{
  "schema_version": 1,
  "report_date": "2026-06-23",
  "title": "AI 日报 2026-06-23",
  "summary": "今天最值得看的主线有 OpenAI更新AI 产品、平台或工程实践；OpenAI披露安全治理和平台控制变化；Alibaba Cloud披露 agent 与开发者工具能力；热门博客这轮主要看 agent 和开发工具的落地边界。",
  "hero_highlights": [
    {
      "title": "OpenAI更新AI 产品、平台或工程实践",
      "url": "https://openai.com/index/omio",
      "reason": "信号集中在产品入口、采购时机和路线图影响",
      "what_happened": "OpenAI更新AI 产品、平台或工程实践，材料覆盖功能变化、使用场景、接入方式、限制条件和后续部署边界，边界落在公开材料仍需要回到原文核对入口、权限、价格和适用范围",
      "why_watch": "信号集中在产品入口、采购时机和路线图影响",
      "category": "product_tool",
      "source_item_ref": "https://openai.com/index/omio"
    },
    {
      "title": "Alibaba Cloud披露 agent 与开发者工具能力",
      "url": "https://www.alibabacloud.com/blog/coding-agent-second-half-from-individual-efficiency-to-organization-level-r%26d-system_603287",
      "reason": "工程侧价值集中在 agent、开发工具和自动化工作流接入",
      "what_happened": "Alibaba Cloud发布面向软件团队的 agent 平台，材料覆盖代码仓库上下文、工作流编排、IDE 集成、企业控制和评估钩子，边界落在工程落地取决于仓库权限、上下文质量、评估回放和团队治理",
      "why_watch": "工程侧价值集中在 agent、开发工具和自动化工作流接入",
      "category": "china_open_source_community",
      "source_item_ref": "https://www.alibabacloud.com/blog/coding-agent-second-half-from-individual-efficiency-to-organization-level-r%26d-system_603287"
    },
    {
      "title": "NVIDIA披露模型评估和研究结果",
      "url": "https://blogs.nvidia.com/blog/nairr-scientific-research-ai-infrastructure/",
      "reason": "NVIDIA披露模型能力和评估方法更新，重点落在能力边界、评估设置、数据来源、使用场景和限制说明。更有价值的信息是模型能力、评估设置、数据来源和限制说明，判断这类方案时还要看结论仍要依赖可复现评测、真实任务和公开限制。文章梳理模型评测或研究结论怎样改变能力边界、成本预期和可靠性判断",
      "what_happened": "NVIDIA披露模型能力和评估方法更新，重点落在能力边界、评估设置、数据来源、使用场景和限制说明。更有价值的信息是模型能力、评估设置、数据来源和限制说明，判断这类方案时还要看结论仍要依赖可复现评测、真实任务和公开限制。文章梳理模型评测或研究结论怎样改变能力边界、成本预期和可靠性判断",
      "why_watch": "NVIDIA披露模型能力和评估方法更新，重点落在能力边界、评估设置、数据来源、使用场景和限制说明。更有价值的信息是模型能力、评估设置、数据来源和限制说明，判断这类方案时还要看结论仍要依赖可复现评测、真实任务和公开限制。文章梳理模型评测或研究结论怎样改变能力边界、成本预期和可靠性判断",
      "category": "research_safety",
      "source_item_ref": "https://blogs.nvidia.com/blog/nairr-scientific-research-ai-infrastructure/"
    }
  ],
  "stories": [
    {
      "story_id": "story-content-openai-news-how-omio-is-building-the-future-of-conversational-travel",
      "title": "OpenAI News RSS: Omio",
      "importance": "general",
      "trend": "AI products and developer workflow",
      "event_date": "2026-06-23",
      "primary_entity": "OpenAI News RSS",
      "event_type": "signal",
      "object": "OpenAI更新AI 产品、平台或工程实践",
      "what_happened": "OpenAI更新AI 产品、平台或工程实践，材料覆盖功能变化、使用场景、接入方式、限制条件和后续部署边界，边界落在公开材料仍需要回到原文核对入口、权限、价格和适用范围。",
      "why_it_matters": "信号集中在产品入口、采购时机和路线图影响",
      "evidence_level": "multi_source",
      "sources": [
        {
          "label": "OpenAI News RSS",
          "url": "https://openai.com/index/omio",
          "type": "official"
        },
        {
          "label": "OpenAI Blog RSS",
          "url": "https://openai.com/index/omio",
          "type": "official"
        },
        {
          "label": "OpenAI Company News RSS",
          "url": "https://openai.com/index/omio",
          "type": "official"
        }
      ]
    },
    {
      "story_id": "story-content-openai-news-daybreak-tools-for-securing-every-organization-in-the-world",
      "title": "OpenAI说明安全治理和平台控制变化",
      "importance": "general",
      "trend": "AI industry",
      "event_date": "2026-06-22",
      "primary_entity": "OpenAI News RSS",
      "event_type": "signal",
      "object": "OpenAI披露安全治理和平台控制变化",
      "what_happened": "OpenAI更新agent 工作流和开发工具能力，材料覆盖任务编排、上下文、权限控制、工程集成和失败恢复，边界落在落地质量取决于权限模型、评估回放、团队流程和可观测性。",
      "why_it_matters": "工程侧价值集中在 agent、开发工具和自动化工作流接入",
      "evidence_level": "multi_source",
      "sources": [
        {
          "label": "OpenAI News RSS",
          "url": "https://openai.com/index/daybreak-securing-the-world",
          "type": "official"
        },
        {
          "label": "OpenAI Blog RSS",
          "url": "https://openai.com/index/daybreak-securing-the-world",
          "type": "official"
        },
        {
          "label": "OpenAI Company News RSS",
          "url": "https://openai.com/index/daybreak-securing-the-world",
          "type": "official"
        }
      ]
    },
    {
      "story_id": "story-content-alibaba-cloud-blog-coding-agent-second-half-from-individual-efficiency-t",
      "title": "Alibaba Cloud更新agent 与开发者工具能力",
      "importance": "general",
      "trend": "AI products and developer workflow",
      "event_date": "2026-06-23",
      "primary_entity": "Alibaba Cloud Blog",
      "event_type": "signal",
      "object": "Alibaba Cloud披露 agent 与开发者工具能力",
      "what_happened": "Alibaba Cloud发布面向软件团队的 agent 平台，材料覆盖代码仓库上下文、工作流编排、IDE 集成、企业控制和评估钩子，边界落在工程落地取决于仓库权限、上下文质量、评估回放和团队治理。",
      "why_it_matters": "工程侧价值集中在 agent、开发工具和自动化工作流接入",
      "evidence_level": "primary",
      "sources": [
        {
          "label": "Alibaba Cloud Blog",
          "url": "https://www.alibabacloud.com/blog/coding-agent-second-half-from-individual-efficiency-to-organization-level-r%26d-system_603287",
          "type": "official"
        }
      ]
    },
    {
      "story_id": "story-content-github-changelog-new-features-and-claude-as-agent-provider-preview-in-je",
      "title": "GitHub Changelog更新agent 与开发者工具能力",
      "importance": "general",
      "trend": "open source AI",
      "event_date": "2026-06-22",
      "primary_entity": "GitHub Changelog",
      "event_type": "update",
      "object": "GitHub Changelog披露 agent 与开发者工具能力",
      "what_happened": "该开源项目推出企业 agent 工作流系统，材料覆盖任务路由、业务流程自动化、护栏和组织集成入口，边界落在企业采用时仍要处理权限、审计、流程接入和失败恢复。",
      "why_it_matters": "工程价值集中在代码、权重、示例和生态复用条件",
      "evidence_level": "primary",
      "sources": [
        {
          "label": "GitHub Changelog",
          "url": "https://github.blog/changelog/2026-06-22-new-features-and-claude-as-agent-provider-preview-in-jetbrains-ides",
          "type": "github"
        }
      ]
    },
    {
      "story_id": "story-content-microsoft-official-blog-powering-the-next-wave-of-ai-expanding-capacity",
      "title": "Official Microsoft Blog: Powering The Next Wave Of AI Expanding Capacity With Our New Datacenter In Pecos",
      "importance": "general",
      "trend": "AI products and developer workflow",
      "event_date": "2026-06-22",
      "primary_entity": "Official Microsoft Blog",
      "event_type": "signal",
      "object": "微软研究院更新AI 产品、平台或工程实践",
      "what_happened": "微软研究院更新AI 产品、平台或工程实践，材料覆盖功能变化、使用场景、接入方式、限制条件和后续部署边界，边界落在公开材料仍需要回到原文核对入口、权限、价格和适用范围。",
      "why_it_matters": "信号集中在产品入口、采购时机和路线图影响",
      "evidence_level": "primary",
      "sources": [
        {
          "label": "Official Microsoft Blog",
          "url": "https://blogs.microsoft.com/blog/2026/06/22/powering-the-next-wave-of-ai-expanding-capacity-with-our-new-datacenter-in-pecos/",
          "type": "official"
        }
      ]
    },
    {
      "story_id": "story-follow-builders-x-peter-yang-i-m-reading-this-and-i-still-don-t-get-what-a-dynam",
      "title": "follow-builders X发布 Claude Code agent 工具工作流",
      "importance": "general",
      "trend": "AI industry",
      "event_date": "2026-06-23",
      "primary_entity": "follow-builders X feed",
      "event_type": "signal",
      "object": "follow-builders X披露 Claude Code agent 工具工作流",
      "what_happened": "follow-builders X更新agent 工作流和开发工具能力，材料覆盖任务编排、上下文、权限控制、工程集成和失败恢复，边界落在落地质量取决于权限模型、评估回放、团队流程和可观测性。",
      "why_it_matters": "工程侧价值集中在 agent、开发工具和自动化工作流接入",
      "evidence_level": "primary",
      "sources": [
        {
          "label": "follow-builders X feed",
          "url": "https://x.com/petergyang/status/2069267139576693028",
          "type": "primary"
        }
      ]
    },
    {
      "story_id": "story-content-nvidia-newsroom-rss-nvidia-brings-trusted-24-7-ai-agents-to-telecom-oper",
      "title": "NVIDIA更新agent 与开发者工具能力",
      "importance": "general",
      "trend": "AI content workflow",
      "event_date": "2026-06-23",
      "primary_entity": "NVIDIA Newsroom RSS",
      "event_type": "signal",
      "object": "NVIDIA披露 agent 与开发者工具能力",
      "what_happened": "NVIDIA更新agent 工作流和开发工具能力，材料覆盖任务编排、上下文、权限控制、工程集成和失败恢复，边界落在落地质量取决于权限模型、评估回放、团队流程和可观测性。",
      "why_it_matters": "内容侧价值集中在素材生成、创作者工具链成本和交付方式",
      "evidence_level": "primary",
      "sources": [
        {
          "label": "NVIDIA Newsroom RSS",
          "url": "https://blogs.nvidia.com/blog/telecom-ai-agents-dtw-ignite-2026/",
          "type": "official"
        }
      ]
    },
    {
      "story_id": "story-content-aws-machine-learning-building-pay-per-intelligence-for-ai-agents-how-amp",
      "title": "AWS更新agent 与开发者工具能力",
      "importance": "general",
      "trend": "AI industry",
      "event_date": "2026-06-22",
      "primary_entity": "AWS Machine Learning Blog",
      "event_type": "signal",
      "object": "AWS披露 agent 与开发者工具能力",
      "what_happened": "AWS更新agent 工作流和开发工具能力，材料覆盖任务编排、上下文、权限控制、工程集成和失败恢复，边界落在落地质量取决于权限模型、评估回放、团队流程和可观测性。",
      "why_it_matters": "工程侧价值集中在 agent、开发工具和自动化工作流接入",
      "evidence_level": "primary",
      "sources": [
        {
          "label": "AWS Machine Learning Blog",
          "url": "https://aws.amazon.com/blogs/machine-learning/building-pay-per-intelligence-for-ai-agents-how-ampersend-uses-amazon-bedrock-agentcore-payments/",
          "type": "official"
        }
      ]
    }
  ],
  "main_items": [
    {
      "title": "OpenAI News RSS: Omio",
      "editorial_category": "product_radar",
      "event_date": "2026-06-23",
      "url": "https://openai.com/index/omio",
      "source": "OpenAI News RSS",
      "tier": "T0",
      "entities": [
        "OpenAI News RSS"
      ],
      "summary": "OpenAI更新AI 产品、平台或工程实践，材料覆盖功能变化、使用场景、接入方式、限制条件和后续部署边界，边界落在公开材料仍需要回到原文核对入口、权限、价格和适用范围。",
      "bullets": [
        "**OpenAI更新AI 产品、平台或工程实践**：材料把AI 产品、平台或工程实践落到功能变化、使用场景、接入方式、限制条件和后续部署边界，已披露事实集中在功能变化、适用场景、接入方式和限制条件。",
        "当前公开的是产品入口、适用对象、价格地区限制、权限要求和后续上线节奏。",
        "这会改变产品和采购团队安排试用、预算审批、替换工具和风险复盘的优先级。"
      ],
      "importance": "general",
      "image_urls": []
    },
    {
      "title": "OpenAI说明安全治理和平台控制变化",
      "editorial_category": "ai_industry",
      "event_date": "2026-06-22",
      "url": "https://openai.com/index/daybreak-securing-the-world",
      "source": "OpenAI News RSS",
      "tier": "T0",
      "entities": [
        "OpenAI News RSS"
      ],
      "summary": "OpenAI更新agent 工作流和开发工具能力，材料覆盖任务编排、上下文、权限控制、工程集成和失败恢复，边界落在落地质量取决于权限模型、评估回放、团队流程和可观测性。",
      "bullets": [
        "**OpenAI披露安全治理和平台控制变化**：材料把agent 工作流和开发工具能力落到任务编排、上下文、权限控制、工程集成和失败恢复，已披露事实集中在agent 工作流、开发工具入口、权限控制和工程集成。",
        "当前公开的是部署方式、权限、上下文管理和失败恢复边界。",
        "这会影响研发团队安排 agent 工具接入顺序、权限设计、评估回放和落地成本。"
      ],
      "importance": "general",
      "image_urls": []
    },
    {
      "title": "Alibaba Cloud更新agent 与开发者工具能力",
      "editorial_category": "engineering_toolchain",
      "event_date": "2026-06-23",
      "url": "https://www.alibabacloud.com/blog/coding-agent-second-half-from-individual-efficiency-to-organization-level-r%26d-system_603287",
      "source": "Alibaba Cloud Blog",
      "tier": "T0",
      "entities": [
        "Alibaba Cloud Blog"
      ],
      "summary": "Alibaba Cloud发布面向软件团队的 agent 平台，材料覆盖代码仓库上下文、工作流编排、IDE 集成、企业控制和评估钩子，边界落在工程落地取决于仓库权限、上下文质量、评估回放和团队治理。",
      "bullets": [
        "**Alibaba Cloud披露 agent 与开发者工**：材料把面向软件团队的 agent 平台落到代码仓库上下文、工作流编排、IDE 集成、企业控制和评估钩子，已披露事实集中在coding agent、仓库上下文、IDE 集成和评估钩子。",
        "当前公开的是部署方式、权限、上下文管理和失败恢复边界。",
        "这会影响研发团队安排 agent 工具接入顺序、权限设计、评估回放和落地成本。"
      ],
      "importance": "general",
      "image_urls": []
    },
    {
      "title": "GitHub Changelog更新agent 与开发者工具能力",
      "editorial_category": "open_source",
      "event_date": "2026-06-22",
      "url": "https://github.blog/changelog/2026-06-22-new-features-and-claude-as-agent-provider-preview-in-jetbrains-ides",
      "source": "GitHub Changelog",
      "tier": "T2",
      "entities": [
        "GitHub Changelog"
      ],
      "summary": "该开源项目推出企业 agent 工作流系统，材料覆盖任务路由、业务流程自动化、护栏和组织集成入口，边界落在企业采用时仍要处理权限、审计、流程接入和失败恢复。",
      "bullets": [
        "**GitHub Changelog披露 agent 与开**：材料把企业 agent 工作流系统落到任务路由、业务流程自动化、护栏和组织集成入口，已披露事实集中在任务路由、业务流程、组织护栏和系统集成点。",
        "当前公开的是代码接口、许可证、维护节奏、集成门槛和团队可复用边界。",
        "这会影响研发团队是否把它放进 PoC、评估清单、现有工作流或长期维护计划。"
      ],
      "importance": "general",
      "image_urls": []
    },
    {
      "title": "Official Microsoft Blog: Powering The Next Wave Of AI Expanding Capacity With Our New Datacenter In Pecos",
      "editorial_category": "product_radar",
      "event_date": "2026-06-22",
      "url": "https://blogs.microsoft.com/blog/2026/06/22/powering-the-next-wave-of-ai-expanding-capacity-with-our-new-datacenter-in-pecos/",
      "source": "Official Microsoft Blog",
      "tier": "T0",
      "entities": [
        "Official Microsoft Blog"
      ],
      "summary": "微软研究院更新AI 产品、平台或工程实践，材料覆盖功能变化、使用场景、接入方式、限制条件和后续部署边界，边界落在公开材料仍需要回到原文核对入口、权限、价格和适用范围。",
      "bullets": [
        "**微软研究院更新AI 产品、平台或工程实践**：材料把AI 产品、平台或工程实践落到功能变化、使用场景、接入方式、限制条件和后续部署边界，已披露事实集中在功能变化、适用场景、接入方式和限制条件。",
        "当前公开的是产品入口、适用对象、价格地区限制、权限要求和后续上线节奏。",
        "这会改变产品和采购团队安排试用、预算审批、替换工具和风险复盘的优先级。"
      ],
      "importance": "general",
      "image_urls": []
    },
    {
      "title": "follow-builders X发布 Claude Code agent 工具工作流",
      "editorial_category": "ai_industry",
      "event_date": "2026-06-23",
      "url": "https://x.com/petergyang/status/2069267139576693028",
      "source": "follow-builders X feed",
      "tier": "T0",
      "entities": [
        "follow-builders X feed"
      ],
      "summary": "follow-builders X更新agent 工作流和开发工具能力，材料覆盖任务编排、上下文、权限控制、工程集成和失败恢复，边界落在落地质量取决于权限模型、评估回放、团队流程和可观测性。",
      "bullets": [
        "**follow-builders X披露 Claude **：材料把agent 工作流和开发工具能力落到任务编排、上下文、权限控制、工程集成和失败恢复，已披露事实集中在agent 工作流、开发工具入口、权限控制和工程集成。",
        "当前公开的是部署方式、权限、上下文管理和失败恢复边界。",
        "这会影响研发团队安排 agent 工具接入顺序、权限设计、评估回放和落地成本。"
      ],
      "importance": "general",
      "image_urls": []
    },
    {
      "title": "NVIDIA更新agent 与开发者工具能力",
      "editorial_category": "content_aigc",
      "event_date": "2026-06-23",
      "url": "https://blogs.nvidia.com/blog/telecom-ai-agents-dtw-ignite-2026/",
      "source": "NVIDIA Newsroom RSS",
      "tier": "T0",
      "entities": [
        "NVIDIA Newsroom RSS"
      ],
      "summary": "NVIDIA更新agent 工作流和开发工具能力，材料覆盖任务编排、上下文、权限控制、工程集成和失败恢复，边界落在落地质量取决于权限模型、评估回放、团队流程和可观测性。",
      "bullets": [
        "**NVIDIA披露 agent 与开发者工具能力**：材料把agent 工作流和开发工具能力落到任务编排、上下文、权限控制、工程集成和失败恢复，已披露事实集中在agent 工作流、开发工具入口、权限控制和工程集成。",
        "当前公开的是试用入口、样例质量、版权边界、价格信息和生产可用范围。",
        "这会影响内容团队判断创作工具能否进入正式生产流程、预算清单和版权审查。"
      ],
      "importance": "general",
      "image_urls": []
    },
    {
      "title": "AWS更新agent 与开发者工具能力",
      "editorial_category": "ai_industry",
      "event_date": "2026-06-22",
      "url": "https://aws.amazon.com/blogs/machine-learning/building-pay-per-intelligence-for-ai-agents-how-ampersend-uses-amazon-bedrock-agentcore-payments/",
      "source": "AWS Machine Learning Blog",
      "tier": "T0",
      "entities": [
        "AWS Machine Learning Blog"
      ],
      "summary": "AWS更新agent 工作流和开发工具能力，材料覆盖任务编排、上下文、权限控制、工程集成和失败恢复，边界落在落地质量取决于权限模型、评估回放、团队流程和可观测性。",
      "bullets": [
        "**AWS披露 agent 与开发者工具能力**：材料把agent 工作流和开发工具能力落到任务编排、上下文、权限控制、工程集成和失败恢复，已披露事实集中在agent 工作流、开发工具入口、权限控制和工程集成。",
        "当前公开的是部署方式、权限、上下文管理和失败恢复边界。",
        "这会影响研发团队安排 agent 工具接入顺序、权限设计、评估回放和落地成本。"
      ],
      "importance": "general",
      "image_urls": []
    }
  ],
  "github_trending": [
    {
      "name": "DeusData/codebase-memory-mcp",
      "repo": "DeusData/codebase-memory-mcp",
      "readme_cache": {
        "key": "github-readme/deusdata/codebase-memory-mcp/main/unknown",
        "hit": true,
        "repo": "deusdata/codebase-memory-mcp",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/DeusData/codebase-memory-mcp/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/DeusData/codebase-memory-mcp",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 1,
      "source_rank": 1,
      "source_scope": "weekly:all",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "notable",
      "description": "DeusData/codebase-memory-mcp 本周出现在开源榜单 weekly #1，本周 +7,560 stars；当前只能确认榜单动量，正式采用前还要核对 README、许可证、维护状态和 issue 反馈。"
    },
    {
      "name": "calesthio/OpenMontage",
      "repo": "calesthio/OpenMontage",
      "readme_cache": {
        "key": "github-readme/calesthio/openmontage/main/unknown",
        "hit": true,
        "repo": "calesthio/openmontage",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/calesthio/OpenMontage/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/calesthio/OpenMontage",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 2,
      "source_rank": 2,
      "source_scope": "weekly:all",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "notable",
      "description": "OpenMontage 是代理式自动化、工具调用和开发者工作流相关的开源项目，公开说明提到Agent 构建、工具调用和工作流编排等能力，并提供部署说明；评估时核对安装步骤、许可证、示例质量、近期维护和接入边界。 它把相关能力沉淀为代码、示例和集成入口，方便和同类方案做功能与工程成本比较。"
    },
    {
      "name": "Panniantong/Agent-Reach",
      "repo": "Panniantong/Agent-Reach",
      "readme_cache": {
        "key": "github-readme/panniantong/agent-reach/main/unknown",
        "hit": true,
        "repo": "panniantong/agent-reach",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/Panniantong/Agent-Reach/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/Panniantong/Agent-Reach",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 3,
      "source_rank": 3,
      "source_scope": "weekly:all",
      "previous_rank": 8,
      "rank_delta": 5,
      "trend": "up",
      "importance": "notable",
      "description": "Panniantong/Agent-Reach 本周出现在开源榜单 weekly #3，本周 +8,108 stars；当前只能确认榜单动量，正式采用前还要核对 README、许可证、维护状态和 issue 反馈。"
    },
    {
      "name": "n0-computer/iroh",
      "repo": "n0-computer/iroh",
      "readme_cache": {
        "key": "github-readme/n0-computer/iroh/main/unknown",
        "hit": true,
        "repo": "n0-computer/iroh",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/n0-computer/iroh/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/n0-computer/iroh",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 4,
      "source_rank": 4,
      "source_scope": "weekly:all",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general",
      "description": "n0-computer/iroh 本周出现在开源榜单 weekly #4，本周 +1,806 stars；当前只能确认榜单动量，正式采用前还要核对 README、许可证、维护状态和 issue 反馈。"
    },
    {
      "name": "google-research/timesfm",
      "repo": "google-research/timesfm",
      "readme_cache": {
        "key": "github-readme/google-research/timesfm/master/unknown",
        "hit": true,
        "repo": "google-research/timesfm",
        "sha": "unknown",
        "default_branch": "master",
        "source_url": "https://raw.githubusercontent.com/google-research/timesfm/master/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/google-research/timesfm",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 5,
      "source_rank": 5,
      "source_scope": "weekly:all",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general",
      "description": "google-research/timesfm 本周出现在开源榜单 weekly #5，本周 +4,259 stars；当前只能确认榜单动量，正式采用前还要核对 README、许可证、维护状态和 issue 反馈。"
    },
    {
      "name": "iptv-org/iptv",
      "repo": "iptv-org/iptv",
      "readme_cache": {
        "key": "github-readme/iptv-org/iptv/master/unknown",
        "hit": true,
        "repo": "iptv-org/iptv",
        "sha": "unknown",
        "default_branch": "master",
        "source_url": "https://raw.githubusercontent.com/iptv-org/iptv/master/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/iptv-org/iptv",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 6,
      "source_rank": 6,
      "source_scope": "weekly:all",
      "previous_rank": 5,
      "rank_delta": -1,
      "trend": "down",
      "importance": "general",
      "description": "iptv-org/iptv 本周出现在开源榜单 weekly #6，本周 +5,017 stars；当前只能确认榜单动量，正式采用前还要核对 README、许可证、维护状态和 issue 反馈。"
    },
    {
      "name": "asgeirtj/system_prompts_leaks",
      "repo": "asgeirtj/system_prompts_leaks",
      "readme_cache": {
        "key": "github-readme/asgeirtj/system_prompts_leaks/main/unknown",
        "hit": true,
        "repo": "asgeirtj/system_prompts_leaks",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/asgeirtj/system_prompts_leaks/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/asgeirtj/system_prompts_leaks",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 7,
      "source_rank": 7,
      "source_scope": "weekly:all",
      "previous_rank": 9,
      "rank_delta": 2,
      "trend": "up",
      "importance": "general",
      "description": "asgeirtj/system_prompts_leaks 本周出现在开源榜单 weekly #7，本周 +2,612 stars；当前只能确认榜单动量，正式采用前还要核对 README、许可证、维护状态和 issue 反馈。"
    },
    {
      "name": "withastro/flue",
      "repo": "withastro/flue",
      "readme_cache": {
        "key": "github-readme/withastro/flue/main/unknown",
        "hit": true,
        "repo": "withastro/flue",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/withastro/flue/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/withastro/flue",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 8,
      "source_rank": 8,
      "source_scope": "weekly:all",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general",
      "description": "withastro/flue 本周出现在开源榜单 weekly #8，本周 +1,413 stars；当前只能确认榜单动量，正式采用前还要核对 README、许可证、维护状态和 issue 反馈。"
    },
    {
      "name": "NVIDIA/SkillSpector",
      "repo": "NVIDIA/SkillSpector",
      "readme_cache": {
        "key": "github-readme/nvidia/skillspector/main/unknown",
        "hit": true,
        "repo": "nvidia/skillspector",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/NVIDIA/SkillSpector/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/NVIDIA/SkillSpector",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 9,
      "source_rank": 9,
      "source_scope": "weekly:all",
      "previous_rank": 2,
      "rank_delta": -7,
      "trend": "down",
      "importance": "general",
      "description": "NVIDIA/SkillSpector 本周出现在开源榜单 weekly #9，本周 +3,302 stars；当前只能确认榜单动量，正式采用前还要核对 README、许可证、维护状态和 issue 反馈。"
    },
    {
      "name": "teslamate-org/teslamate",
      "repo": "teslamate-org/teslamate",
      "readme_cache": {
        "key": "github-readme/teslamate-org/teslamate/main/unknown",
        "hit": true,
        "repo": "teslamate-org/teslamate",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/teslamate-org/teslamate/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/teslamate-org/teslamate",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 10,
      "source_rank": 10,
      "source_scope": "weekly:all",
      "previous_rank": 2,
      "rank_delta": -8,
      "trend": "down",
      "importance": "general",
      "description": "teslamate-org/teslamate 本周出现在开源榜单 weekly #10，本周 +401 stars；当前只能确认榜单动量，正式采用前还要核对 README、许可证、维护状态和 issue 反馈。"
    },
    {
      "name": "microsoft/presidio",
      "repo": "microsoft/presidio",
      "readme_fetch_status": "failed",
      "readme_error": "HTTP 404",
      "url": "https://github.com/microsoft/presidio",
      "event_date": "2026-06-23",
      "source": "GitHub Trending Python weekly",
      "language": "python",
      "window": "weekly",
      "rank": 11,
      "source_rank": 6,
      "source_scope": "weekly:python",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general",
      "description": "microsoft/presidio 本周出现在开源榜单 Python weekly #11，本周 +827 stars；当前只能确认榜单动量，正式采用前还要核对 README、许可证、维护状态和 issue 反馈。"
    },
    {
      "name": "meshery/meshery",
      "repo": "meshery/meshery",
      "readme_cache": {
        "key": "github-readme/meshery/meshery/master/unknown",
        "hit": true,
        "repo": "meshery/meshery",
        "sha": "unknown",
        "default_branch": "master",
        "source_url": "https://raw.githubusercontent.com/meshery/meshery/master/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/meshery/meshery",
      "event_date": "2026-06-23",
      "source": "GitHub Trending TypeScript weekly",
      "language": "typescript",
      "window": "weekly",
      "rank": 12,
      "source_rank": 8,
      "source_scope": "weekly:typescript",
      "previous_rank": 4,
      "rank_delta": -4,
      "trend": "down",
      "importance": "general",
      "description": "meshery 是代理式自动化、工具调用和开发者工作流相关的开源项目，公开说明提到工具调用和工作流编排等能力，并提供部署说明；评估时核对安装步骤、许可证、示例质量、近期维护和接入边界。 它把相关能力沉淀为代码、示例和集成入口，方便和同类方案做功能与工程成本比较。"
    },
    {
      "name": "swc-project/swc",
      "repo": "swc-project/swc",
      "readme_cache": {
        "key": "github-readme/swc-project/swc/main/unknown",
        "hit": true,
        "repo": "swc-project/swc",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/swc-project/swc/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/swc-project/swc",
      "event_date": "2026-06-23",
      "source": "GitHub Trending Rust weekly",
      "language": "rust",
      "window": "weekly",
      "rank": 13,
      "source_rank": 2,
      "source_scope": "weekly:rust",
      "previous_rank": 4,
      "rank_delta": 2,
      "trend": "up",
      "importance": "general",
      "description": "swc-project/swc 本周出现在开源榜单 Rust weekly #13，本周 +258 stars；当前只能确认榜单动量，正式采用前还要核对 README、许可证、维护状态和 issue 反馈。"
    },
    {
      "name": "getlago/lago",
      "repo": "getlago/lago",
      "readme_cache": {
        "key": "github-readme/getlago/lago/main/unknown",
        "hit": true,
        "repo": "getlago/lago",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/getlago/lago/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/getlago/lago",
      "event_date": "2026-06-23",
      "source": "GitHub Trending Go weekly",
      "language": "go",
      "window": "weekly",
      "rank": 14,
      "source_rank": 1,
      "source_scope": "weekly:go",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general",
      "description": "getlago/lago 本周出现在开源榜单 Go weekly #14，本周 +209 stars；当前只能确认榜单动量，正式采用前还要核对 README、许可证、维护状态和 issue 反馈。"
    },
    {
      "name": "Stirling-Tools/Stirling-PDF",
      "repo": "Stirling-Tools/Stirling-PDF",
      "readme_cache": {
        "key": "github-readme/stirling-tools/stirling-pdf/main/unknown",
        "hit": true,
        "repo": "stirling-tools/stirling-pdf",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/Stirling-Tools/Stirling-PDF/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/Stirling-Tools/Stirling-PDF",
      "event_date": "2026-06-23",
      "source": "GitHub Trending Java weekly",
      "language": "java",
      "window": "weekly",
      "rank": 15,
      "source_rank": 1,
      "source_scope": "weekly:java",
      "previous_rank": 13,
      "rank_delta": 12,
      "trend": "up",
      "importance": "general",
      "description": "Stirling-PDF 是代理式自动化、工具调用和开发者工作流相关的开源项目，公开说明提到工具调用和工作流编排、API/SDK 适配等能力，并提供部署说明；评估时核对安装步骤、许可证、示例质量、近期维护和接入边界。 它把相关能力沉淀为代码、示例和集成入口，方便和同类方案做功能与工程成本比较。"
    },
    {
      "name": "google/agents-cli",
      "repo": "google/agents-cli",
      "readme_cache": {
        "key": "github-readme/google/agents-cli/main/unknown",
        "hit": true,
        "repo": "google/agents-cli",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/google/agents-cli/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/google/agents-cli",
      "event_date": "2026-06-23",
      "source": "GitHub Trending Python weekly",
      "language": "python",
      "window": "weekly",
      "rank": 16,
      "source_rank": 7,
      "source_scope": "weekly:python",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general",
      "description": "google/agents-cli 本周出现在开源榜单 Python weekly #16，本周 +168 stars；当前只能确认榜单动量，正式采用前还要核对 README、许可证、维护状态和 issue 反馈。"
    },
    {
      "name": "jamiepine/voicebox",
      "repo": "jamiepine/voicebox",
      "readme_cache": {
        "key": "github-readme/jamiepine/voicebox/main/unknown",
        "hit": true,
        "repo": "jamiepine/voicebox",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/jamiepine/voicebox/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/jamiepine/voicebox",
      "event_date": "2026-06-23",
      "source": "GitHub Trending TypeScript weekly",
      "language": "typescript",
      "window": "weekly",
      "rank": 17,
      "source_rank": 9,
      "source_scope": "weekly:typescript",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general",
      "description": "voicebox 是代理式自动化、工具调用和开发者工作流相关的开源项目，公开说明提到Agent 构建、API/SDK 适配等能力，并提供示例；评估时核对安装步骤、许可证、示例质量、近期维护和接入边界。 它把相关能力沉淀为代码、示例和集成入口，方便和同类方案做功能与工程成本比较。"
    },
    {
      "name": "Universal-Debloater-Alliance/universal-android-debloater-next-generation",
      "repo": "Universal-Debloater-Alliance/universal-android-debloater-next-generation",
      "readme_cache": {
        "key": "github-readme/universal-debloater-alliance/universal-android-debloater-next-generation/main/unknown",
        "hit": true,
        "repo": "universal-debloater-alliance/universal-android-debloater-next-generation",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/Universal-Debloater-Alliance/universal-android-debloater-next-generation/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/Universal-Debloater-Alliance/universal-android-debloater-next-generation",
      "event_date": "2026-06-23",
      "source": "GitHub Trending Rust weekly",
      "language": "rust",
      "window": "weekly",
      "rank": 18,
      "source_rank": 3,
      "source_scope": "weekly:rust",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general",
      "description": "Universal-Debloater-Alliance/universal-android-debloater-next-generation 本周出现在开源榜单 Rust weekly #18，本周 +1,163 stars；当前只能确认榜单动量，正式采用前还要核对 README、许可证、维护状态和 issue 反馈。"
    },
    {
      "name": "everywall/ladder",
      "repo": "everywall/ladder",
      "readme_cache": {
        "key": "github-readme/everywall/ladder/main/unknown",
        "hit": true,
        "repo": "everywall/ladder",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/everywall/ladder/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/everywall/ladder",
      "event_date": "2026-06-23",
      "source": "GitHub Trending Go weekly",
      "language": "go",
      "window": "weekly",
      "rank": 19,
      "source_rank": 2,
      "source_scope": "weekly:go",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general",
      "description": "everywall/ladder 本周出现在开源榜单 Go weekly #19，本周 +439 stars；当前只能确认榜单动量，正式采用前还要核对 README、许可证、维护状态和 issue 反馈。"
    },
    {
      "name": "apache/seatunnel",
      "repo": "apache/seatunnel",
      "readme_cache": {
        "key": "github-readme/apache/seatunnel/master/unknown",
        "hit": true,
        "repo": "apache/seatunnel",
        "sha": "unknown",
        "default_branch": "master",
        "source_url": "https://raw.githubusercontent.com/apache/seatunnel/master/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/apache/seatunnel",
      "event_date": "2026-06-23",
      "source": "GitHub Trending Java weekly",
      "language": "java",
      "window": "weekly",
      "rank": 20,
      "source_rank": 2,
      "source_scope": "weekly:java",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general",
      "description": "apache/seatunnel 本周出现在开源榜单 Java weekly #20，本周 +43 stars；当前只能确认榜单动量，正式采用前还要核对 README、许可证、维护状态和 issue 反馈。"
    }
  ],
  "huggingface_trending": [],
  "model_releases": [],
  "hot_blogs": [
    {
      "title": "NVIDIA披露 agent 与开发者工具能力",
      "editorial_category": "viewpoint_analysis",
      "url": "https://developer.nvidia.com/blog/how-telcos-build-autonomous-networks-with-agentic-ai/",
      "publisher": "NVIDIA Developer Blog",
      "author": "NVIDIA Developer Blog",
      "event_date": "2026-06-23",
      "topic": "AI engineering tools",
      "summary": "NVIDIA更新agent 工作流和开发工具能力，重点落在任务编排、上下文、权限控制、工程集成和失败恢复。更有价值的信息是agent 工作流、开发工具入口、权限控制和工程集成，判断这类方案时还要看落地质量取决于权限模型、评估回放、团队流程和可观测性。文章拆解 agent、开发工具或自动化流程里的任务规划、权限、上下文、工具调用和失败恢复。",
      "content_type": "blog",
      "importance": "notable",
      "image_urls": []
    },
    {
      "title": "NVIDIA披露模型评估和研究结果",
      "editorial_category": "viewpoint_analysis",
      "image_url": "https://iprsoftwaremedia.com/219/files/202606/abe517b68cc6efdc17d4a2f48c42b692/6a39321d3d6332b76c54d030_nairr-842x450/nairr-842x450_thmb.jpg",
      "image_alt": "NAIRR Science Program Reshapes Scientific Research, Powered by NVIDIA AI Infrastructure",
      "image_source": "feed",
      "url": "https://blogs.nvidia.com/blog/nairr-scientific-research-ai-infrastructure/",
      "publisher": "NVIDIA Newsroom RSS",
      "author": "NVIDIA Newsroom RSS",
      "event_date": "2026-06-22",
      "topic": "research / evaluation",
      "summary": "NVIDIA披露模型能力和评估方法更新，重点落在能力边界、评估设置、数据来源、使用场景和限制说明。更有价值的信息是模型能力、评估设置、数据来源和限制说明，判断这类方案时还要看结论仍要依赖可复现评测、真实任务和公开限制。文章梳理模型评测或研究结论怎样改变能力边界、成本预期和可靠性判断。",
      "content_type": "blog",
      "importance": "notable",
      "image_urls": []
    }
  ],
  "chinese_media_dynamics": [
    {
      "title": "57场面试杀进OpenAI！华人博士开源「AI面经」，含泪推荐",
      "url": "https://www.qbitai.com/2026/06/437425.html",
      "publisher": "QbitAI",
      "author": "QbitAI",
      "event_date": "2026-06-23",
      "topic": "中文 AI 媒体动态",
      "summary": "57场面试杀进OpenAI！华人博士开源「AI面经」，含泪推荐：希望你能找到快乐。",
      "key_points": [
        "57场面试杀进OpenAI",
        "华人博士开源「AI面经」，含泪推荐：希望你能找到快乐",
        "This is an intermediary/self-media lead; trace it to a primary source before treating it as a reported fact."
      ],
      "importance": "notable",
      "image_urls": []
    }
  ],
  "daily_tracking": [
    {
      "id": "openrouter-rankings",
      "name": "OpenRouter",
      "url": "https://openrouter.ai/rankings",
      "event_date": "2026-06-23",
      "source": "OpenRouter Rankings",
      "category": "model_usage",
      "importance": "notable",
      "change_status": "changed",
      "change_summary": "OpenRouter 本周 Top 10 已解析：#1 DeepSeek V4 Flash 4.96T tokens；#2 MiMo-V2.5 4.1T tokens；#3 MiniMax M3 3.77T tokens；Claude Opus 4.8 周变化 39%。",
      "summary": "OpenRouter 公开榜单显示，本周调用热度第一是 DeepSeek V4 Flash（deepseek，4.96T tokens，周变化 16%）。 Top 10 供应商分布为 anthropic 3、deepseek 2、minimax 1、openrouter 1、tencent 1、xiaomi 1、z-ai 1，可用来观察开发者在 OpenRouter 平台内的真实调用偏好。 新进榜模型包括 GLM 5.2，应继续核对是否来自新发布、免费额度或价格变化。",
      "watch_points": [
        "Claude Opus 4.8 的周变化为 39%，需要结合发布、价格、免费额度和上下文窗口变化判断原因。",
        "新进榜模型：GLM 5.2（z-ai）。",
        "OpenRouter 用量是平台内需求信号；生产选型仍需回到延迟、价格、上下文长度和自有任务复测。"
      ],
      "metrics": [
        {
          "label": "榜单范围",
          "value": "This Week Top 10",
          "trend": "same"
        },
        {
          "label": "供应商分布",
          "value": "anthropic 3、deepseek 2、minimax 1、openrouter 1、tencent 1、xiaomi 1、z-ai 1",
          "trend": "unknown"
        },
        {
          "label": "#1",
          "value": "DeepSeek V4 Flash（deepseek）：4.96T tokens，周变化 16%",
          "trend": "up"
        },
        {
          "label": "#2",
          "value": "MiMo-V2.5（xiaomi）：4.1T tokens，周变化 12%",
          "trend": "up"
        },
        {
          "label": "#3",
          "value": "MiniMax M3（minimax）：3.77T tokens，周变化 17%",
          "trend": "up"
        },
        {
          "label": "#4",
          "value": "Hy3 preview（tencent）：3.68T tokens，周变化 5%",
          "trend": "up"
        },
        {
          "label": "#5",
          "value": "Owl Alpha（openrouter）：2.7T tokens，周变化 10%",
          "trend": "up"
        },
        {
          "label": "#6",
          "value": "DeepSeek V4 Pro（deepseek）：2.5T tokens，周变化 32%",
          "trend": "up"
        },
        {
          "label": "#7",
          "value": "Claude Opus 4.7（anthropic）：2.45T tokens，周变化 3%",
          "trend": "up"
        },
        {
          "label": "#8",
          "value": "Claude Opus 4.8（anthropic）：1.73T tokens，周变化 39%",
          "trend": "up"
        },
        {
          "label": "#9",
          "value": "Claude Sonnet 4.6（anthropic）：1.53T tokens，周变化 24%",
          "trend": "up"
        },
        {
          "label": "#10",
          "value": "GLM 5.2（z-ai）：1.51T tokens，周变化 new",
          "trend": "new"
        }
      ],
      "snapshot": {
        "type": "openrouter_rankings_public_page",
        "collection_method": "public_page_playwright",
        "snapshot_status": "complete",
        "snapshot_as_of": "2026-06-23T08:05:41.865Z",
        "source_url": "https://openrouter.ai/rankings",
        "top_entries": [
          {
            "rank": 1,
            "model": "DeepSeek V4 Flash",
            "provider": "deepseek",
            "tokens": "4.96T tokens",
            "change": "16%"
          },
          {
            "rank": 2,
            "model": "MiMo-V2.5",
            "provider": "xiaomi",
            "tokens": "4.1T tokens",
            "change": "12%"
          },
          {
            "rank": 3,
            "model": "MiniMax M3",
            "provider": "minimax",
            "tokens": "3.77T tokens",
            "change": "17%"
          },
          {
            "rank": 4,
            "model": "Hy3 preview",
            "provider": "tencent",
            "tokens": "3.68T tokens",
            "change": "5%"
          },
          {
            "rank": 5,
            "model": "Owl Alpha",
            "provider": "openrouter",
            "tokens": "2.7T tokens",
            "change": "10%"
          },
          {
            "rank": 6,
            "model": "DeepSeek V4 Pro",
            "provider": "deepseek",
            "tokens": "2.5T tokens",
            "change": "32%"
          },
          {
            "rank": 7,
            "model": "Claude Opus 4.7",
            "provider": "anthropic",
            "tokens": "2.45T tokens",
            "change": "3%"
          },
          {
            "rank": 8,
            "model": "Claude Opus 4.8",
            "provider": "anthropic",
            "tokens": "1.73T tokens",
            "change": "39%"
          },
          {
            "rank": 9,
            "model": "Claude Sonnet 4.6",
            "provider": "anthropic",
            "tokens": "1.53T tokens",
            "change": "24%"
          },
          {
            "rank": 10,
            "model": "GLM 5.2",
            "provider": "z-ai",
            "tokens": "1.51T tokens",
            "change": "new"
          }
        ],
        "official_component_snapshot": {
          "source": "official_dom",
          "component_kind": "openrouter_rankings",
          "source_url": "https://openrouter.ai/rankings",
          "captured_at": "2026-06-23T08:05:41.865Z",
          "selector_version": "openrouter-rankings-v1",
          "source_selector": "[data-openrouter-rankings]",
          "sanitized_html": "<section class=\"openrouter-rankings-card\" data-openrouter-rankings>\n        <header>\n          <p>OpenRouter Top Models</p>\n          <span>This Week usage ranking</span>\n        </header>\n        <table>\n          <thead><tr><th>Rank</th><th>Model</th><th>Provider</th><th>Tokens</th><th>Change</th></tr></thead>\n          <tbody>\n        <tr><td>#1</td><td>DeepSeek V4 Flash</td><td>deepseek</td><td>4.96T tokens</td><td>16%</td></tr>\n        <tr><td>#2</td><td>MiMo-V2.5</td><td>xiaomi</td><td>4.1T tokens</td><td>12%</td></tr>\n        <tr><td>#3</td><td>MiniMax M3</td><td>minimax</td><td>3.77T tokens</td><td>17%</td></tr>\n        <tr><td>#4</td><td>Hy3 preview</td><td>tencent</td><td>3.68T tokens</td><td>5%</td></tr>\n        <tr><td>#5</td><td>Owl Alpha</td><td>openrouter</td><td>2.7T tokens</td><td>10%</td></tr>\n        <tr><td>#6</td><td>DeepSeek V4 Pro</td><td>deepseek</td><td>2.5T tokens</td><td>32%</td></tr>\n        <tr><td>#7</td><td>Claude Opus 4.7</td><td>anthropic</td><td>2.45T tokens</td><td>3%</td></tr>\n        <tr><td>#8</td><td>Claude Opus 4.8</td><td>anthropic</td><td>1.73T tokens</td><td>39%</td></tr>\n        <tr><td>#9</td><td>Claude Sonnet 4.6</td><td>anthropic</td><td>1.53T tokens</td><td>24%</td></tr>\n        <tr><td>#10</td><td>GLM 5.2</td><td>z-ai</td><td>1.51T tokens</td><td>new</td></tr></tbody>\n        </table>\n      </section>",
          "sanitized_css": ".openrouter-rankings-card { border: 1px solid currentColor; padding: 16px; }\n      .openrouter-rankings-card table { width: 100%; border-collapse: collapse; }\n      .openrouter-rankings-card th, .openrouter-rankings-card td { padding: 8px; border-top: 1px solid currentColor; text-align: left; }",
          "dom_hash": "sha256:5dedd778e4cc59939509d407b4276fcc42f15d2345bb0e50a1ce1877a8c2c043",
          "css_hash": "sha256:e5df3dc0e07de42f5c2ca4021bbf59258d47d1ef0fa569d55d98b09876618e43"
        },
        "history_entries": []
      },
      "tracking_component_snapshot": {
        "source": "OpenRouter",
        "component_kind": "openrouter_rankings",
        "source_url": "https://openrouter.ai/rankings",
        "collected_at": "2026-06-23T08:05:41.865Z",
        "selector_version": "openrouter-rankings-v1",
        "raw_dom_hash": "sha256:67db99023a07100f358f776f9d9baa457d5ad89fa6b389dde36548313466016f",
        "data_hash": "sha256:b5219635da9ff71637e5da13441ea05543eda6239c28f2ac0cde202a3a8b8e35",
        "tabs": [
          {
            "id": "top-models",
            "label": "Top Models",
            "view": "stacked_bar",
            "fallback_reason": ""
          },
          {
            "id": "leaderboard",
            "label": "LLM Leaderboard",
            "view": "leaderboard",
            "fallback_reason": ""
          }
        ],
        "series": [
          {
            "id": "openrouter-top-models-weekly-usage",
            "tab_id": "top-models",
            "label": "Weekly usage across OpenRouter",
            "chart": "stacked_bar",
            "rows": [
              {
                "rank": 1,
                "model": "DeepSeek V4 Flash",
                "provider": "deepseek",
                "value": 4960000000000,
                "value_label": "4.96T tokens",
                "change": "16%"
              },
              {
                "rank": 2,
                "model": "MiMo-V2.5",
                "provider": "xiaomi",
                "value": 4099999999999.9995,
                "value_label": "4.1T tokens",
                "change": "12%"
              },
              {
                "rank": 3,
                "model": "MiniMax M3",
                "provider": "minimax",
                "value": 3770000000000,
                "value_label": "3.77T tokens",
                "change": "17%"
              },
              {
                "rank": 4,
                "model": "Hy3 preview",
                "provider": "tencent",
                "value": 3680000000000,
                "value_label": "3.68T tokens",
                "change": "5%"
              },
              {
                "rank": 5,
                "model": "Owl Alpha",
                "provider": "openrouter",
                "value": 2700000000000,
                "value_label": "2.7T tokens",
                "change": "10%"
              },
              {
                "rank": 6,
                "model": "DeepSeek V4 Pro",
                "provider": "deepseek",
                "value": 2500000000000,
                "value_label": "2.5T tokens",
                "change": "32%"
              },
              {
                "rank": 7,
                "model": "Claude Opus 4.7",
                "provider": "anthropic",
                "value": 2450000000000,
                "value_label": "2.45T tokens",
                "change": "3%"
              },
              {
                "rank": 8,
                "model": "Claude Opus 4.8",
                "provider": "anthropic",
                "value": 1730000000000,
                "value_label": "1.73T tokens",
                "change": "39%"
              },
              {
                "rank": 9,
                "model": "Claude Sonnet 4.6",
                "provider": "anthropic",
                "value": 1530000000000,
                "value_label": "1.53T tokens",
                "change": "24%"
              },
              {
                "rank": 10,
                "model": "GLM 5.2",
                "provider": "z-ai",
                "value": 1510000000000,
                "value_label": "1.51T tokens",
                "change": "new"
              }
            ],
            "fallback_reason": ""
          },
          {
            "id": "openrouter-llm-leaderboard",
            "tab_id": "leaderboard",
            "label": "LLM Leaderboard",
            "chart": "leaderboard",
            "rows": [
              {
                "rank": 1,
                "model": "DeepSeek V4 Flash",
                "provider": "deepseek",
                "value": 4960000000000,
                "value_label": "4.96T tokens",
                "change": "16%"
              },
              {
                "rank": 2,
                "model": "MiMo-V2.5",
                "provider": "xiaomi",
                "value": 4099999999999.9995,
                "value_label": "4.1T tokens",
                "change": "12%"
              },
              {
                "rank": 3,
                "model": "MiniMax M3",
                "provider": "minimax",
                "value": 3770000000000,
                "value_label": "3.77T tokens",
                "change": "17%"
              },
              {
                "rank": 4,
                "model": "Hy3 preview",
                "provider": "tencent",
                "value": 3680000000000,
                "value_label": "3.68T tokens",
                "change": "5%"
              },
              {
                "rank": 5,
                "model": "Owl Alpha",
                "provider": "openrouter",
                "value": 2700000000000,
                "value_label": "2.7T tokens",
                "change": "10%"
              },
              {
                "rank": 6,
                "model": "DeepSeek V4 Pro",
                "provider": "deepseek",
                "value": 2500000000000,
                "value_label": "2.5T tokens",
                "change": "32%"
              },
              {
                "rank": 7,
                "model": "Claude Opus 4.7",
                "provider": "anthropic",
                "value": 2450000000000,
                "value_label": "2.45T tokens",
                "change": "3%"
              },
              {
                "rank": 8,
                "model": "Claude Opus 4.8",
                "provider": "anthropic",
                "value": 1730000000000,
                "value_label": "1.73T tokens",
                "change": "39%"
              },
              {
                "rank": 9,
                "model": "Claude Sonnet 4.6",
                "provider": "anthropic",
                "value": 1530000000000,
                "value_label": "1.53T tokens",
                "change": "24%"
              },
              {
                "rank": 10,
                "model": "GLM 5.2",
                "provider": "z-ai",
                "value": 1510000000000,
                "value_label": "1.51T tokens",
                "change": "new"
              }
            ],
            "fallback_reason": ""
          }
        ],
        "rows": [
          {
            "rank": 1,
            "model": "DeepSeek V4 Flash",
            "provider": "deepseek",
            "value": 4960000000000,
            "value_label": "4.96T tokens",
            "change": "16%"
          },
          {
            "rank": 2,
            "model": "MiMo-V2.5",
            "provider": "xiaomi",
            "value": 4099999999999.9995,
            "value_label": "4.1T tokens",
            "change": "12%"
          },
          {
            "rank": 3,
            "model": "MiniMax M3",
            "provider": "minimax",
            "value": 3770000000000,
            "value_label": "3.77T tokens",
            "change": "17%"
          },
          {
            "rank": 4,
            "model": "Hy3 preview",
            "provider": "tencent",
            "value": 3680000000000,
            "value_label": "3.68T tokens",
            "change": "5%"
          },
          {
            "rank": 5,
            "model": "Owl Alpha",
            "provider": "openrouter",
            "value": 2700000000000,
            "value_label": "2.7T tokens",
            "change": "10%"
          },
          {
            "rank": 6,
            "model": "DeepSeek V4 Pro",
            "provider": "deepseek",
            "value": 2500000000000,
            "value_label": "2.5T tokens",
            "change": "32%"
          },
          {
            "rank": 7,
            "model": "Claude Opus 4.7",
            "provider": "anthropic",
            "value": 2450000000000,
            "value_label": "2.45T tokens",
            "change": "3%"
          },
          {
            "rank": 8,
            "model": "Claude Opus 4.8",
            "provider": "anthropic",
            "value": 1730000000000,
            "value_label": "1.73T tokens",
            "change": "39%"
          },
          {
            "rank": 9,
            "model": "Claude Sonnet 4.6",
            "provider": "anthropic",
            "value": 1530000000000,
            "value_label": "1.53T tokens",
            "change": "24%"
          },
          {
            "rank": 10,
            "model": "GLM 5.2",
            "provider": "z-ai",
            "value": 1510000000000,
            "value_label": "1.51T tokens",
            "change": "new"
          }
        ],
        "previous_snapshot": null,
        "diff": {
          "summary": "No previous component snapshot was available for comparison.",
          "changed_rows": [],
          "new_entries": [
            "DeepSeek V4 Flash",
            "MiMo-V2.5",
            "MiniMax M3",
            "Hy3 preview",
            "Owl Alpha",
            "DeepSeek V4 Pro",
            "Claude Opus 4.7",
            "Claude Opus 4.8",
            "Claude Sonnet 4.6",
            "GLM 5.2"
          ]
        },
        "cache_path": "",
        "fallback_reason": "",
        "official_component_snapshot": {
          "source": "official_dom",
          "component_kind": "openrouter_rankings",
          "source_url": "https://openrouter.ai/rankings",
          "captured_at": "2026-06-23T08:05:41.865Z",
          "selector_version": "openrouter-rankings-v1",
          "source_selector": "[data-openrouter-rankings]",
          "sanitized_html": "<section class=\"openrouter-rankings-card\" data-openrouter-rankings>\n        <header>\n          <p>OpenRouter Top Models</p>\n          <span>This Week usage ranking</span>\n        </header>\n        <table>\n          <thead><tr><th>Rank</th><th>Model</th><th>Provider</th><th>Tokens</th><th>Change</th></tr></thead>\n          <tbody>\n        <tr><td>#1</td><td>DeepSeek V4 Flash</td><td>deepseek</td><td>4.96T tokens</td><td>16%</td></tr>\n        <tr><td>#2</td><td>MiMo-V2.5</td><td>xiaomi</td><td>4.1T tokens</td><td>12%</td></tr>\n        <tr><td>#3</td><td>MiniMax M3</td><td>minimax</td><td>3.77T tokens</td><td>17%</td></tr>\n        <tr><td>#4</td><td>Hy3 preview</td><td>tencent</td><td>3.68T tokens</td><td>5%</td></tr>\n        <tr><td>#5</td><td>Owl Alpha</td><td>openrouter</td><td>2.7T tokens</td><td>10%</td></tr>\n        <tr><td>#6</td><td>DeepSeek V4 Pro</td><td>deepseek</td><td>2.5T tokens</td><td>32%</td></tr>\n        <tr><td>#7</td><td>Claude Opus 4.7</td><td>anthropic</td><td>2.45T tokens</td><td>3%</td></tr>\n        <tr><td>#8</td><td>Claude Opus 4.8</td><td>anthropic</td><td>1.73T tokens</td><td>39%</td></tr>\n        <tr><td>#9</td><td>Claude Sonnet 4.6</td><td>anthropic</td><td>1.53T tokens</td><td>24%</td></tr>\n        <tr><td>#10</td><td>GLM 5.2</td><td>z-ai</td><td>1.51T tokens</td><td>new</td></tr></tbody>\n        </table>\n      </section>",
          "sanitized_css": ".openrouter-rankings-card { border: 1px solid currentColor; padding: 16px; }\n      .openrouter-rankings-card table { width: 100%; border-collapse: collapse; }\n      .openrouter-rankings-card th, .openrouter-rankings-card td { padding: 8px; border-top: 1px solid currentColor; text-align: left; }",
          "dom_hash": "sha256:5dedd778e4cc59939509d407b4276fcc42f15d2345bb0e50a1ce1877a8c2c043",
          "css_hash": "sha256:e5df3dc0e07de42f5c2ca4021bbf59258d47d1ef0fa569d55d98b09876618e43"
        },
        "public_trace": {
          "source_url": "https://openrouter.ai/rankings",
          "collected_at": "2026-06-23T08:05:41.865Z",
          "selector_version": "openrouter-rankings-v1",
          "data_hash": "sha256:b5219635da9ff71637e5da13441ea05543eda6239c28f2ac0cde202a3a8b8e35",
          "top_rows": [
            {
              "rank": 1,
              "model": "DeepSeek V4 Flash",
              "provider": "deepseek",
              "value_label": "4.96T tokens",
              "change": "16%"
            },
            {
              "rank": 2,
              "model": "MiMo-V2.5",
              "provider": "xiaomi",
              "value_label": "4.1T tokens",
              "change": "12%"
            },
            {
              "rank": 3,
              "model": "MiniMax M3",
              "provider": "minimax",
              "value_label": "3.77T tokens",
              "change": "17%"
            },
            {
              "rank": 4,
              "model": "Hy3 preview",
              "provider": "tencent",
              "value_label": "3.68T tokens",
              "change": "5%"
            },
            {
              "rank": 5,
              "model": "Owl Alpha",
              "provider": "openrouter",
              "value_label": "2.7T tokens",
              "change": "10%"
            },
            {
              "rank": 6,
              "model": "DeepSeek V4 Pro",
              "provider": "deepseek",
              "value_label": "2.5T tokens",
              "change": "32%"
            },
            {
              "rank": 7,
              "model": "Claude Opus 4.7",
              "provider": "anthropic",
              "value_label": "2.45T tokens",
              "change": "3%"
            },
            {
              "rank": 8,
              "model": "Claude Opus 4.8",
              "provider": "anthropic",
              "value_label": "1.73T tokens",
              "change": "39%"
            },
            {
              "rank": 9,
              "model": "Claude Sonnet 4.6",
              "provider": "anthropic",
              "value_label": "1.53T tokens",
              "change": "24%"
            },
            {
              "rank": 10,
              "model": "GLM 5.2",
              "provider": "z-ai",
              "value_label": "1.51T tokens",
              "change": "new"
            }
          ],
          "diff": {
            "summary": "No previous component snapshot was available for comparison.",
            "changed_rows": [],
            "new_entries": [
              "DeepSeek V4 Flash",
              "MiMo-V2.5",
              "MiniMax M3",
              "Hy3 preview",
              "Owl Alpha",
              "DeepSeek V4 Pro",
              "Claude Opus 4.7",
              "Claude Opus 4.8",
              "Claude Sonnet 4.6",
              "GLM 5.2"
            ]
          },
          "cache_status": "live",
          "fallback_reason": ""
        }
      }
    },
    {
      "id": "artificial-analysis-intelligence-index",
      "name": "Artificial Analysis",
      "url": "https://artificialanalysis.ai/evaluations/artificial-analysis-intelligence-index",
      "event_date": "2026-06-23",
      "source": "Artificial Analysis Intelligence Index",
      "category": "model_benchmark",
      "importance": "notable",
      "change_status": "changed",
      "change_summary": "Artificial Analysis Intelligence Index Top 10 已解析：#1 Claude Fable 5 (with fallback) 60 分，#2 Claude Opus 4.8 (max) 56 分，#3 GPT-5.5 (xhigh) 55 分。",
      "summary": "Artificial Analysis 公开榜单显示，当前 Intelligence Index 第一是 Claude Fable 5 (with fallback)（anthropic，60 分）。 前三名为 Claude Fable 5 (with fallback) 60 分、Claude Opus 4.8 (max) 56 分、GPT-5.5 (xhigh) 55 分，Top 10 供应商分布为 anthropic 4、google 2、openai 2、alibaba 1、zhipu 1。 这个榜单适合做模型 shortlist 和能力变化监测，但生产选型仍要结合延迟、价格、上下文长度和自有任务复测。",
      "watch_points": [
        "榜首 Claude Fable 5 (with fallback) 的综合分为 60 分，需要继续看它在代码、长上下文和 agentic task 分项上的表现。",
        "Top 10 内部竞争接近：46 分有 2 个模型，不要只按一个名次做选型。",
        "把 Intelligence Index 与价格、延迟、吞吐和可用地区一起看，避免用综合分替代真实 workload 复测。"
      ],
      "metrics": [
        {
          "label": "榜单范围",
          "value": "Intelligence Index Top 10",
          "trend": "same"
        },
        {
          "label": "供应商分布",
          "value": "anthropic 4、google 2、openai 2、alibaba 1、zhipu 1",
          "trend": "unknown"
        },
        {
          "label": "#1",
          "value": "Claude Fable 5 (with fallback)（anthropic）：60 分",
          "trend": "unknown"
        },
        {
          "label": "#2",
          "value": "Claude Opus 4.8 (max)（anthropic）：56 分",
          "trend": "unknown"
        },
        {
          "label": "#3",
          "value": "GPT-5.5 (xhigh)（openai）：55 分",
          "trend": "unknown"
        },
        {
          "label": "#4",
          "value": "Claude Opus 4.7 (max)（anthropic）：54 分",
          "trend": "unknown"
        },
        {
          "label": "#5",
          "value": "GPT-5.5 (high)（openai）：53 分",
          "trend": "unknown"
        },
        {
          "label": "#6",
          "value": "GLM-5.2 (max)（zhipu）：51 分",
          "trend": "unknown"
        },
        {
          "label": "#7",
          "value": "Gemini 3.5 Flash（google）：50 分",
          "trend": "unknown"
        },
        {
          "label": "#8",
          "value": "Claude Sonnet 4.6 (max)（anthropic）：47 分",
          "trend": "unknown"
        },
        {
          "label": "#9",
          "value": "Gemini 3.1 Pro Preview（google）：46 分",
          "trend": "unknown"
        },
        {
          "label": "#10",
          "value": "Qwen3.7 Max（alibaba）：46 分",
          "trend": "unknown"
        }
      ],
      "snapshot": {
        "type": "artificial_analysis_intelligence_index_public_page",
        "collection_method": "public_page_playwright",
        "snapshot_status": "complete",
        "snapshot_as_of": "2026-06-23T08:05:41.865Z",
        "source_url": "https://artificialanalysis.ai/evaluations/artificial-analysis-intelligence-index",
        "top_entries": [
          {
            "rank": 1,
            "model": "Claude Fable 5 (with fallback)",
            "provider": "anthropic",
            "tokens": "60 分",
            "change": "AA Index"
          },
          {
            "rank": 2,
            "model": "Claude Opus 4.8 (max)",
            "provider": "anthropic",
            "tokens": "56 分",
            "change": "AA Index"
          },
          {
            "rank": 3,
            "model": "GPT-5.5 (xhigh)",
            "provider": "openai",
            "tokens": "55 分",
            "change": "AA Index"
          },
          {
            "rank": 4,
            "model": "Claude Opus 4.7 (max)",
            "provider": "anthropic",
            "tokens": "54 分",
            "change": "AA Index"
          },
          {
            "rank": 5,
            "model": "GPT-5.5 (high)",
            "provider": "openai",
            "tokens": "53 分",
            "change": "AA Index"
          },
          {
            "rank": 6,
            "model": "GLM-5.2 (max)",
            "provider": "zhipu",
            "tokens": "51 分",
            "change": "AA Index"
          },
          {
            "rank": 7,
            "model": "Gemini 3.5 Flash",
            "provider": "google",
            "tokens": "50 分",
            "change": "AA Index"
          },
          {
            "rank": 8,
            "model": "Claude Sonnet 4.6 (max)",
            "provider": "anthropic",
            "tokens": "47 分",
            "change": "AA Index"
          },
          {
            "rank": 9,
            "model": "Gemini 3.1 Pro Preview",
            "provider": "google",
            "tokens": "46 分",
            "change": "AA Index"
          },
          {
            "rank": 10,
            "model": "Qwen3.7 Max",
            "provider": "alibaba",
            "tokens": "46 分",
            "change": "AA Index"
          }
        ],
        "component_tabs": {
          "score": {
            "rows": [
              {
                "rank": 1,
                "model": "Claude Fable 5 (with fallback)",
                "provider": "anthropic",
                "value": 60,
                "value_label": "60 分",
                "change": "AA Index",
                "metric": "Score"
              },
              {
                "rank": 2,
                "model": "Claude Opus 4.8 (max)",
                "provider": "anthropic",
                "value": 56,
                "value_label": "56 分",
                "change": "AA Index",
                "metric": "Score"
              },
              {
                "rank": 3,
                "model": "GPT-5.5 (xhigh)",
                "provider": "openai",
                "value": 55,
                "value_label": "55 分",
                "change": "AA Index",
                "metric": "Score"
              },
              {
                "rank": 4,
                "model": "Claude Opus 4.7 (max)",
                "provider": "anthropic",
                "value": 54,
                "value_label": "54 分",
                "change": "AA Index",
                "metric": "Score"
              },
              {
                "rank": 5,
                "model": "GPT-5.5 (high)",
                "provider": "openai",
                "value": 53,
                "value_label": "53 分",
                "change": "AA Index",
                "metric": "Score"
              },
              {
                "rank": 6,
                "model": "GLM-5.2 (max)",
                "provider": "zhipu",
                "value": 51,
                "value_label": "51 分",
                "change": "AA Index",
                "metric": "Score"
              },
              {
                "rank": 7,
                "model": "Gemini 3.5 Flash",
                "provider": "google",
                "value": 50,
                "value_label": "50 分",
                "change": "AA Index",
                "metric": "Score"
              },
              {
                "rank": 8,
                "model": "Claude Sonnet 4.6 (max)",
                "provider": "anthropic",
                "value": 47,
                "value_label": "47 分",
                "change": "AA Index",
                "metric": "Score"
              },
              {
                "rank": 9,
                "model": "Gemini 3.1 Pro Preview",
                "provider": "google",
                "value": 46,
                "value_label": "46 分",
                "change": "AA Index",
                "metric": "Score"
              },
              {
                "rank": 10,
                "model": "Qwen3.7 Max",
                "provider": "alibaba",
                "value": 46,
                "value_label": "46 分",
                "change": "AA Index",
                "metric": "Score"
              }
            ]
          }
        },
        "official_component_snapshot": {
          "source": "official_dom",
          "component_kind": "artificial_analysis_index",
          "source_url": "https://artificialanalysis.ai/evaluations/artificial-analysis-intelligence-index",
          "captured_at": "2026-06-23T08:05:41.865Z",
          "selector_version": "artificial-analysis-index-v1",
          "source_selector": "[data-artificial-analysis-index]",
          "sanitized_html": "<section class=\"artificial-analysis-index-card\" data-artificial-analysis-index>\n        <header>\n          <p>Artificial Analysis Intelligence Index</p>\n          <span>Top models by independent Intelligence Index</span>\n        </header>\n        <table>\n          <thead><tr><th>Rank</th><th>Model</th><th>Provider</th><th>Score</th><th>Metric</th></tr></thead>\n          <tbody>\n        <tr><td>#1</td><td>Claude Fable 5 (with fallback)</td><td>anthropic</td><td>60 分</td><td>AA Index</td></tr>\n        <tr><td>#2</td><td>Claude Opus 4.8 (max)</td><td>anthropic</td><td>56 分</td><td>AA Index</td></tr>\n        <tr><td>#3</td><td>GPT-5.5 (xhigh)</td><td>openai</td><td>55 分</td><td>AA Index</td></tr>\n        <tr><td>#4</td><td>Claude Opus 4.7 (max)</td><td>anthropic</td><td>54 分</td><td>AA Index</td></tr>\n        <tr><td>#5</td><td>GPT-5.5 (high)</td><td>openai</td><td>53 分</td><td>AA Index</td></tr>\n        <tr><td>#6</td><td>GLM-5.2 (max)</td><td>zhipu</td><td>51 分</td><td>AA Index</td></tr>\n        <tr><td>#7</td><td>Gemini 3.5 Flash</td><td>google</td><td>50 分</td><td>AA Index</td></tr>\n        <tr><td>#8</td><td>Claude Sonnet 4.6 (max)</td><td>anthropic</td><td>47 分</td><td>AA Index</td></tr>\n        <tr><td>#9</td><td>Gemini 3.1 Pro Preview</td><td>google</td><td>46 分</td><td>AA Index</td></tr>\n        <tr><td>#10</td><td>Qwen3.7 Max</td><td>alibaba</td><td>46 分</td><td>AA Index</td></tr></tbody>\n        </table>\n      </section>",
          "sanitized_css": ".artificial-analysis-index-card { border: 1px solid currentColor; padding: 16px; }\n      .artificial-analysis-index-card table { width: 100%; border-collapse: collapse; }\n      .artificial-analysis-index-card th, .artificial-analysis-index-card td { padding: 8px; border-top: 1px solid currentColor; text-align: left; }",
          "dom_hash": "sha256:2a6211eed7acea0dbf188caca37b12ac5937ac03c08119c42ccd2e94f897d66e",
          "css_hash": "sha256:ca6c14bf5033437bf403050f8a1267f835b68aab80f54905dfa8ecc653808bbf"
        },
        "history_entries": []
      },
      "tracking_component_snapshot": {
        "source": "Artificial Analysis",
        "component_kind": "artificial_analysis_index",
        "source_url": "https://artificialanalysis.ai/evaluations/artificial-analysis-intelligence-index",
        "collected_at": "2026-06-23T08:05:41.865Z",
        "selector_version": "artificial-analysis-index-v1",
        "raw_dom_hash": "sha256:caa7d33c2116c5495c0ff87bb3af671e33346e063be109cb1e5beccdf50e227a",
        "data_hash": "sha256:63c4d52f408853ec7593dfced721bb188a60cf3228a41d630a3952f2d28d08f0",
        "tabs": [
          {
            "id": "score",
            "label": "Score",
            "view": "score_table",
            "fallback_reason": ""
          }
        ],
        "series": [
          {
            "id": "artificial-analysis-score",
            "tab_id": "score",
            "label": "Score",
            "chart": "score_table",
            "rows": [
              {
                "rank": 1,
                "model": "Claude Fable 5 (with fallback)",
                "provider": "anthropic",
                "value": 60,
                "value_label": "60 分",
                "change": "AA Index",
                "metric": "Score"
              },
              {
                "rank": 2,
                "model": "Claude Opus 4.8 (max)",
                "provider": "anthropic",
                "value": 56,
                "value_label": "56 分",
                "change": "AA Index",
                "metric": "Score"
              },
              {
                "rank": 3,
                "model": "GPT-5.5 (xhigh)",
                "provider": "openai",
                "value": 55,
                "value_label": "55 分",
                "change": "AA Index",
                "metric": "Score"
              },
              {
                "rank": 4,
                "model": "Claude Opus 4.7 (max)",
                "provider": "anthropic",
                "value": 54,
                "value_label": "54 分",
                "change": "AA Index",
                "metric": "Score"
              },
              {
                "rank": 5,
                "model": "GPT-5.5 (high)",
                "provider": "openai",
                "value": 53,
                "value_label": "53 分",
                "change": "AA Index",
                "metric": "Score"
              },
              {
                "rank": 6,
                "model": "GLM-5.2 (max)",
                "provider": "zhipu",
                "value": 51,
                "value_label": "51 分",
                "change": "AA Index",
                "metric": "Score"
              },
              {
                "rank": 7,
                "model": "Gemini 3.5 Flash",
                "provider": "google",
                "value": 50,
                "value_label": "50 分",
                "change": "AA Index",
                "metric": "Score"
              },
              {
                "rank": 8,
                "model": "Claude Sonnet 4.6 (max)",
                "provider": "anthropic",
                "value": 47,
                "value_label": "47 分",
                "change": "AA Index",
                "metric": "Score"
              },
              {
                "rank": 9,
                "model": "Gemini 3.1 Pro Preview",
                "provider": "google",
                "value": 46,
                "value_label": "46 分",
                "change": "AA Index",
                "metric": "Score"
              },
              {
                "rank": 10,
                "model": "Qwen3.7 Max",
                "provider": "alibaba",
                "value": 46,
                "value_label": "46 分",
                "change": "AA Index",
                "metric": "Score"
              }
            ],
            "fallback_reason": ""
          }
        ],
        "rows": [
          {
            "rank": 1,
            "model": "Claude Fable 5 (with fallback)",
            "provider": "anthropic",
            "value": 60,
            "value_label": "60 分",
            "change": "AA Index",
            "metric": "AA Index"
          },
          {
            "rank": 2,
            "model": "Claude Opus 4.8 (max)",
            "provider": "anthropic",
            "value": 56,
            "value_label": "56 分",
            "change": "AA Index",
            "metric": "AA Index"
          },
          {
            "rank": 3,
            "model": "GPT-5.5 (xhigh)",
            "provider": "openai",
            "value": 55,
            "value_label": "55 分",
            "change": "AA Index",
            "metric": "AA Index"
          },
          {
            "rank": 4,
            "model": "Claude Opus 4.7 (max)",
            "provider": "anthropic",
            "value": 54,
            "value_label": "54 分",
            "change": "AA Index",
            "metric": "AA Index"
          },
          {
            "rank": 5,
            "model": "GPT-5.5 (high)",
            "provider": "openai",
            "value": 53,
            "value_label": "53 分",
            "change": "AA Index",
            "metric": "AA Index"
          },
          {
            "rank": 6,
            "model": "GLM-5.2 (max)",
            "provider": "zhipu",
            "value": 51,
            "value_label": "51 分",
            "change": "AA Index",
            "metric": "AA Index"
          },
          {
            "rank": 7,
            "model": "Gemini 3.5 Flash",
            "provider": "google",
            "value": 50,
            "value_label": "50 分",
            "change": "AA Index",
            "metric": "AA Index"
          },
          {
            "rank": 8,
            "model": "Claude Sonnet 4.6 (max)",
            "provider": "anthropic",
            "value": 47,
            "value_label": "47 分",
            "change": "AA Index",
            "metric": "AA Index"
          },
          {
            "rank": 9,
            "model": "Gemini 3.1 Pro Preview",
            "provider": "google",
            "value": 46,
            "value_label": "46 分",
            "change": "AA Index",
            "metric": "AA Index"
          },
          {
            "rank": 10,
            "model": "Qwen3.7 Max",
            "provider": "alibaba",
            "value": 46,
            "value_label": "46 分",
            "change": "AA Index",
            "metric": "AA Index"
          }
        ],
        "previous_snapshot": null,
        "diff": {
          "summary": "No previous component snapshot was available for comparison.",
          "changed_rows": [],
          "new_entries": [
            "Claude Fable 5 (with fallback)",
            "Claude Opus 4.8 (max)",
            "GPT-5.5 (xhigh)",
            "Claude Opus 4.7 (max)",
            "GPT-5.5 (high)",
            "GLM-5.2 (max)",
            "Gemini 3.5 Flash",
            "Claude Sonnet 4.6 (max)",
            "Gemini 3.1 Pro Preview",
            "Qwen3.7 Max"
          ]
        },
        "cache_path": "",
        "fallback_reason": "",
        "official_component_snapshot": {
          "source": "official_dom",
          "component_kind": "artificial_analysis_index",
          "source_url": "https://artificialanalysis.ai/evaluations/artificial-analysis-intelligence-index",
          "captured_at": "2026-06-23T08:05:41.865Z",
          "selector_version": "artificial-analysis-index-v1",
          "source_selector": "[data-artificial-analysis-index]",
          "sanitized_html": "<section class=\"artificial-analysis-index-card\" data-artificial-analysis-index>\n        <header>\n          <p>Artificial Analysis Intelligence Index</p>\n          <span>Top models by independent Intelligence Index</span>\n        </header>\n        <table>\n          <thead><tr><th>Rank</th><th>Model</th><th>Provider</th><th>Score</th><th>Metric</th></tr></thead>\n          <tbody>\n        <tr><td>#1</td><td>Claude Fable 5 (with fallback)</td><td>anthropic</td><td>60 分</td><td>AA Index</td></tr>\n        <tr><td>#2</td><td>Claude Opus 4.8 (max)</td><td>anthropic</td><td>56 分</td><td>AA Index</td></tr>\n        <tr><td>#3</td><td>GPT-5.5 (xhigh)</td><td>openai</td><td>55 分</td><td>AA Index</td></tr>\n        <tr><td>#4</td><td>Claude Opus 4.7 (max)</td><td>anthropic</td><td>54 分</td><td>AA Index</td></tr>\n        <tr><td>#5</td><td>GPT-5.5 (high)</td><td>openai</td><td>53 分</td><td>AA Index</td></tr>\n        <tr><td>#6</td><td>GLM-5.2 (max)</td><td>zhipu</td><td>51 分</td><td>AA Index</td></tr>\n        <tr><td>#7</td><td>Gemini 3.5 Flash</td><td>google</td><td>50 分</td><td>AA Index</td></tr>\n        <tr><td>#8</td><td>Claude Sonnet 4.6 (max)</td><td>anthropic</td><td>47 分</td><td>AA Index</td></tr>\n        <tr><td>#9</td><td>Gemini 3.1 Pro Preview</td><td>google</td><td>46 分</td><td>AA Index</td></tr>\n        <tr><td>#10</td><td>Qwen3.7 Max</td><td>alibaba</td><td>46 分</td><td>AA Index</td></tr></tbody>\n        </table>\n      </section>",
          "sanitized_css": ".artificial-analysis-index-card { border: 1px solid currentColor; padding: 16px; }\n      .artificial-analysis-index-card table { width: 100%; border-collapse: collapse; }\n      .artificial-analysis-index-card th, .artificial-analysis-index-card td { padding: 8px; border-top: 1px solid currentColor; text-align: left; }",
          "dom_hash": "sha256:2a6211eed7acea0dbf188caca37b12ac5937ac03c08119c42ccd2e94f897d66e",
          "css_hash": "sha256:ca6c14bf5033437bf403050f8a1267f835b68aab80f54905dfa8ecc653808bbf"
        },
        "public_trace": {
          "source_url": "https://artificialanalysis.ai/evaluations/artificial-analysis-intelligence-index",
          "collected_at": "2026-06-23T08:05:41.865Z",
          "selector_version": "artificial-analysis-index-v1",
          "data_hash": "sha256:63c4d52f408853ec7593dfced721bb188a60cf3228a41d630a3952f2d28d08f0",
          "top_rows": [
            {
              "rank": 1,
              "model": "Claude Fable 5 (with fallback)",
              "provider": "anthropic",
              "value_label": "60 分",
              "change": "AA Index"
            },
            {
              "rank": 2,
              "model": "Claude Opus 4.8 (max)",
              "provider": "anthropic",
              "value_label": "56 分",
              "change": "AA Index"
            },
            {
              "rank": 3,
              "model": "GPT-5.5 (xhigh)",
              "provider": "openai",
              "value_label": "55 分",
              "change": "AA Index"
            },
            {
              "rank": 4,
              "model": "Claude Opus 4.7 (max)",
              "provider": "anthropic",
              "value_label": "54 分",
              "change": "AA Index"
            },
            {
              "rank": 5,
              "model": "GPT-5.5 (high)",
              "provider": "openai",
              "value_label": "53 分",
              "change": "AA Index"
            },
            {
              "rank": 6,
              "model": "GLM-5.2 (max)",
              "provider": "zhipu",
              "value_label": "51 分",
              "change": "AA Index"
            },
            {
              "rank": 7,
              "model": "Gemini 3.5 Flash",
              "provider": "google",
              "value_label": "50 分",
              "change": "AA Index"
            },
            {
              "rank": 8,
              "model": "Claude Sonnet 4.6 (max)",
              "provider": "anthropic",
              "value_label": "47 分",
              "change": "AA Index"
            },
            {
              "rank": 9,
              "model": "Gemini 3.1 Pro Preview",
              "provider": "google",
              "value_label": "46 分",
              "change": "AA Index"
            },
            {
              "rank": 10,
              "model": "Qwen3.7 Max",
              "provider": "alibaba",
              "value_label": "46 分",
              "change": "AA Index"
            }
          ],
          "diff": {
            "summary": "No previous component snapshot was available for comparison.",
            "changed_rows": [],
            "new_entries": [
              "Claude Fable 5 (with fallback)",
              "Claude Opus 4.8 (max)",
              "GPT-5.5 (xhigh)",
              "Claude Opus 4.7 (max)",
              "GPT-5.5 (high)",
              "GLM-5.2 (max)",
              "Gemini 3.5 Flash",
              "Claude Sonnet 4.6 (max)",
              "Gemini 3.1 Pro Preview",
              "Qwen3.7 Max"
            ]
          },
          "cache_status": "live",
          "fallback_reason": ""
        }
      }
    },
    {
      "id": "swe-bench-pro-public",
      "name": "SWE-bench Pro",
      "url": "https://labs.scale.com/leaderboard/swe_bench_pro_public",
      "event_date": "2026-06-23",
      "source": "Scale Labs SWE-Bench Pro",
      "category": "coding_benchmark",
      "importance": "major",
      "change_status": "changed",
      "change_summary": "SWE-bench Pro Public Dataset Top 10 已解析：#1 gpt-5.4 (xHigh)* 59.10±3.56%，#2 Muse Spark* 55.00±3.60%，#3 claude-opus-4-6 (thinking)* 51.90±3.61%；新进榜条目包括 Muse Spark*。",
      "summary": "Scale Labs 公开榜单显示，SWE-bench Pro Public Dataset 当前第一是 gpt-5.4 (xHigh)*（openai，Resolve Rate 59.10±3.56%）。 前三名为 gpt-5.4 (xHigh)* 59.10±3.56%、Muse Spark* 55.00±3.60%、claude-opus-4-6 (thinking)* 51.90±3.61%，Top 10 供应商分布为 anthropic 4、openai 3、google 2、scale 1。 这个榜单适合观察 coding agent 在长周期真实工程任务上的相对表现，但生产选型仍要结合 scaffold、成本上限、置信区间和团队自有仓库复测。",
      "watch_points": [
        "榜首 gpt-5.4 (xHigh)* 的 Resolve Rate 为 59.10±3.56%，需要看它是否依赖特定 agent scaffold 或成本上限。",
        "新进榜条目：Muse Spark*（scale）。",
        "把 SWE-bench Pro 与真实 IDE/CI 工作流分开看，避免把公开 benchmark 直接等同于团队仓库里的修复率。"
      ],
      "metrics": [
        {
          "label": "榜单范围",
          "value": "SWE-bench Pro Public Top 10",
          "trend": "same"
        },
        {
          "label": "供应商分布",
          "value": "anthropic 4、openai 3、google 2、scale 1",
          "trend": "unknown"
        },
        {
          "label": "#1",
          "value": "gpt-5.4 (xHigh)*（openai）：Resolve Rate 59.10±3.56%",
          "trend": "unknown"
        },
        {
          "label": "#2",
          "value": "Muse Spark*（scale）：Resolve Rate 55.00±3.60%",
          "trend": "new"
        },
        {
          "label": "#3",
          "value": "claude-opus-4-6 (thinking)*（anthropic）：Resolve Rate 51.90±3.61%",
          "trend": "unknown"
        },
        {
          "label": "#4",
          "value": "gemini-3.1-pro (thinking)*（google）：Resolve Rate 46.10±3.60%",
          "trend": "unknown"
        },
        {
          "label": "#5",
          "value": "claude-opus-4-5-20251101（anthropic）：Resolve Rate 45.89±3.60%",
          "trend": "unknown"
        },
        {
          "label": "#6",
          "value": "claude-4-5-Sonnet（anthropic）：Resolve Rate 43.60±3.60%",
          "trend": "unknown"
        },
        {
          "label": "#7",
          "value": "gemini-3-pro-preview（google）：Resolve Rate 43.30±3.60%",
          "trend": "unknown"
        },
        {
          "label": "#8",
          "value": "claude-4-Sonnet（anthropic）：Resolve Rate 42.70±3.59%",
          "trend": "unknown"
        },
        {
          "label": "#9",
          "value": "gpt-5-2025-08-07 (High)（openai）：Resolve Rate 41.78±3.49%",
          "trend": "unknown"
        },
        {
          "label": "#10",
          "value": "gpt-5.2-codex（openai）：Resolve Rate 41.04±3.57%",
          "trend": "unknown"
        }
      ],
      "snapshot": {
        "type": "swe_bench_pro_public_page",
        "collection_method": "public_page_static",
        "snapshot_status": "complete",
        "snapshot_as_of": "2026-06-23T08:05:41.865Z",
        "source_url": "https://labs.scale.com/leaderboard/swe_bench_pro_public",
        "top_entries": [
          {
            "rank": 1,
            "model": "gpt-5.4 (xHigh)*",
            "provider": "openai",
            "tokens": "59.10±3.56%",
            "change": "Resolve Rate"
          },
          {
            "rank": 2,
            "model": "Muse Spark*",
            "provider": "scale",
            "tokens": "55.00±3.60%",
            "change": "new"
          },
          {
            "rank": 3,
            "model": "claude-opus-4-6 (thinking)*",
            "provider": "anthropic",
            "tokens": "51.90±3.61%",
            "change": "Resolve Rate"
          },
          {
            "rank": 4,
            "model": "gemini-3.1-pro (thinking)*",
            "provider": "google",
            "tokens": "46.10±3.60%",
            "change": "Resolve Rate"
          },
          {
            "rank": 5,
            "model": "claude-opus-4-5-20251101",
            "provider": "anthropic",
            "tokens": "45.89±3.60%",
            "change": "Resolve Rate"
          },
          {
            "rank": 6,
            "model": "claude-4-5-Sonnet",
            "provider": "anthropic",
            "tokens": "43.60±3.60%",
            "change": "Resolve Rate"
          },
          {
            "rank": 7,
            "model": "gemini-3-pro-preview",
            "provider": "google",
            "tokens": "43.30±3.60%",
            "change": "Resolve Rate"
          },
          {
            "rank": 8,
            "model": "claude-4-Sonnet",
            "provider": "anthropic",
            "tokens": "42.70±3.59%",
            "change": "Resolve Rate"
          },
          {
            "rank": 9,
            "model": "gpt-5-2025-08-07 (High)",
            "provider": "openai",
            "tokens": "41.78±3.49%",
            "change": "Resolve Rate"
          },
          {
            "rank": 10,
            "model": "gpt-5.2-codex",
            "provider": "openai",
            "tokens": "41.04±3.57%",
            "change": "Resolve Rate"
          }
        ],
        "official_component_snapshot": {
          "source": "official_dom",
          "component_kind": "swe_bench_pro",
          "source_url": "https://labs.scale.com/leaderboard/swe_bench_pro_public",
          "captured_at": "2026-06-23T08:05:41.865Z",
          "selector_version": "swe-bench-pro-v1",
          "source_selector": "[data-swe-bench-pro-leaderboard]",
          "sanitized_html": "<section class=\"swe-bench-pro-card\" data-swe-bench-pro-leaderboard>\n        <header>\n          <p>SWE-Bench Pro (Public Dataset)</p>\n          <h2>Performance Comparison</h2>\n          <span>Primary metric: Resolve Rate</span>\n        </header>\n        <table>\n          <thead><tr><th>Rank</th><th>Model / Agent</th><th>Provider</th><th>Resolve Rate</th><th>Change</th></tr></thead>\n          <tbody>\n        <tr>\n          <td>#1</td>\n          <td>gpt-5.4 (xHigh)*</td>\n          <td>openai</td>\n          <td>59.10±3.56%</td>\n          <td>Resolve Rate</td>\n        </tr>\n        <tr>\n          <td>#2</td>\n          <td>Muse Spark*</td>\n          <td>scale</td>\n          <td>55.00±3.60%</td>\n          <td>new</td>\n        </tr>\n        <tr>\n          <td>#3</td>\n          <td>claude-opus-4-6 (thinking)*</td>\n          <td>anthropic</td>\n          <td>51.90±3.61%</td>\n          <td>Resolve Rate</td>\n        </tr>\n        <tr>\n          <td>#4</td>\n          <td>gemini-3.1-pro (thinking)*</td>\n          <td>google</td>\n          <td>46.10±3.60%</td>\n          <td>Resolve Rate</td>\n        </tr>\n        <tr>\n          <td>#5</td>\n          <td>claude-opus-4-5-20251101</td>\n          <td>anthropic</td>\n          <td>45.89±3.60%</td>\n          <td>Resolve Rate</td>\n        </tr>\n        <tr>\n          <td>#6</td>\n          <td>claude-4-5-Sonnet</td>\n          <td>anthropic</td>\n          <td>43.60±3.60%</td>\n          <td>Resolve Rate</td>\n        </tr>\n        <tr>\n          <td>#7</td>\n          <td>gemini-3-pro-preview</td>\n          <td>google</td>\n          <td>43.30±3.60%</td>\n          <td>Resolve Rate</td>\n        </tr>\n        <tr>\n          <td>#8</td>\n          <td>claude-4-Sonnet</td>\n          <td>anthropic</td>\n          <td>42.70±3.59%</td>\n          <td>Resolve Rate</td>\n        </tr>\n        <tr>\n          <td>#9</td>\n          <td>gpt-5-2025-08-07 (High)</td>\n          <td>openai</td>\n          <td>41.78±3.49%</td>\n          <td>Resolve Rate</td>\n        </tr>\n        <tr>\n          <td>#10</td>\n          <td>gpt-5.2-codex</td>\n          <td>openai</td>\n          <td>41.04±3.57%</td>\n          <td>Resolve Rate</td>\n        </tr></tbody>\n        </table>\n      </section>",
          "sanitized_css": ".swe-bench-pro-card { border: 1px solid currentColor; padding: 16px; }\n      .swe-bench-pro-card table { width: 100%; border-collapse: collapse; }\n      .swe-bench-pro-card th, .swe-bench-pro-card td { padding: 8px; border-top: 1px solid currentColor; text-align: left; }",
          "dom_hash": "sha256:cc4506cfb6f43dc3ea7331ad2e9ab545ed056a3aab2309bf4201d14baa1ce040",
          "css_hash": "sha256:bbb18aff9c5bd0f35808108d31a64c2b62e0adcab81b24181da21bcd9a31c42d"
        },
        "history_entries": []
      },
      "tracking_component_snapshot": {
        "source": "Scale Labs SWE-Bench Pro",
        "component_kind": "swe_bench_pro",
        "source_url": "https://labs.scale.com/leaderboard/swe_bench_pro_public",
        "collected_at": "2026-06-23T08:05:41.865Z",
        "selector_version": "swe-bench-pro-v1",
        "raw_dom_hash": "sha256:2d5ebf88219cf9ca3b8537c2a99a9339988bd6f4b8cb73e80b37c9c1e786a9a9",
        "data_hash": "sha256:2c2ddd4e3797a9a00f322ba4701d5df64c83eaf0f40e43b951cfa26f32d557d7",
        "tabs": [
          {
            "id": "leaderboard",
            "label": "Public Leaderboard",
            "view": "leaderboard",
            "fallback_reason": ""
          }
        ],
        "series": [
          {
            "id": "swe-bench-pro-public-leaderboard",
            "tab_id": "leaderboard",
            "label": "SWE-Bench Pro Public Dataset",
            "chart": "leaderboard",
            "rows": [
              {
                "rank": 1,
                "model": "gpt-5.4 (xHigh)*",
                "provider": "openai",
                "value": 59.1,
                "value_label": "59.10±3.56%",
                "change": "Resolve Rate",
                "metric": "Resolve Rate"
              },
              {
                "rank": 2,
                "model": "Muse Spark*",
                "provider": "scale",
                "value": 55,
                "value_label": "55.00±3.60%",
                "change": "new",
                "metric": "Resolve Rate"
              },
              {
                "rank": 3,
                "model": "claude-opus-4-6 (thinking)*",
                "provider": "anthropic",
                "value": 51.9,
                "value_label": "51.90±3.61%",
                "change": "Resolve Rate",
                "metric": "Resolve Rate"
              },
              {
                "rank": 4,
                "model": "gemini-3.1-pro (thinking)*",
                "provider": "google",
                "value": 46.1,
                "value_label": "46.10±3.60%",
                "change": "Resolve Rate",
                "metric": "Resolve Rate"
              },
              {
                "rank": 5,
                "model": "claude-opus-4-5-20251101",
                "provider": "anthropic",
                "value": 45.89,
                "value_label": "45.89±3.60%",
                "change": "Resolve Rate",
                "metric": "Resolve Rate"
              },
              {
                "rank": 6,
                "model": "claude-4-5-Sonnet",
                "provider": "anthropic",
                "value": 43.6,
                "value_label": "43.60±3.60%",
                "change": "Resolve Rate",
                "metric": "Resolve Rate"
              },
              {
                "rank": 7,
                "model": "gemini-3-pro-preview",
                "provider": "google",
                "value": 43.3,
                "value_label": "43.30±3.60%",
                "change": "Resolve Rate",
                "metric": "Resolve Rate"
              },
              {
                "rank": 8,
                "model": "claude-4-Sonnet",
                "provider": "anthropic",
                "value": 42.7,
                "value_label": "42.70±3.59%",
                "change": "Resolve Rate",
                "metric": "Resolve Rate"
              },
              {
                "rank": 9,
                "model": "gpt-5-2025-08-07 (High)",
                "provider": "openai",
                "value": 41.78,
                "value_label": "41.78±3.49%",
                "change": "Resolve Rate",
                "metric": "Resolve Rate"
              },
              {
                "rank": 10,
                "model": "gpt-5.2-codex",
                "provider": "openai",
                "value": 41.04,
                "value_label": "41.04±3.57%",
                "change": "Resolve Rate",
                "metric": "Resolve Rate"
              }
            ],
            "fallback_reason": ""
          }
        ],
        "rows": [
          {
            "rank": 1,
            "model": "gpt-5.4 (xHigh)*",
            "provider": "openai",
            "value": 59.1,
            "value_label": "59.10±3.56%",
            "change": "Resolve Rate",
            "metric": "Resolve Rate"
          },
          {
            "rank": 2,
            "model": "Muse Spark*",
            "provider": "scale",
            "value": 55,
            "value_label": "55.00±3.60%",
            "change": "new",
            "metric": "Resolve Rate"
          },
          {
            "rank": 3,
            "model": "claude-opus-4-6 (thinking)*",
            "provider": "anthropic",
            "value": 51.9,
            "value_label": "51.90±3.61%",
            "change": "Resolve Rate",
            "metric": "Resolve Rate"
          },
          {
            "rank": 4,
            "model": "gemini-3.1-pro (thinking)*",
            "provider": "google",
            "value": 46.1,
            "value_label": "46.10±3.60%",
            "change": "Resolve Rate",
            "metric": "Resolve Rate"
          },
          {
            "rank": 5,
            "model": "claude-opus-4-5-20251101",
            "provider": "anthropic",
            "value": 45.89,
            "value_label": "45.89±3.60%",
            "change": "Resolve Rate",
            "metric": "Resolve Rate"
          },
          {
            "rank": 6,
            "model": "claude-4-5-Sonnet",
            "provider": "anthropic",
            "value": 43.6,
            "value_label": "43.60±3.60%",
            "change": "Resolve Rate",
            "metric": "Resolve Rate"
          },
          {
            "rank": 7,
            "model": "gemini-3-pro-preview",
            "provider": "google",
            "value": 43.3,
            "value_label": "43.30±3.60%",
            "change": "Resolve Rate",
            "metric": "Resolve Rate"
          },
          {
            "rank": 8,
            "model": "claude-4-Sonnet",
            "provider": "anthropic",
            "value": 42.7,
            "value_label": "42.70±3.59%",
            "change": "Resolve Rate",
            "metric": "Resolve Rate"
          },
          {
            "rank": 9,
            "model": "gpt-5-2025-08-07 (High)",
            "provider": "openai",
            "value": 41.78,
            "value_label": "41.78±3.49%",
            "change": "Resolve Rate",
            "metric": "Resolve Rate"
          },
          {
            "rank": 10,
            "model": "gpt-5.2-codex",
            "provider": "openai",
            "value": 41.04,
            "value_label": "41.04±3.57%",
            "change": "Resolve Rate",
            "metric": "Resolve Rate"
          }
        ],
        "previous_snapshot": null,
        "diff": {
          "summary": "No previous component snapshot was available for comparison.",
          "changed_rows": [],
          "new_entries": [
            "gpt-5.4 (xHigh)*",
            "Muse Spark*",
            "claude-opus-4-6 (thinking)*",
            "gemini-3.1-pro (thinking)*",
            "claude-opus-4-5-20251101",
            "claude-4-5-Sonnet",
            "gemini-3-pro-preview",
            "claude-4-Sonnet",
            "gpt-5-2025-08-07 (High)",
            "gpt-5.2-codex"
          ]
        },
        "cache_path": "",
        "fallback_reason": "",
        "official_component_snapshot": {
          "source": "official_dom",
          "component_kind": "swe_bench_pro",
          "source_url": "https://labs.scale.com/leaderboard/swe_bench_pro_public",
          "captured_at": "2026-06-23T08:05:41.865Z",
          "selector_version": "swe-bench-pro-v1",
          "source_selector": "[data-swe-bench-pro-leaderboard]",
          "sanitized_html": "<section class=\"swe-bench-pro-card\" data-swe-bench-pro-leaderboard>\n        <header>\n          <p>SWE-Bench Pro (Public Dataset)</p>\n          <h2>Performance Comparison</h2>\n          <span>Primary metric: Resolve Rate</span>\n        </header>\n        <table>\n          <thead><tr><th>Rank</th><th>Model / Agent</th><th>Provider</th><th>Resolve Rate</th><th>Change</th></tr></thead>\n          <tbody>\n        <tr>\n          <td>#1</td>\n          <td>gpt-5.4 (xHigh)*</td>\n          <td>openai</td>\n          <td>59.10±3.56%</td>\n          <td>Resolve Rate</td>\n        </tr>\n        <tr>\n          <td>#2</td>\n          <td>Muse Spark*</td>\n          <td>scale</td>\n          <td>55.00±3.60%</td>\n          <td>new</td>\n        </tr>\n        <tr>\n          <td>#3</td>\n          <td>claude-opus-4-6 (thinking)*</td>\n          <td>anthropic</td>\n          <td>51.90±3.61%</td>\n          <td>Resolve Rate</td>\n        </tr>\n        <tr>\n          <td>#4</td>\n          <td>gemini-3.1-pro (thinking)*</td>\n          <td>google</td>\n          <td>46.10±3.60%</td>\n          <td>Resolve Rate</td>\n        </tr>\n        <tr>\n          <td>#5</td>\n          <td>claude-opus-4-5-20251101</td>\n          <td>anthropic</td>\n          <td>45.89±3.60%</td>\n          <td>Resolve Rate</td>\n        </tr>\n        <tr>\n          <td>#6</td>\n          <td>claude-4-5-Sonnet</td>\n          <td>anthropic</td>\n          <td>43.60±3.60%</td>\n          <td>Resolve Rate</td>\n        </tr>\n        <tr>\n          <td>#7</td>\n          <td>gemini-3-pro-preview</td>\n          <td>google</td>\n          <td>43.30±3.60%</td>\n          <td>Resolve Rate</td>\n        </tr>\n        <tr>\n          <td>#8</td>\n          <td>claude-4-Sonnet</td>\n          <td>anthropic</td>\n          <td>42.70±3.59%</td>\n          <td>Resolve Rate</td>\n        </tr>\n        <tr>\n          <td>#9</td>\n          <td>gpt-5-2025-08-07 (High)</td>\n          <td>openai</td>\n          <td>41.78±3.49%</td>\n          <td>Resolve Rate</td>\n        </tr>\n        <tr>\n          <td>#10</td>\n          <td>gpt-5.2-codex</td>\n          <td>openai</td>\n          <td>41.04±3.57%</td>\n          <td>Resolve Rate</td>\n        </tr></tbody>\n        </table>\n      </section>",
          "sanitized_css": ".swe-bench-pro-card { border: 1px solid currentColor; padding: 16px; }\n      .swe-bench-pro-card table { width: 100%; border-collapse: collapse; }\n      .swe-bench-pro-card th, .swe-bench-pro-card td { padding: 8px; border-top: 1px solid currentColor; text-align: left; }",
          "dom_hash": "sha256:cc4506cfb6f43dc3ea7331ad2e9ab545ed056a3aab2309bf4201d14baa1ce040",
          "css_hash": "sha256:bbb18aff9c5bd0f35808108d31a64c2b62e0adcab81b24181da21bcd9a31c42d"
        },
        "public_trace": {
          "source_url": "https://labs.scale.com/leaderboard/swe_bench_pro_public",
          "collected_at": "2026-06-23T08:05:41.865Z",
          "selector_version": "swe-bench-pro-v1",
          "data_hash": "sha256:2c2ddd4e3797a9a00f322ba4701d5df64c83eaf0f40e43b951cfa26f32d557d7",
          "top_rows": [
            {
              "rank": 1,
              "model": "gpt-5.4 (xHigh)*",
              "provider": "openai",
              "value_label": "59.10±3.56%",
              "change": "Resolve Rate"
            },
            {
              "rank": 2,
              "model": "Muse Spark*",
              "provider": "scale",
              "value_label": "55.00±3.60%",
              "change": "new"
            },
            {
              "rank": 3,
              "model": "claude-opus-4-6 (thinking)*",
              "provider": "anthropic",
              "value_label": "51.90±3.61%",
              "change": "Resolve Rate"
            },
            {
              "rank": 4,
              "model": "gemini-3.1-pro (thinking)*",
              "provider": "google",
              "value_label": "46.10±3.60%",
              "change": "Resolve Rate"
            },
            {
              "rank": 5,
              "model": "claude-opus-4-5-20251101",
              "provider": "anthropic",
              "value_label": "45.89±3.60%",
              "change": "Resolve Rate"
            },
            {
              "rank": 6,
              "model": "claude-4-5-Sonnet",
              "provider": "anthropic",
              "value_label": "43.60±3.60%",
              "change": "Resolve Rate"
            },
            {
              "rank": 7,
              "model": "gemini-3-pro-preview",
              "provider": "google",
              "value_label": "43.30±3.60%",
              "change": "Resolve Rate"
            },
            {
              "rank": 8,
              "model": "claude-4-Sonnet",
              "provider": "anthropic",
              "value_label": "42.70±3.59%",
              "change": "Resolve Rate"
            },
            {
              "rank": 9,
              "model": "gpt-5-2025-08-07 (High)",
              "provider": "openai",
              "value_label": "41.78±3.49%",
              "change": "Resolve Rate"
            },
            {
              "rank": 10,
              "model": "gpt-5.2-codex",
              "provider": "openai",
              "value_label": "41.04±3.57%",
              "change": "Resolve Rate"
            }
          ],
          "diff": {
            "summary": "No previous component snapshot was available for comparison.",
            "changed_rows": [],
            "new_entries": [
              "gpt-5.4 (xHigh)*",
              "Muse Spark*",
              "claude-opus-4-6 (thinking)*",
              "gemini-3.1-pro (thinking)*",
              "claude-opus-4-5-20251101",
              "claude-4-5-Sonnet",
              "gemini-3-pro-preview",
              "claude-4-Sonnet",
              "gpt-5-2025-08-07 (High)",
              "gpt-5.2-codex"
            ]
          },
          "cache_status": "live",
          "fallback_reason": ""
        }
      }
    }
  ],
  "projects": [
    {
      "name": "DeusData/codebase-memory-mcp",
      "editorial_category": "open_source",
      "domains": [
        "agent"
      ],
      "use_case": "适合先评估该仓库的运行入口、集成边界、许可证和近期维护，再决定是否进入团队试用。",
      "url": "https://github.com/DeusData/codebase-memory-mcp",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "calesthio/OpenMontage",
      "editorial_category": "open_source",
      "domains": [
        "agent"
      ],
      "use_case": "适合先评估该仓库的运行入口、集成边界、许可证和近期维护，再决定是否进入团队试用。",
      "url": "https://github.com/calesthio/OpenMontage",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "Panniantong/Agent-Reach",
      "editorial_category": "open_source",
      "domains": [
        "agent"
      ],
      "use_case": "适合先评估该仓库的运行入口、集成边界、许可证和近期维护，再决定是否进入团队试用。",
      "url": "https://github.com/Panniantong/Agent-Reach",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "n0-computer/iroh",
      "editorial_category": "open_source",
      "domains": [
        "AI tooling"
      ],
      "use_case": "适合先评估该仓库的运行入口、集成边界、许可证和近期维护，再决定是否进入团队试用。",
      "url": "https://github.com/n0-computer/iroh",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "google-research/timesfm",
      "editorial_category": "open_source",
      "domains": [
        "AI tooling"
      ],
      "use_case": "适合先评估该仓库的运行入口、集成边界、许可证和近期维护，再决定是否进入团队试用。",
      "url": "https://github.com/google-research/timesfm",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "iptv-org/iptv",
      "editorial_category": "open_source",
      "domains": [
        "AI tooling"
      ],
      "use_case": "适合先评估该仓库的运行入口、集成边界、许可证和近期维护，再决定是否进入团队试用。",
      "url": "https://github.com/iptv-org/iptv",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "asgeirtj/system_prompts_leaks",
      "editorial_category": "open_source",
      "domains": [
        "agent"
      ],
      "use_case": "适合先评估该仓库的运行入口、集成边界、许可证和近期维护，再决定是否进入团队试用。",
      "url": "https://github.com/asgeirtj/system_prompts_leaks",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "withastro/flue",
      "editorial_category": "open_source",
      "domains": [
        "agent"
      ],
      "use_case": "适合先评估该仓库的运行入口、集成边界、许可证和近期维护，再决定是否进入团队试用。",
      "url": "https://github.com/withastro/flue",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "NVIDIA/SkillSpector",
      "editorial_category": "open_source",
      "domains": [
        "agent"
      ],
      "use_case": "适合先评估该仓库的运行入口、集成边界、许可证和近期维护，再决定是否进入团队试用。",
      "url": "https://github.com/NVIDIA/SkillSpector",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "teslamate-org/teslamate",
      "editorial_category": "open_source",
      "domains": [
        "AI tooling"
      ],
      "use_case": "适合先评估该仓库的运行入口、集成边界、许可证和近期维护，再决定是否进入团队试用。",
      "url": "https://github.com/teslamate-org/teslamate",
      "event_date": "2026-06-23",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    }
  ],
  "builder_observations": [
    {
      "author": "Thibault Sottiaux",
      "handle": "thsottiaux",
      "editorial_category": "x_discussion",
      "content": "原帖围绕AI 工具和 agent 实践给出一条产品判断线索，重点是文件入口、版本历史，以及它怎样接进现有 AI 工具链；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "original_text": "Let's Patch The Planet. Updates to codex security and a new GPT-5.5-Cyber. A day of celebration for cyber defense acceleration. https://t.co/SYKQvsTA44",
      "translation": "原帖围绕AI 工具和 agent 实践给出一条产品判断线索，重点是文件入口、版本历史，以及它怎样接进现有 AI 工具链；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "avatar_url": "https://unavatar.io/x/thsottiaux",
      "url": "https://x.com/thsottiaux/status/2069152290326630518",
      "role": "builder",
      "event_date": "2026-06-22",
      "source": "follow-builders X feed",
      "importance": "notable",
      "image_urls": []
    },
    {
      "author": "Aaron Levie",
      "handle": "levie",
      "editorial_category": "x_discussion",
      "content": "原帖围绕AI 工具和 agent 实践给出一条工程落地线索，重点是真实场景、落地边界和哪些做法可以直接复用；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "original_text": "Almost all AI model and agent progress is downstream from evals. Open weights post training for specific domains comes down to evals. Agent improvements in the applied AI layer is all about evals. Agentic enterprise deployments that actually can augment work is all about evals. It’s all evals. This will become a core competency of any enterprise in the future. The companies that are able to best understand their own (and/or customers) workflows and how well agents participate in that work will ...",
      "translation": "原帖围绕AI 工具和 agent 实践给出一条工程落地线索，重点是真实场景、落地边界和哪些做法可以直接复用；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "avatar_url": "https://unavatar.io/x/levie",
      "url": "https://x.com/levie/status/2069228335255949775",
      "role": "builder",
      "event_date": "2026-06-23",
      "source": "follow-builders X feed",
      "importance": "notable",
      "image_urls": []
    },
    {
      "author": "Swyx",
      "handle": "swyx",
      "editorial_category": "x_discussion",
      "content": "原帖围绕AI 工具和 agent 实践给出一条工程落地线索，重点是权限放行、工作流编排和长任务稳定性；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "original_text": "i dont think anyone is correctly doing the math around how SpaceX, the NeoCloud+NeoLab, is currently going to market? SpaceX has already recouped about HALF its investment in Cursor, in compute deals. The other half is paid for if Composer 3 does well. No other company is simultaneously a leading model lab + neocloud (at least where GPUs is concerned). its a crazy effective combo iff you've adequately planned out gpu supply if inhouse training 1) goes very well 2) doesn't go very well",
      "translation": "原帖围绕AI 工具和 agent 实践给出一条工程落地线索，重点是权限放行、工作流编排和长任务稳定性；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "avatar_url": "https://unavatar.io/x/swyx",
      "url": "https://x.com/swyx/status/2069301071965741388",
      "role": "builder",
      "event_date": "2026-06-23",
      "source": "follow-builders X feed",
      "importance": "notable",
      "image_urls": []
    },
    {
      "author": "Peter Yang",
      "handle": "petergyang",
      "editorial_category": "x_discussion",
      "content": "原帖围绕AI 工具和 agent 实践给出一条产品判断线索，重点是文件入口、版本历史，以及它怎样接进现有 AI 工具链；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "original_text": "I want to do a podcast episode with someone who's good at using Codex / Claude Code to create fun pixel or threejs games and can show us how to do it. I am a gamer at heart! Who's the best person to talk to?",
      "translation": "原帖围绕AI 工具和 agent 实践给出一条产品判断线索，重点是文件入口、版本历史，以及它怎样接进现有 AI 工具链；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "avatar_url": "https://unavatar.io/x/petergyang",
      "url": "https://x.com/petergyang/status/2069118077313425840",
      "role": "builder",
      "event_date": "2026-06-22",
      "source": "follow-builders X feed",
      "importance": "notable",
      "image_urls": []
    },
    {
      "author": "Guillermo Rauch",
      "handle": "rauchg",
      "editorial_category": "x_discussion",
      "content": "原帖围绕模型产品和能力变化给出一条产品判断线索，重点是文件入口、版本历史，以及它怎样接进现有 AI 工具链；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "original_text": "Claude Design → Vercel, in one click https://t.co/Btq9hFk7OB https://t.co/NpgdokzpvE",
      "translation": "原帖围绕模型产品和能力变化给出一条产品判断线索，重点是文件入口、版本历史，以及它怎样接进现有 AI 工具链；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "avatar_url": "https://unavatar.io/x/rauchg",
      "url": "https://x.com/rauchg/status/2069219190834127276",
      "role": "builder",
      "event_date": "2026-06-23",
      "source": "follow-builders X feed",
      "importance": "notable",
      "image_urls": []
    },
    {
      "author": "Aaron Levie",
      "handle": "levie",
      "editorial_category": "x_discussion",
      "content": "原帖围绕AI 工具和 agent 实践给出一条工程落地线索，重点是真实场景、落地边界和哪些做法可以直接复用；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "original_text": "We heard that HTML is a big deal again. You can now preview, edit, manage versions, and securely share any HTML based content on Box. Great for being able to work with any agent produced content immediately. https://t.co/Rgo2TO6RIg",
      "translation": "原帖围绕AI 工具和 agent 实践给出一条工程落地线索，重点是真实场景、落地边界和哪些做法可以直接复用；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "avatar_url": "https://unavatar.io/x/levie",
      "url": "https://x.com/levie/status/2069140445205348432",
      "role": "builder",
      "event_date": "2026-06-22",
      "source": "follow-builders X feed",
      "importance": "notable",
      "image_urls": []
    },
    {
      "author": "Ryo Lu",
      "handle": "ryolu_",
      "editorial_category": "x_discussion",
      "content": "原帖围绕AI 工具和 agent 实践给出一条产品判断线索，重点是文件入口、版本历史，以及它怎样接进现有 AI 工具链；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "original_text": "here's my talk at Cursor Compile some thoughts on how we build in the age of AI and what doesn't change https://t.co/otMw3nwPkr",
      "translation": "原帖围绕AI 工具和 agent 实践给出一条产品判断线索，重点是文件入口、版本历史，以及它怎样接进现有 AI 工具链；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "avatar_url": "https://unavatar.io/x/ryolu_",
      "url": "https://x.com/ryolu_/status/2069218497272717661",
      "role": "builder",
      "event_date": "2026-06-23",
      "source": "follow-builders X feed",
      "importance": "notable",
      "image_urls": []
    }
  ],
  "official_org_updates": [],
  "evidence_assets": [],
  "generated_at": "2026-06-23T08:25:16.734Z",
  "report_status": "normal",
  "canonical_url": "https://jasonxzwen.github.io/ai-daily-cn/reports/2026/06/2026-06-23.html",
  "html_path": "reports/2026/06/2026-06-23.html",
  "quality_status": {
    "status": "degraded",
    "public_note": "Some discovery coverage is degraded; this report may be incomplete.",
    "affected_sections": [
      "huggingface_trending",
      "hot_blogs",
      "builder_observations"
    ],
    "degraded_events": [
      {
        "section": "huggingface_trending",
        "message": "huggingface_trending coverage is degraded and should be disclosed in the public report.",
        "severity": "degraded"
      },
      {
        "section": "hot_blogs",
        "message": "hot_blogs coverage is degraded and should be disclosed in the public report.",
        "severity": "degraded"
      },
      {
        "section": "builder_observations",
        "message": "builder_observations coverage is degraded and should be disclosed in the public report.",
        "severity": "degraded"
      },
      {
        "section": "builder_observations",
        "message": "builder_observations below strict publish minimum: 7/8.",
        "severity": "degraded"
      }
    ]
  }
}