn": "OfficeQA Pro v2: 64.4; Frontier Finance: 58.6.",
      "sourceUrl": "https://www.kimi.ai/blog/kimi-k3-1-pro",
      "originalUrl": "https://statics.kimi.ai/kimi-blogs/kimi-k3-1/20261023/finance-productivity-v4.webp",
      "credit": "Moonshot AI / Kimi",
      "kind": "official",
      "visuallyInspected": true,
      "visuallyInspectedAt": "2026-10-24",
      "inspectionMethod": "AI assistant inspected the full original chart including labels, legends and footnotes; qualitative visual review, not an independent human rating",
      "independentlyReproducedByTokrace": false,
      "sourcePublishedAt": null,
      "sourceDateBasis": "Launch date independently dated by Artificial Analysis and reflected in dated vendor asset paths; vendor blog does not display a publication date"
    },
    {
      "id": "official-finance-internal",
      "sourcePage": "https://www.kimi.ai/blog/kimi-k3-1-pro",
      "imageUrl": "https://kimi-img.kimi.ai/pub/slides/kimi-fs/weaver/assets/f0a2d8ff95b181942bbe5a78405058ef.webp",
      "copyright": "Moonshot AI / Kimi",
      "sourceDate": "2026-10-23",
      "localPath": "public/evaluations/kimi-k3-1-pro/assets/official-finance-internal.webp",
      "publicPath": "/evaluations/kimi-k3-1-pro/assets/official-finance-internal.webp",
      "bytes": 50140,
      "sha256": "f74ee59d0c6410c0e0e98a816db9820831484099fb3ee288cf4db96dc2a4bef9",
      "retrievedAt": "2026-10-24",
      "originalBytes": true,
      "width": 2931,
      "height": 1608,
      "format": "webp",
      "path": "/evaluations/kimi-k3-1-pro/assets/official-finance-internal.webp",
      "titleZh": "官方内部金融评测",
      "titleEn": "Official internal finance benchmarks",
      "altZh": "官方内部金融评测：Kimi K3.1 Pro 与其他模型对照",
      "altEn": "Official internal finance benchmarks: Kimi K3.1 Pro and peer models",
      "captionZh": "内部建模、投研和经营模拟，对照 K3。",
      "captionEn": "Internal modeling, research and business simulation versus K3.",
      "sourceUrl": "https://www.kimi.ai/blog/kimi-k3-1-pro",
      "originalUrl": "https://kimi-img.kimi.ai/pub/slides/kimi-fs/weaver/assets/f0a2d8ff95b181942bbe5a78405058ef.webp",
      "credit": "Moonshot AI / Kimi",
      "kind": "official",
      "visuallyInspected": true,
      "visuallyInspectedAt": "2026-10-24",
      "inspectionMethod": "AI assistant inspected the full original chart including labels, legends and footnotes; qualitative visual review, not an independent human rating",
      "independentlyReproducedByTokrace": false,
      "sourcePublishedAt": null,
      "sourceDateBasis": "Launch date independently dated by Artificial Analysis and reflected in dated vendor asset paths; vendor blog does not display a publication date"
    },
    {
      "id": "official-hallucination",
      "sourcePage": "https://www.kimi.ai/blog/kimi-k3-1-pro",
      "imageUrl": "https://statics.kimi.ai/kimi-blogs/kimi-k3-1/20261023/hallu-bench-results-v2.webp",
      "copyright": "Moonshot AI / Kimi",
      "sourceDate": "2026-10-23",
      "localPath": "public/evaluations/kimi-k3-1-pro/assets/official-hallucination.webp",
      "publicPath": "/evaluations/kimi-k3-1-pro/assets/official-hallucination.webp",
      "bytes": 56622,
      "sha256": "a2d382925fc460ea83a4d236f4861d926011d3710ec0378a27742e0659341ab1",
      "retrievedAt": "2026-10-24",
      "originalBytes": true,
      "width": 2400,
      "height": 743,
      "format": "webp",
      "path": "/evaluations/kimi-k3-1-pro/assets/official-hallucination.webp",
      "titleZh": "官方幻觉压力测试",
      "titleEn": "Official hallucination stress tests",
      "altZh": "官方幻觉压力测试：Kimi K3.1 Pro 与其他模型对照",
      "altEn": "Official hallucination stress tests: Kimi K3.1 Pro and peer models",
      "captionZh": "声明级错误率；压力测试不代表日常错误率。",
      "captionEn": "Claim-level errors under stress tests; not everyday error rates.",
      "sourceUrl": "https://www.kimi.ai/blog/kimi-k3-1-pro",
      "originalUrl": "https://statics.kimi.ai/kimi-blogs/kimi-k3-1/20261023/hallu-bench-results-v2.webp",
      "credit": "Moonshot AI / Kimi",
      "kind": "official",
      "visuallyInspected": true,
      "visuallyInspectedAt": "2026-10-24",
      "inspectionMethod": "AI assistant inspected the full original chart including labels, legends and footnotes; qualitative visual review, not an independent human rating",
      "independentlyReproducedByTokrace": false,
      "sourcePublishedAt": null,
      "sourceDateBasis": "Launch date independently dated by Artificial Analysis and reflected in dated vendor asset paths; vendor blog does not display a publication date"
    }
  ],
  "attributionNotice": "Original charts remain copyright their respective owners; source links and original bytes retained. Benchmark results are attributed reports and have not been independently reproduced by TOKRACE."
}