{
  "schema_version": 1,
  "report_date": "2026-06-17",
  "title": "AI 日报 2026-06-17",
  "summary": "今天最值得看的主线有 OpenAI披露模型能力和评估方法更新；Qwen 团队介绍机器人学习与多模态推理实验；微软研究院更新AI 产品、平台或工程实践；热门博客这轮主要看 agent 和开发工具的落地边界。",
  "hero_highlights": [
    {
      "title": "OpenAI披露模型能力和评估方法更新",
      "url": "https://openai.com/index/deployment-simulation",
      "reason": "研究价值集中在评测设置、能力边界和内部实验参照",
      "what_happened": "OpenAI披露模型能力和评估方法更新，材料覆盖能力边界、评估设置、数据来源、使用场景和限制说明，边界落在结论仍要依赖可复现评测、真实任务和公开限制",
      "why_watch": "研究价值集中在评测设置、能力边界和内部实验参照",
      "category": "model_platform",
      "source_item_ref": "https://openai.com/index/deployment-simulation"
    },
    {
      "title": "Agent Dashboard发布生产 agent 观测面板",
      "url": "https://x.ai/news/agent-dashboard",
      "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": "Agent Dashboard发布生产 agent 观测面板，材料覆盖工具调用轨迹、事故时间线、成本归因、回滚状态和发布健康度，边界落在观测价值取决于能否把失败记录、成本和发布状态串进同一条链路",
      "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": "product_tool",
      "source_item_ref": "https://x.ai/news/agent-dashboard"
    },
    {
      "title": "Qwen 团队介绍机器人学习与多模态推理实验",
      "url": "https://www.alibabacloud.com/blog/qwen-robotworld-boundless-worlds-for-embodied-agents_603268",
      "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": "36Kr 专访围绕具身智能短板、VLA 与世界模型关系展开，核心是机器人是否能补上物理规律和因果预测能力",
      "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/qwen-robotworld-boundless-worlds-for-embodied-agents_603268"
    }
  ],
  "main_items": [
    {
      "title": "OpenAI News RSS: Deployment Simulation",
      "editorial_category": "ai_industry",
      "event_date": "2026-06-16",
      "url": "https://openai.com/index/deployment-simulation",
      "source": "OpenAI News RSS",
      "tier": "T0",
      "entities": [
        "OpenAI News RSS"
      ],
      "summary": "OpenAI披露模型能力和评估方法更新，材料覆盖能力边界、评估设置、数据来源、使用场景和限制说明，边界落在结论仍要依赖可复现评测、真实任务和公开限制。",
      "bullets": [
        "**OpenAI披露模型能力和评估方法更新**：材料把模型能力和评估方法更新落到能力边界、评估设置、数据来源、使用场景和限制说明，已披露事实集中在模型能力、评估设置、数据来源和限制说明。",
        "当前公开的是实验设置、数据范围、对比基线、复现材料和作者承认的限制。",
        "这会改变模型和平台团队对能力边界、推理成本、可靠性和内部实验设计的预期。"
      ],
      "importance": "major",
      "image_urls": []
    },
    {
      "title": "Qwen 团队介绍机器人学习与多模态推理实验",
      "editorial_category": "ai_industry",
      "event_date": "2026-06-17",
      "url": "https://www.alibabacloud.com/blog/qwen-robotworld-boundless-worlds-for-embodied-agents_603268",
      "source": "Alibaba Cloud Blog",
      "tier": "T0",
      "entities": [
        "Alibaba Cloud Blog"
      ],
      "summary": "36Kr 专访围绕具身智能短板、VLA 与世界模型关系展开，核心是机器人是否能补上物理规律和因果预测能力。",
      "bullets": [
        "**具身智能路线**：专访把 VLA、世界模型和机器人对物理因果的理解放在一起，重点是当前系统仍缺少稳定的物理预测能力。",
        "**Qwen 团队介绍机器人学习与多模态推理实验**：文章把行业焦虑落到具身智能的物理世界理解能力，讨论世界模型是否能成为补足 VLA 路线短板的方向。",
        "当前公开的是部署方式、权限、上下文管理和失败恢复边界。"
      ],
      "importance": "major",
      "image_urls": []
    },
    {
      "title": "Official Microsoft Blog: Achieving Success With AI",
      "editorial_category": "company_business",
      "event_date": "2026-06-16",
      "url": "https://blogs.microsoft.com/blog/2026/06/16/achieving-success-with-ai/",
      "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。",
        "已披露细节覆盖投入方向、合作节奏、组织动作、执行安排和后续资源配置。",
        "这会影响市场对供应商投入方向、合作优先级和组织重心的判断。"
      ],
      "importance": "major",
      "image_urls": []
    },
    {
      "title": "DeepMind展示住房建设约束规划项目",
      "editorial_category": "ai_industry",
      "event_date": "2026-06-16",
      "url": "https://deepmind.google/blog/unlocking-uk-house-building-with-ai-accelerated-planning/",
      "source": "Google DeepMind RSS",
      "tier": "T0",
      "entities": [
        "Google DeepMind RSS"
      ],
      "summary": "DeepMind展示住房建设约束规划项目，材料覆盖选址约束、基础设施取舍、规划流程和公共部门决策支持，边界落在这类 AI 规划工具的价值取决于数据边界、审批流程和责任归属。",
      "bullets": [
        "**DeepMind展示住房建设约束规划项目**：材料把住房建设约束规划项目落到选址约束、基础设施取舍、规划流程和公共部门决策支持，已披露事实集中在规划约束、选址模型、基础设施取舍和公共部门使用场景。",
        "已披露细节覆盖适用对象、证据来源、执行安排、后续时间表和风险边界。",
        "这会影响产品团队判断路线优先级、接入时机、资源投入和后续风险预案。"
      ],
      "importance": "major",
      "image_urls": []
    },
    {
      "title": "Google Keyword Blog: Google Cloud Summit London 2026",
      "editorial_category": "ai_industry",
      "event_date": "2026-06-17",
      "url": "https://blog.google/company-news/inside-google/around-the-globe/google-europe/united-kingdom/google-cloud-summit-london-2026/",
      "source": "Google Keyword Blog",
      "tier": "T0",
      "entities": [
        "Google Keyword Blog"
      ],
      "summary": "Google Keyword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": [
        "**Google Keyword更新AI 产品、平台或工程**：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。",
        "已披露细节覆盖适用对象、证据来源、执行安排、后续时间表和风险边界。",
        "这会影响产品团队判断路线优先级、接入时机、资源投入和后续风险预案。"
      ],
      "importance": "major",
      "image_urls": []
    },
    {
      "title": "microsoft/easycopilotlab2 开源项目更新 agent 工作流能力",
      "editorial_category": "open_source",
      "event_date": "2026-06-16",
      "url": "https://github.com/microsoft/easycopilotlab2",
      "source": "Microsoft GitHub Organization",
      "tier": "T2",
      "entities": [
        "microsoft/easycopilotlab2"
      ],
      "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": [
        "**该开源项目推出企业 agent 工作流系统**：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": "notable",
      "image_urls": []
    },
    {
      "title": "Z.ai Hugging Face Organization: Glm 52 Blog",
      "editorial_category": "open_source",
      "event_date": "2026-06-17",
      "url": "https://huggingface.co/blog/zai-org/glm-52-blog",
      "source": "Z.ai Hugging Face Organization",
      "tier": "T0",
      "entities": [
        "Z.ai Hugging Face Organization"
      ],
      "summary": "相关团队更新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": [
        "**相关团队更新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": "major",
      "image_urls": []
    },
    {
      "title": "Agent Dashboard发布生产 agent 观测面板",
      "editorial_category": "engineering_toolchain",
      "event_date": "2026-06-16",
      "url": "https://x.ai/news/agent-dashboard",
      "source": "xAI Company News",
      "tier": "T0",
      "entities": [
        "xAI Company News"
      ],
      "summary": "Agent Dashboard发布生产 agent 观测面板，材料覆盖工具调用轨迹、事故时间线、成本归因、回滚状态和发布健康度，边界落在观测价值取决于能否把失败记录、成本和发布状态串进同一条链路。",
      "bullets": [
        "**Agent Dashboard发布生产 agent 观**：材料把生产 agent 观测面板落到工具调用轨迹、事故时间线、成本归因、回滚状态和发布健康度，已披露事实集中在tool-call traces、事故记录、成本归因和回滚状态。",
        "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": "major",
      "image_urls": []
    }
  ],
  "github_trending": [
    {
      "name": "apple/container",
      "repo": "apple/container",
      "readme_cache": {
        "key": "github-readme/apple/container/main/unknown",
        "hit": true,
        "repo": "apple/container",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/apple/container/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/apple/container",
      "event_date": "2026-06-17",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 1,
      "source_rank": 1,
      "source_scope": "weekly:all",
      "previous_rank": 2,
      "rank_delta": 1,
      "trend": "up",
      "importance": "notable",
      "description": "container 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，公开说明提到评测与回归、工具调用和工作流编排等能力，并提供测试或评测资产；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。"
    },
    {
      "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": "2026-06-17",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 2,
      "source_rank": 2,
      "source_scope": "weekly:all",
      "previous_rank": 17,
      "rank_delta": 15,
      "trend": "up",
      "importance": "notable",
      "description": "SkillSpector 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、评测与回归等能力，并提供测试或评测资产；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": "phuryn/pm-skills",
      "repo": "phuryn/pm-skills",
      "readme_cache": {
        "key": "github-readme/phuryn/pm-skills/main/unknown",
        "hit": true,
        "repo": "phuryn/pm-skills",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/phuryn/pm-skills/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/phuryn/pm-skills",
      "event_date": "2026-06-17",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 3,
      "source_rank": 3,
      "source_scope": "weekly:all",
      "previous_rank": 3,
      "rank_delta": 0,
      "trend": "same",
      "importance": "general",
      "description": "pm-skills 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，公开说明提到评测与回归、工具调用和工作流编排等能力，并提供测试或评测资产；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。"
    },
    {
      "name": "addyosmani/agent-skills",
      "repo": "addyosmani/agent-skills",
      "readme_cache": {
        "key": "github-readme/addyosmani/agent-skills/main/unknown",
        "hit": true,
        "repo": "addyosmani/agent-skills",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/addyosmani/agent-skills/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/addyosmani/agent-skills",
      "event_date": "2026-06-17",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 4,
      "source_rank": 4,
      "source_scope": "weekly:all",
      "previous_rank": 6,
      "rank_delta": 2,
      "trend": "up",
      "importance": "general",
      "description": "addyosmani/agent-skills 本周出现在开源榜单 weekly #4，本周 +11,431 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": "2026-06-17",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 5,
      "source_rank": 5,
      "source_scope": "weekly:all",
      "previous_rank": 1,
      "rank_delta": -4,
      "trend": "down",
      "importance": "general",
      "description": "iptv-org/iptv 本周出现在开源榜单 weekly #5，本周 +6,246 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": "mvanhorn/last30days-skill",
      "repo": "mvanhorn/last30days-skill",
      "readme_cache": {
        "key": "github-readme/mvanhorn/last30days-skill/main/unknown",
        "hit": true,
        "repo": "mvanhorn/last30days-skill",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/mvanhorn/last30days-skill/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/mvanhorn/last30days-skill",
      "event_date": "2026-06-17",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 6,
      "source_rank": 6,
      "source_scope": "weekly:all",
      "previous_rank": 1,
      "rank_delta": -5,
      "trend": "down",
      "importance": "general",
      "description": "last30days-skill 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、评测与回归等能力，并提供测试或评测资产；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": "chopratejas/headroom",
      "repo": "chopratejas/headroom",
      "readme_cache": {
        "key": "github-readme/chopratejas/headroom/main/unknown",
        "hit": true,
        "repo": "chopratejas/headroom",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/chopratejas/headroom/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/chopratejas/headroom",
      "event_date": "2026-06-17",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 7,
      "source_rank": 7,
      "source_scope": "weekly:all",
      "previous_rank": 5,
      "rank_delta": -2,
      "trend": "down",
      "importance": "general",
      "description": "chopratejas/headroom 本周出现在开源榜单 weekly #7，本周 +9,766 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": "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": "2026-06-17",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 8,
      "source_rank": 8,
      "source_scope": "weekly:all",
      "previous_rank": 3,
      "rank_delta": -5,
      "trend": "down",
      "importance": "general",
      "description": "Panniantong/Agent-Reach 本周出现在开源榜单 weekly #8，本周 +6,427 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": "2026-06-17",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 9,
      "source_rank": 9,
      "source_scope": "weekly:all",
      "previous_rank": 16,
      "rank_delta": 7,
      "trend": "up",
      "importance": "general",
      "description": "asgeirtj/system_prompts_leaks 本周出现在开源榜单 weekly #9，本周 +1,220 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": "music-assistant/server",
      "repo": "music-assistant/server",
      "readme_cache": {
        "key": "github-readme/music-assistant/server/main/unknown",
        "hit": true,
        "repo": "music-assistant/server",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/music-assistant/server/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/music-assistant/server",
      "event_date": "2026-06-17",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 10,
      "source_rank": 10,
      "source_scope": "weekly:all",
      "previous_rank": 11,
      "rank_delta": 1,
      "trend": "up",
      "importance": "general",
      "description": "music-assistant/server 本周出现在开源榜单 weekly #10，本周 +865 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": "soxoj/maigret",
      "repo": "soxoj/maigret",
      "readme_cache": {
        "key": "github-readme/soxoj/maigret/main/unknown",
        "hit": true,
        "repo": "soxoj/maigret",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/soxoj/maigret/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/soxoj/maigret",
      "event_date": "2026-06-17",
      "source": "GitHub Trending Python weekly",
      "language": "python",
      "window": "weekly",
      "rank": 11,
      "source_rank": 8,
      "source_scope": "weekly:python",
      "previous_rank": 10,
      "rank_delta": 2,
      "trend": "up",
      "importance": "general",
      "description": "maigret 是开发者工具、SDK 集成和平台适配相关的开源项目，公开说明提到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": "puppeteer/puppeteer",
      "repo": "puppeteer/puppeteer",
      "readme_cache": {
        "key": "github-readme/puppeteer/puppeteer/main/unknown",
        "hit": true,
        "repo": "puppeteer/puppeteer",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/puppeteer/puppeteer/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/puppeteer/puppeteer",
      "event_date": "2026-06-17",
      "source": "GitHub Trending TypeScript weekly",
      "language": "typescript",
      "window": "weekly",
      "rank": 12,
      "source_rank": 6,
      "source_scope": "weekly:typescript",
      "previous_rank": 14,
      "rank_delta": 8,
      "trend": "up",
      "importance": "general",
      "description": "puppeteer/puppeteer 本周出现在开源榜单 TypeScript weekly #12，本周 +353 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": "biomejs/biome",
      "repo": "biomejs/biome",
      "readme_cache": {
        "key": "github-readme/biomejs/biome/main/unknown",
        "hit": true,
        "repo": "biomejs/biome",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/biomejs/biome/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/biomejs/biome",
      "event_date": "2026-06-17",
      "source": "GitHub Trending Rust weekly",
      "language": "rust",
      "window": "weekly",
      "rank": 13,
      "source_rank": 1,
      "source_scope": "weekly:rust",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general",
      "description": "biomejs/biome 本周出现在开源榜单 Rust weekly #13，本周 +154 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": "juicedata/juicefs",
      "repo": "juicedata/juicefs",
      "readme_cache": {
        "key": "github-readme/juicedata/juicefs/main/unknown",
        "hit": true,
        "repo": "juicedata/juicefs",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/juicedata/juicefs/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/juicedata/juicefs",
      "event_date": "2026-06-17",
      "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": "juicefs 是模型评测、回归验证和工程质量控制相关的开源项目，公开说明提到评测与回归、记忆或知识检索等能力，并提供测试或评测资产、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。"
    },
    {
      "name": "jenkinsci/jenkins",
      "repo": "jenkinsci/jenkins",
      "readme_cache": {
        "key": "github-readme/jenkinsci/jenkins/master/unknown",
        "hit": true,
        "repo": "jenkinsci/jenkins",
        "sha": "unknown",
        "default_branch": "master",
        "source_url": "https://raw.githubusercontent.com/jenkinsci/jenkins/master/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/jenkinsci/jenkins",
      "event_date": "2026-06-17",
      "source": "GitHub Trending Java weekly",
      "language": "java",
      "window": "weekly",
      "rank": 15,
      "source_rank": 1,
      "source_scope": "weekly:java",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general",
      "description": "jenkins 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，公开说明提到评测与回归、工具调用和工作流编排等能力，并提供测试或评测资产、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。"
    },
    {
      "name": "roboflow/supervision",
      "repo": "roboflow/supervision",
      "readme_cache": {
        "key": "github-readme/roboflow/supervision/main/unknown",
        "hit": true,
        "repo": "roboflow/supervision",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/roboflow/supervision/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/roboflow/supervision",
      "event_date": "2026-06-17",
      "source": "GitHub Trending Python weekly",
      "language": "python",
      "window": "weekly",
      "rank": 16,
      "source_rank": 9,
      "source_scope": "weekly:python",
      "previous_rank": 11,
      "rank_delta": 2,
      "trend": "up",
      "importance": "general",
      "description": "roboflow/supervision 本周出现在开源榜单 Python weekly #16，本周 +1,669 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": "freeCodeCamp/freeCodeCamp",
      "repo": "freeCodeCamp/freeCodeCamp",
      "readme_cache": {
        "key": "github-readme/freecodecamp/freecodecamp/main/unknown",
        "hit": true,
        "repo": "freecodecamp/freecodecamp",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/freeCodeCamp/freeCodeCamp/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/freeCodeCamp/freeCodeCamp",
      "event_date": "2026-06-17",
      "source": "GitHub Trending TypeScript weekly",
      "language": "typescript",
      "window": "weekly",
      "rank": 17,
      "source_rank": 7,
      "source_scope": "weekly:typescript",
      "previous_rank": 7,
      "rank_delta": 0,
      "trend": "same",
      "importance": "general",
      "description": "freeCodeCamp/freeCodeCamp 本周出现在开源榜单 TypeScript weekly #17，本周 +2,003 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": "rolldown/rolldown",
      "repo": "rolldown/rolldown",
      "readme_cache": {
        "key": "github-readme/rolldown/rolldown/main/unknown",
        "hit": true,
        "repo": "rolldown/rolldown",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/rolldown/rolldown/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/rolldown/rolldown",
      "event_date": "2026-06-17",
      "source": "GitHub Trending Rust weekly",
      "language": "rust",
      "window": "weekly",
      "rank": 18,
      "source_rank": 2,
      "source_scope": "weekly:rust",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general",
      "description": "rolldown/rolldown 本周出现在开源榜单 Rust weekly #18，本周 +70 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": "kenn-io/agentsview",
      "repo": "kenn-io/agentsview",
      "readme_cache": {
        "key": "github-readme/kenn-io/agentsview/main/unknown",
        "hit": true,
        "repo": "kenn-io/agentsview",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/kenn-io/agentsview/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/kenn-io/agentsview",
      "event_date": "2026-06-17",
      "source": "GitHub Trending Go weekly",
      "language": "go",
      "window": "weekly",
      "rank": 19,
      "source_rank": 2,
      "source_scope": "weekly:go",
      "previous_rank": 14,
      "rank_delta": 12,
      "trend": "up",
      "importance": "general",
      "description": "agentsview 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": "apache/flink",
      "repo": "apache/flink",
      "readme_cache": {
        "key": "github-readme/apache/flink/master/unknown",
        "hit": true,
        "repo": "apache/flink",
        "sha": "unknown",
        "default_branch": "master",
        "source_url": "https://raw.githubusercontent.com/apache/flink/master/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/apache/flink",
      "event_date": "2026-06-17",
      "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": "flink 是模型评测、回归验证和工程质量控制相关的开源项目，公开说明提到评测与回归、记忆或知识检索、API/SDK 适配等能力，并提供示例、测试或评测资产；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。"
    }
  ],
  "huggingface_trending": [],
  "model_releases": [],
  "hot_blogs": [
    {
      "title": "AWS讲解SageMaker 推理容器缓存方案",
      "editorial_category": "content_aigc",
      "url": "https://aws.amazon.com/blogs/machine-learning/introducing-container-caching-in-amazon-sagemaker-ai-for-faster-model-scaling/",
      "publisher": "AWS Machine Learning Blog",
      "author": "AWS Machine Learning Blog",
      "event_date": "2026-06-16",
      "topic": "AIGC / content generation",
      "summary": "AWS讲解SageMaker 推理容器缓存方案，重点落在模型加载延迟、冷启动时间、发布风险和生产推理成本。更有价值的信息是容器缓存、模型加载、冷启动延迟和部署成本，判断这类方案时还要看收益取决于模型大小、镜像组织、缓存命中率和部署频率。文章分析内容生成工具怎样改变素材生产、创作流程、质量判断或商业边界。",
      "content_type": "blog",
      "importance": "notable",
      "image_urls": []
    },
    {
      "title": "NVIDIA拆解交易基础模型与反欺诈工作流",
      "editorial_category": "viewpoint_analysis",
      "url": "https://developer.nvidia.com/blog/build-your-own-transaction-foundation-model-for-financial-intelligence/",
      "publisher": "NVIDIA Developer Blog",
      "author": "NVIDIA Developer Blog",
      "event_date": "2026-06-16",
      "topic": "AI engineering tools",
      "summary": "NVIDIA拆解交易基础模型与反欺诈工作流，重点落在交易序列建模、特征流水线、合成数据边界和部署取舍。更有价值的信息是交易数据、序列建模、特征流水线和反欺诈部署，判断这类方案时还要看金融场景还要处理数据偏差、可解释性、误报成本和合规要求。",
      "content_type": "blog",
      "importance": "notable",
      "image_urls": []
    },
    {
      "title": "AWS说明多 agent 安全护栏方案",
      "editorial_category": "viewpoint_analysis",
      "url": "https://aws.amazon.com/blogs/machine-learning/safeguard-your-agentic-ai-applications-with-the-amazon-bedrock-guardrails-invokeguardrailchecks-api/",
      "publisher": "AWS Machine Learning Blog",
      "author": "AWS Machine Learning Blog",
      "event_date": "2026-06-16",
      "topic": "AI engineering tools",
      "summary": "AWS说明多 agent 安全护栏方案，重点落在策略检查、提示过滤、响应控制、企业应用和可观测性。更有价值的信息是Guardrails、策略检查、提示过滤和响应控制，判断这类方案时还要看多 agent 系统仍要处理策略一致性、误拦截、日志留存和人工兜底。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拆解XR 眼镜里的端侧 agent 开发流程",
      "editorial_category": "viewpoint_analysis",
      "url": "https://developer.nvidia.com/blog/building-ai-agents-for-ar-glasses-and-xr-devices-with-nvidia-xr-ai/",
      "publisher": "NVIDIA Developer Blog",
      "author": "NVIDIA Developer Blog",
      "event_date": "2026-06-16",
      "topic": "AI engineering tools",
      "summary": "NVIDIA拆解XR 眼镜里的端侧 agent 开发流程，重点落在端侧推理、语音交互、感知输入、avatar 渲染、SDK 集成和部署边界。更有价值的信息是XR AI、端侧推理、语音交互、感知输入和 SDK 集成，判断这类方案时还要看落地质量取决于设备算力、延迟、隐私权限、场景数据和开发者工具成熟度。",
      "content_type": "blog",
      "importance": "notable",
      "image_urls": []
    },
    {
      "title": "NVIDIA介绍游戏 agent SDK 与 Unreal 插件方案",
      "editorial_category": "viewpoint_analysis",
      "url": "https://developer.nvidia.com/blog/build-on-device-ai-companions-with-the-nvidia-ace-game-agent-sdk-and-unreal-engine-5-plugins/",
      "publisher": "NVIDIA Developer Blog",
      "author": "NVIDIA Developer Blog",
      "event_date": "2026-06-16",
      "topic": "AI engineering tools",
      "summary": "NVIDIA介绍游戏 agent SDK 与 Unreal 插件方案，重点落在角色行为、语音接口、本地推理、场景集成、插件工作流和部署取舍。更有价值的信息是ACE Game Agent SDK、Unreal Engine 插件、本地推理和角色行为接口，判断这类方案时还要看游戏内 agent 还要处理实时延迟、内容安全、角色一致性和引擎集成成本。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": "AWS说明SageMaker 推测解码并行化方案",
      "editorial_category": "viewpoint_analysis",
      "url": "https://aws.amazon.com/blogs/machine-learning/parallelize-speculative-decoding-with-p-eagle-on-amazon-sagemaker-ai/",
      "publisher": "AWS Machine Learning Blog",
      "author": "AWS Machine Learning Blog",
      "event_date": "2026-06-16",
      "topic": "AI engineering tools",
      "summary": "AWS说明SageMaker 推测解码并行化方案，重点落在draft model 并行、解码延迟、吞吐取舍、部署设置和适用条件。更有价值的信息是P-EAGLE、speculative decoding、SageMaker 部署和吞吐延迟指标，判断这类方案时还要看优化收益取决于模型结构、请求形态、草稿模型质量和线上延迟预算。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Blackwell MLPerf 训练性能结果",
      "editorial_category": "viewpoint_analysis",
      "image_url": "https://iprsoftwaremedia.com/219/files/202606/602edf4b1b6f2d23bf718143c3f3fa5e/6a3167733d63328a97fbbcd4_end-to-end-corp-blog-best-models-trained-1280x680-4660123-842x450/end-to-end-corp-blog-best-models-trained-1280x680-4660123-842x450_thmb.jpg",
      "image_alt": "Fastest, Largest, Strongest: NVIDIA Blackwell Sweeps MLPerf Training 6.0",
      "image_source": "feed",
      "url": "https://blogs.nvidia.com/blog/blackwell-mlperf-training-6-0/",
      "publisher": "NVIDIA Newsroom RSS",
      "author": "NVIDIA Newsroom RSS",
      "event_date": "2026-06-16",
      "topic": "AI industry",
      "summary": "NVIDIA披露Blackwell MLPerf 训练性能结果，重点落在训练基准、硬件吞吐、模型规模、对比设置和数据中心部署前提。更有价值的信息是Blackwell、MLPerf Training、吞吐指标和训练基准设置，判断这类方案时还要看benchmark 结果仍要结合任务类型、集群配置、能耗和真实训练负载判断。文章梳理一个 AI 产品、平台或工程实践的具体变化，而不是只给观点。",
      "content_type": "blog",
      "importance": "notable",
      "image_urls": []
    },
    {
      "title": "Planet AI更新agent 工作流和开发工具能力",
      "editorial_category": "viewpoint_analysis",
      "url": "https://huggingface.co/blog/amazon/strands-lerobot-hub-to-hardware",
      "publisher": "Planet AI",
      "author": "Planet AI",
      "event_date": "2026-06-17",
      "topic": "AI engineering tools",
      "summary": "Planet AI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": []
    }
  ],
  "chinese_media_dynamics": [
    {
      "title": "困住医疗AI的死循环，终于有国产玩家跑通了",
      "url": "https://www.qbitai.com/2026/06/436171.html",
      "publisher": "QbitAI",
      "author": "QbitAI",
      "event_date": "2026-06-17",
      "topic": "中文 AI 媒体动态",
      "summary": "困住医疗AI的死循环，终于有国产玩家跑通了：在多项关键医疗测评上打败了GPT-5.5。",
      "key_points": [
        "困住医疗AI的死循环，终于有国产玩家跑通了：在多项关键医疗测评上打败了GPT-5.5",
        "This is an intermediary/self-media lead; trace it to a primary source before treating it as a reported fact."
      ],
      "importance": "notable",
      "image_urls": []
    },
    {
      "title": "微信支付发布AI专属卡 WorkBuddy率先接入",
      "url": "https://www.qbitai.com/2026/06/436160.html",
      "publisher": "QbitAI",
      "author": "QbitAI",
      "event_date": "2026-06-17",
      "topic": "中文 AI 媒体动态",
      "summary": "微信支付发布AI专属卡 WorkBuddy率先接入：用户可以在与智能体的对话中提出消费需求。",
      "key_points": [
        "微信支付发布AI专属卡 WorkBuddy率先接入：用户可以在与智能体的对话中提出消费需求",
        "This is an intermediary/self-media lead; trace it to a primary source before treating it as a reported fact."
      ],
      "importance": "notable",
      "image_urls": []
    },
    {
      "title": "头部具身大脑公司再获数亿美元融资！世界模型路线，15家VC抢着投",
      "url": "https://www.qbitai.com/2026/06/436148.html",
      "publisher": "QbitAI",
      "author": "QbitAI",
      "event_date": "2026-06-17",
      "topic": "中文 AI 媒体动态",
      "summary": "头部具身大脑公司再获数亿美元融资！世界模型路线，15家VC抢着投：半年三连发：从开源到端侧再到训练场。",
      "key_points": [
        "头部具身大脑公司再获数亿美元融资",
        "世界模型路线，15家VC抢着投：半年三连发：从开源到端侧再到训练场",
        "This is an intermediary/self-media lead; trace it to a primary source before treating it as a reported fact."
      ],
      "importance": "notable",
      "image_urls": []
    },
    {
      "title": "Grok 4.3现已在Amazon Bedrock上正式可用",
      "url": "https://www.qbitai.com/2026/06/436134.html",
      "publisher": "QbitAI",
      "author": "QbitAI",
      "event_date": "2026-06-17",
      "topic": "中文 AI 媒体动态",
      "summary": "Grok 4.3现已在Amazon Bedrock上正式可用：xAI正式成为Amazon Bedrock的模型供应商之一。",
      "key_points": [
        "Grok 4.3现已在Amazon Bedrock上正式可用：xAI正式成为Amazon Bedrock的模型供应商之一",
        "This is an intermediary/self-media lead; trace it to a primary source before treating it as a reported fact."
      ],
      "importance": "notable",
      "image_urls": []
    },
    {
      "title": "天工3.1 重磅发布：上线 Skywork Design 与 Dynamic Workflows，给 AI 一张画布和一支军团",
      "url": "https://www.qbitai.com/2026/06/436110.html",
      "publisher": "QbitAI",
      "author": "QbitAI",
      "event_date": "2026-06-17",
      "topic": "中文 AI 媒体动态",
      "summary": "天工3.1 重磅发布：上线 Skywork Design 与 Dynamic Workflows，给 AI 一张画布和一支军团：天工超级智能体的收入实现了三倍增长。",
      "key_points": [
        "天工3.1 重磅发布：上线 Skywork Design 与 Dynamic Workflows，给 AI 一张画布和一支军团：天工超级智能体的收入实现了三倍增长",
        "This is an intermediary/self-media lead; trace it to a primary source before treating it as a rep"
      ],
      "importance": "notable",
      "image_urls": []
    },
    {
      "title": "刚刚，Fable-5之下，智谱开源的GLM-5.2拿下AI编程第一！",
      "url": "https://www.qbitai.com/2026/06/436085.html",
      "publisher": "QbitAI",
      "author": "QbitAI",
      "event_date": "2026-06-17",
      "topic": "中文 AI 媒体动态",
      "summary": "刚刚，Fable-5之下，智谱开源的GLM-5.2拿下AI编程第一！：1M上下文。",
      "key_points": [
        "刚刚，Fable-5之下，智谱开源的GLM-5.2拿下AI编程第一",
        "：1M上下文",
        "This is an intermediary/self-media lead; trace it to a primary source before treating it as a reported fact."
      ],
      "importance": "notable",
      "image_urls": []
    },
    {
      "title": "许锦波率分子之心完成逾亿美元融资，定义全球AI蛋白质产业新基建",
      "url": "https://www.qbitai.com/2026/06/436077.html",
      "publisher": "QbitAI",
      "author": "QbitAI",
      "event_date": "2026-06-17",
      "topic": "中文 AI 媒体动态",
      "summary": "许锦波率分子之心完成逾亿美元融资，定义全球AI蛋白质产业新基建：世界级科学家领跑AI蛋白第二次范式革命。",
      "key_points": [
        "许锦波率分子之心完成逾亿美元融资，定义全球AI蛋白质产业新基建：世界级科学家领跑AI蛋白第二次范式革命",
        "This is an intermediary/self-media lead; trace it to a primary source before treating it as a reported fact."
      ],
      "importance": "notable",
      "image_urls": []
    },
    {
      "title": "具透 | 动态应用网格、Liquid Glass 微调，watchOS 27 首个开发者测试版一览",
      "url": "https://sspai.com/post/110958",
      "publisher": "SSPAI",
      "author": "SSPAI",
      "event_date": "2026-06-17",
      "topic": "中文 AI 媒体动态",
      "summary": "具透 | 动态应用网格、Liquid Glass 微调，watchOS 27 首个开发者测试版一览：AI 之外，watchOS 27 中还有这些新功能。 查看全文。",
      "key_points": [
        "具透 | 动态应用网格、Liquid Glass 微调，watchOS 27 首个开发者测试版一览：AI 之外，watchOS 27 中还有这些新功能",
        "查看全文",
        "This is an intermediary/self-media lead; trace it to a primary source before treating it as a rep"
      ],
      "importance": "notable",
      "image_urls": []
    }
  ],
  "daily_tracking": [
    {
      "id": "openrouter-rankings",
      "name": "OpenRouter",
      "url": "https://openrouter.ai/rankings",
      "event_date": "2026-06-17",
      "source": "OpenRouter Rankings",
      "category": "model_usage",
      "importance": "notable",
      "change_status": "changed",
      "change_summary": "OpenRouter 本周 Top 10 已解析：#1 MiniMax M3 4.64T tokens；#2 DeepSeek V4 Flash 4.41T tokens；#3 Hy3 preview 3.84T tokens；Claude Opus 4.7 周变化 67%。",
      "summary": "OpenRouter 公开榜单显示，本周调用热度第一是 MiniMax M3（minimax，4.64T tokens，周变化 44%）。 Top 10 供应商分布为 anthropic 3、deepseek 3、minimax 1、openrouter 1、tencent 1、xiaomi 1，可用来观察开发者在 OpenRouter 平台内的真实调用偏好。 该快照只说明 OpenRouter 平台内使用热度，不能替代能力榜单或全市场份额判断。",
      "watch_points": [
        "Claude Opus 4.7 的周变化为 67%，需要结合发布、价格、免费额度和上下文窗口变化判断原因。",
        "若没有新进榜，重点看榜首和供应商份额是否迁移。",
        "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 3、minimax 1、openrouter 1、tencent 1、xiaomi 1",
          "trend": "unknown"
        },
        {
          "label": "#1",
          "value": "MiniMax M3（minimax）：4.64T tokens，周变化 44%",
          "trend": "up"
        },
        {
          "label": "#2",
          "value": "DeepSeek V4 Flash（deepseek）：4.41T tokens，周变化 4%",
          "trend": "up"
        },
        {
          "label": "#3",
          "value": "Hy3 preview（tencent）：3.84T tokens，周变化 9%",
          "trend": "up"
        },
        {
          "label": "#4",
          "value": "MiMo-V2.5（xiaomi）：3.66T tokens，周变化 34%",
          "trend": "up"
        },
        {
          "label": "#5",
          "value": "Claude Opus 4.7（anthropic）：2.69T tokens，周变化 67%",
          "trend": "up"
        },
        {
          "label": "#6",
          "value": "Owl Alpha（openrouter）：2.45T tokens，周变化 22%",
          "trend": "up"
        },
        {
          "label": "#7",
          "value": "DeepSeek V4 Pro（deepseek）：1.97T tokens，周变化 3%",
          "trend": "up"
        },
        {
          "label": "#8",
          "value": "Claude Sonnet 4.6（anthropic）：1.88T tokens，周变化 4%",
          "trend": "up"
        },
        {
          "label": "#9",
          "value": "Claude Opus 4.8（anthropic）：1.28T tokens，周变化 4%",
          "trend": "up"
        },
        {
          "label": "#10",
          "value": "DeepSeek V3.2（deepseek）：1.13T tokens，周变化 4%",
          "trend": "up"
        }
      ],
      "snapshot": {
        "type": "openrouter_rankings_public_page",
        "collection_method": "public_page_playwright",
        "snapshot_status": "complete",
        "snapshot_as_of": "2026-06-17T10:49:18.258Z",
        "source_url": "https://openrouter.ai/rankings",
        "top_entries": [
          {
            "rank": 1,
            "model": "MiniMax M3",
            "provider": "minimax",
            "tokens": "4.64T tokens",
            "change": "44%"
          },
          {
            "rank": 2,
            "model": "DeepSeek V4 Flash",
            "provider": "deepseek",
            "tokens": "4.41T tokens",
            "change": "4%"
          },
          {
            "rank": 3,
            "model": "Hy3 preview",
            "provider": "tencent",
            "tokens": "3.84T tokens",
            "change": "9%"
          },
          {
            "rank": 4,
            "model": "MiMo-V2.5",
            "provider": "xiaomi",
            "tokens": "3.66T tokens",
            "change": "34%"
          },
          {
            "rank": 5,
            "model": "Claude Opus 4.7",
            "provider": "anthropic",
            "tokens": "2.69T tokens",
            "change": "67%"
          },
          {
            "rank": 6,
            "model": "Owl Alpha",
            "provider": "openrouter",
            "tokens": "2.45T tokens",
            "change": "22%"
          },
          {
            "rank": 7,
            "model": "DeepSeek V4 Pro",
            "provider": "deepseek",
            "tokens": "1.97T tokens",
            "change": "3%"
          },
          {
            "rank": 8,
            "model": "Claude Sonnet 4.6",
            "provider": "anthropic",
            "tokens": "1.88T tokens",
            "change": "4%"
          },
          {
            "rank": 9,
            "model": "Claude Opus 4.8",
            "provider": "anthropic",
            "tokens": "1.28T tokens",
            "change": "4%"
          },
          {
            "rank": 10,
            "model": "DeepSeek V3.2",
            "provider": "deepseek",
            "tokens": "1.13T tokens",
            "change": "4%"
          }
        ],
        "official_component_snapshot": {
          "source": "official_dom",
          "component_kind": "openrouter_rankings",
          "source_url": "https://openrouter.ai/rankings",
          "captured_at": "2026-06-17T10:49:18.258Z",
          "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>MiniMax M3</td><td>minimax</td><td>4.64T tokens</td><td>44%</td></tr>\n        <tr><td>#2</td><td>DeepSeek V4 Flash</td><td>deepseek</td><td>4.41T tokens</td><td>4%</td></tr>\n        <tr><td>#3</td><td>Hy3 preview</td><td>tencent</td><td>3.84T tokens</td><td>9%</td></tr>\n        <tr><td>#4</td><td>MiMo-V2.5</td><td>xiaomi</td><td>3.66T tokens</td><td>34%</td></tr>\n        <tr><td>#5</td><td>Claude Opus 4.7</td><td>anthropic</td><td>2.69T tokens</td><td>67%</td></tr>\n        <tr><td>#6</td><td>Owl Alpha</td><td>openrouter</td><td>2.45T tokens</td><td>22%</td></tr>\n        <tr><td>#7</td><td>DeepSeek V4 Pro</td><td>deepseek</td><td>1.97T tokens</td><td>3%</td></tr>\n        <tr><td>#8</td><td>Claude Sonnet 4.6</td><td>anthropic</td><td>1.88T tokens</td><td>4%</td></tr>\n        <tr><td>#9</td><td>Claude Opus 4.8</td><td>anthropic</td><td>1.28T tokens</td><td>4%</td></tr>\n        <tr><td>#10</td><td>DeepSeek V3.2</td><td>deepseek</td><td>1.13T tokens</td><td>4%</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:ba75a68e760c6a68e6d6c9b43302f8f544ebdfde65e3aab7cb4a51d665fd79b9",
          "css_hash": "sha256:e5df3dc0e07de42f5c2ca4021bbf59258d47d1ef0fa569d55d98b09876618e43"
        },
        "history_entries": []
      },
      "tracking_component_snapshot": {
        "source": "OpenRouter",
        "component_kind": "openrouter_rankings",
        "source_url": "https://openrouter.ai/rankings",
        "collected_at": "2026-06-17T10:49:18.258Z",
        "selector_version": "openrouter-rankings-v1",
        "raw_dom_hash": "sha256:cf0186cc19f16ef14c443cd403e8274921f927967fb760365721c7042e6477c6",
        "data_hash": "sha256:44156e911a7aa4480a82e772abbe489244c4a4dab1d1d19950c7cc5b89c87c36",
        "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": "MiniMax M3",
                "provider": "minimax",
                "value": 4640000000000,
                "value_label": "4.64T tokens",
                "change": "44%"
              },
              {
                "rank": 2,
                "model": "DeepSeek V4 Flash",
                "provider": "deepseek",
                "value": 4410000000000,
                "value_label": "4.41T tokens",
                "change": "4%"
              },
              {
                "rank": 3,
                "model": "Hy3 preview",
                "provider": "tencent",
                "value": 3840000000000,
                "value_label": "3.84T tokens",
                "change": "9%"
              },
              {
                "rank": 4,
                "model": "MiMo-V2.5",
                "provider": "xiaomi",
                "value": 3660000000000,
                "value_label": "3.66T tokens",
                "change": "34%"
              },
              {
                "rank": 5,
                "model": "Claude Opus 4.7",
                "provider": "anthropic",
                "value": 2690000000000,
                "value_label": "2.69T tokens",
                "change": "67%"
              },
              {
                "rank": 6,
                "model": "Owl Alpha",
                "provider": "openrouter",
                "value": 2450000000000,
                "value_label": "2.45T tokens",
                "change": "22%"
              },
              {
                "rank": 7,
                "model": "DeepSeek V4 Pro",
                "provider": "deepseek",
                "value": 1970000000000,
                "value_label": "1.97T tokens",
                "change": "3%"
              },
              {
                "rank": 8,
                "model": "Claude Sonnet 4.6",
                "provider": "anthropic",
                "value": 1880000000000,
                "value_label": "1.88T tokens",
                "change": "4%"
              },
              {
                "rank": 9,
                "model": "Claude Opus 4.8",
                "provider": "anthropic",
                "value": 1280000000000,
                "value_label": "1.28T tokens",
                "change": "4%"
              },
              {
                "rank": 10,
                "model": "DeepSeek V3.2",
                "provider": "deepseek",
                "value": 1130000000000,
                "value_label": "1.13T tokens",
                "change": "4%"
              }
            ],
            "fallback_reason": ""
          },
          {
            "id": "openrouter-llm-leaderboard",
            "tab_id": "leaderboard",
            "label": "LLM Leaderboard",
            "chart": "leaderboard",
            "rows": [
              {
                "rank": 1,
                "model": "MiniMax M3",
                "provider": "minimax",
                "value": 4640000000000,
                "value_label": "4.64T tokens",
                "change": "44%"
              },
              {
                "rank": 2,
                "model": "DeepSeek V4 Flash",
                "provider": "deepseek",
                "value": 4410000000000,
                "value_label": "4.41T tokens",
                "change": "4%"
              },
              {
                "rank": 3,
                "model": "Hy3 preview",
                "provider": "tencent",
                "value": 3840000000000,
                "value_label": "3.84T tokens",
                "change": "9%"
              },
              {
                "rank": 4,
                "model": "MiMo-V2.5",
                "provider": "xiaomi",
                "value": 3660000000000,
                "value_label": "3.66T tokens",
                "change": "34%"
              },
              {
                "rank": 5,
                "model": "Claude Opus 4.7",
                "provider": "anthropic",
                "value": 2690000000000,
                "value_label": "2.69T tokens",
                "change": "67%"
              },
              {
                "rank": 6,
                "model": "Owl Alpha",
                "provider": "openrouter",
                "value": 2450000000000,
                "value_label": "2.45T tokens",
                "change": "22%"
              },
              {
                "rank": 7,
                "model": "DeepSeek V4 Pro",
                "provider": "deepseek",
                "value": 1970000000000,
                "value_label": "1.97T tokens",
                "change": "3%"
              },
              {
                "rank": 8,
                "model": "Claude Sonnet 4.6",
                "provider": "anthropic",
                "value": 1880000000000,
                "value_label": "1.88T tokens",
                "change": "4%"
              },
              {
                "rank": 9,
                "model": "Claude Opus 4.8",
                "provider": "anthropic",
                "value": 1280000000000,
                "value_label": "1.28T tokens",
                "change": "4%"
              },
              {
                "rank": 10,
                "model": "DeepSeek V3.2",
                "provider": "deepseek",
                "value": 1130000000000,
                "value_label": "1.13T tokens",
                "change": "4%"
              }
            ],
            "fallback_reason": ""
          }
        ],
        "rows": [
          {
            "rank": 1,
            "model": "MiniMax M3",
            "provider": "minimax",
            "value": 4640000000000,
            "value_label": "4.64T tokens",
            "change": "44%"
          },
          {
            "rank": 2,
            "model": "DeepSeek V4 Flash",
            "provider": "deepseek",
            "value": 4410000000000,
            "value_label": "4.41T tokens",
            "change": "4%"
          },
          {
            "rank": 3,
            "model": "Hy3 preview",
            "provider": "tencent",
            "value": 3840000000000,
            "value_label": "3.84T tokens",
            "change": "9%"
          },
          {
            "rank": 4,
            "model": "MiMo-V2.5",
            "provider": "xiaomi",
            "value": 3660000000000,
            "value_label": "3.66T tokens",
            "change": "34%"
          },
          {
            "rank": 5,
            "model": "Claude Opus 4.7",
            "provider": "anthropic",
            "value": 2690000000000,
            "value_label": "2.69T tokens",
            "change": "67%"
          },
          {
            "rank": 6,
            "model": "Owl Alpha",
            "provider": "openrouter",
            "value": 2450000000000,
            "value_label": "2.45T tokens",
            "change": "22%"
          },
          {
            "rank": 7,
            "model": "DeepSeek V4 Pro",
            "provider": "deepseek",
            "value": 1970000000000,
            "value_label": "1.97T tokens",
            "change": "3%"
          },
          {
            "rank": 8,
            "model": "Claude Sonnet 4.6",
            "provider": "anthropic",
            "value": 1880000000000,
            "value_label": "1.88T tokens",
            "change": "4%"
          },
          {
            "rank": 9,
            "model": "Claude Opus 4.8",
            "provider": "anthropic",
            "value": 1280000000000,
            "value_label": "1.28T tokens",
            "change": "4%"
          },
          {
            "rank": 10,
            "model": "DeepSeek V3.2",
            "provider": "deepseek",
            "value": 1130000000000,
            "value_label": "1.13T tokens",
            "change": "4%"
          }
        ],
        "previous_snapshot": null,
        "diff": {
          "summary": "No previous component snapshot was available for comparison.",
          "changed_rows": [],
          "new_entries": [
            "MiniMax M3",
            "DeepSeek V4 Flash",
            "Hy3 preview",
            "MiMo-V2.5",
            "Claude Opus 4.7",
            "Owl Alpha",
            "DeepSeek V4 Pro",
            "Claude Sonnet 4.6",
            "Claude Opus 4.8",
            "DeepSeek V3.2"
          ]
        },
        "cache_path": "",
        "fallback_reason": "",
        "official_component_snapshot": {
          "source": "official_dom",
          "component_kind": "openrouter_rankings",
          "source_url": "https://openrouter.ai/rankings",
          "captured_at": "2026-06-17T10:49:18.258Z",
          "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>MiniMax M3</td><td>minimax</td><td>4.64T tokens</td><td>44%</td></tr>\n        <tr><td>#2</td><td>DeepSeek V4 Flash</td><td>deepseek</td><td>4.41T tokens</td><td>4%</td></tr>\n        <tr><td>#3</td><td>Hy3 preview</td><td>tencent</td><td>3.84T tokens</td><td>9%</td></tr>\n        <tr><td>#4</td><td>MiMo-V2.5</td><td>xiaomi</td><td>3.66T tokens</td><td>34%</td></tr>\n        <tr><td>#5</td><td>Claude Opus 4.7</td><td>anthropic</td><td>2.69T tokens</td><td>67%</td></tr>\n        <tr><td>#6</td><td>Owl Alpha</td><td>openrouter</td><td>2.45T tokens</td><td>22%</td></tr>\n        <tr><td>#7</td><td>DeepSeek V4 Pro</td><td>deepseek</td><td>1.97T tokens</td><td>3%</td></tr>\n        <tr><td>#8</td><td>Claude Sonnet 4.6</td><td>anthropic</td><td>1.88T tokens</td><td>4%</td></tr>\n        <tr><td>#9</td><td>Claude Opus 4.8</td><td>anthropic</td><td>1.28T tokens</td><td>4%</td></tr>\n        <tr><td>#10</td><td>DeepSeek V3.2</td><td>deepseek</td><td>1.13T tokens</td><td>4%</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:ba75a68e760c6a68e6d6c9b43302f8f544ebdfde65e3aab7cb4a51d665fd79b9",
          "css_hash": "sha256:e5df3dc0e07de42f5c2ca4021bbf59258d47d1ef0fa569d55d98b09876618e43"
        },
        "public_trace": {
          "source_url": "https://openrouter.ai/rankings",
          "collected_at": "2026-06-17T10:49:18.258Z",
          "selector_version": "openrouter-rankings-v1",
          "data_hash": "sha256:44156e911a7aa4480a82e772abbe489244c4a4dab1d1d19950c7cc5b89c87c36",
          "top_rows": [
            {
              "rank": 1,
              "model": "MiniMax M3",
              "provider": "minimax",
              "value_label": "4.64T tokens",
              "change": "44%"
            },
            {
              "rank": 2,
              "model": "DeepSeek V4 Flash",
              "provider": "deepseek",
              "value_label": "4.41T tokens",
              "change": "4%"
            },
            {
              "rank": 3,
              "model": "Hy3 preview",
              "provider": "tencent",
              "value_label": "3.84T tokens",
              "change": "9%"
            },
            {
              "rank": 4,
              "model": "MiMo-V2.5",
              "provider": "xiaomi",
              "value_label": "3.66T tokens",
              "change": "34%"
            },
            {
              "rank": 5,
              "model": "Claude Opus 4.7",
              "provider": "anthropic",
              "value_label": "2.69T tokens",
              "change": "67%"
            },
            {
              "rank": 6,
              "model": "Owl Alpha",
              "provider": "openrouter",
              "value_label": "2.45T tokens",
              "change": "22%"
            },
            {
              "rank": 7,
              "model": "DeepSeek V4 Pro",
              "provider": "deepseek",
              "value_label": "1.97T tokens",
              "change": "3%"
            },
            {
              "rank": 8,
              "model": "Claude Sonnet 4.6",
              "provider": "anthropic",
              "value_label": "1.88T tokens",
              "change": "4%"
            },
            {
              "rank": 9,
              "model": "Claude Opus 4.8",
              "provider": "anthropic",
              "value_label": "1.28T tokens",
              "change": "4%"
            },
            {
              "rank": 10,
              "model": "DeepSeek V3.2",
              "provider": "deepseek",
              "value_label": "1.13T tokens",
              "change": "4%"
            }
          ],
          "diff": {
            "summary": "No previous component snapshot was available for comparison.",
            "changed_rows": [],
            "new_entries": [
              "MiniMax M3",
              "DeepSeek V4 Flash",
              "Hy3 preview",
              "MiMo-V2.5",
              "Claude Opus 4.7",
              "Owl Alpha",
              "DeepSeek V4 Pro",
              "Claude Sonnet 4.6",
              "Claude Opus 4.8",
              "DeepSeek V3.2"
            ]
          },
          "cache_status": "live",
          "fallback_reason": ""
        }
      }
    },
    {
      "id": "artificial-analysis-intelligence-index",
      "name": "Artificial Analysis",
      "url": "https://artificialanalysis.ai/evaluations/artificial-analysis-intelligence-index",
      "event_date": "2026-06-17",
      "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": "2026-06-17T10:49:18.258Z",
        "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": "2026-06-17T10:49:18.258Z",
          "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": "2026-06-17T10:49:18.258Z",
        "selector_version": "artificial-analysis-index-v1",
        "raw_dom_hash": "sha256:caa7d33c2116c5495c0ff87bb3af671e33346e063be109cb1e5beccdf50e227a",
        "data_hash": "sha256:a673bd2b91d22697e0ca6b71afbf6ab505f2a1c1c6c94f16c15975fe32ff3db9",
        "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": "2026-06-17T10:49:18.258Z",
          "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": "2026-06-17T10:49:18.258Z",
          "selector_version": "artificial-analysis-index-v1",
          "data_hash": "sha256:a673bd2b91d22697e0ca6b71afbf6ab505f2a1c1c6c94f16c15975fe32ff3db9",
          "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": "2026-06-17",
      "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": "2026-06-17T10:49:18.258Z",
        "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": "2026-06-17T10:49:18.258Z",
          "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": "2026-06-17T10:49:18.258Z",
        "selector_version": "swe-bench-pro-v1",
        "raw_dom_hash": "sha256:2d5ebf88219cf9ca3b8537c2a99a9339988bd6f4b8cb73e80b37c9c1e786a9a9",
        "data_hash": "sha256:4a2b521368077791598faa67547d3e67a97e2557092e96bc3a6b9223cb7d7496",
        "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": "2026-06-17T10:49:18.258Z",
          "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": "2026-06-17T10:49:18.258Z",
          "selector_version": "swe-bench-pro-v1",
          "data_hash": "sha256:4a2b521368077791598faa67547d3e67a97e2557092e96bc3a6b9223cb7d7496",
          "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": "apple/container",
      "editorial_category": "open_source",
      "domains": [
        "AI tooling"
      ],
      "url": "https://github.com/apple/container",
      "event_date": "2026-06-17",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "NVIDIA/SkillSpector",
      "editorial_category": "open_source",
      "domains": [
        "agent"
      ],
      "url": "https://github.com/NVIDIA/SkillSpector",
      "event_date": "2026-06-17",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "phuryn/pm-skills",
      "editorial_category": "open_source",
      "domains": [
        "AI tooling"
      ],
      "url": "https://github.com/phuryn/pm-skills",
      "event_date": "2026-06-17",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "addyosmani/agent-skills",
      "editorial_category": "open_source",
      "domains": [
        "agent"
      ],
      "url": "https://github.com/addyosmani/agent-skills",
      "event_date": "2026-06-17",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "iptv-org/iptv",
      "editorial_category": "open_source",
      "domains": [
        "AI tooling"
      ],
      "url": "https://github.com/iptv-org/iptv",
      "event_date": "2026-06-17",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "mvanhorn/last30days-skill",
      "editorial_category": "open_source",
      "domains": [
        "agent"
      ],
      "url": "https://github.com/mvanhorn/last30days-skill",
      "event_date": "2026-06-17",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "chopratejas/headroom",
      "editorial_category": "open_source",
      "domains": [
        "agent"
      ],
      "url": "https://github.com/chopratejas/headroom",
      "event_date": "2026-06-17",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "Panniantong/Agent-Reach",
      "editorial_category": "open_source",
      "domains": [
        "agent"
      ],
      "url": "https://github.com/Panniantong/Agent-Reach",
      "event_date": "2026-06-17",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "asgeirtj/system_prompts_leaks",
      "editorial_category": "open_source",
      "domains": [
        "agent"
      ],
      "url": "https://github.com/asgeirtj/system_prompts_leaks",
      "event_date": "2026-06-17",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "music-assistant/server",
      "editorial_category": "open_source",
      "domains": [
        "AI tooling"
      ],
      "url": "https://github.com/music-assistant/server",
      "event_date": "2026-06-17",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    }
  ],
  "builder_observations": [
    {
      "author": "Josh Woodward",
      "handle": "joshwoodward",
      "editorial_category": "x_discussion",
      "content": "原帖围绕模型产品和能力变化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": "🇧🇷World-changing AI companies are coming from Brazil. That’s why we’ve officially expanded our Google AI Futures Fund to Brazil, partnering with venture capital leader Monashees to launch the Gama Fund. We’re looking for an elite cohort of deep tech founders and will offer: - Early access to Google DeepMind models - Up to $2M in co-investment - $350k in Google Cloud & Gemini credits - Direct co-development with Google engineers at our new IPT Open campus hub Apply today: https://t.co/8sv9seJL...",
      "translation": "原帖围绕模型产品和能力变化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/joshwoodward",
      "url": "https://x.com/joshwoodward/status/2067025851829330076",
      "role": "builder",
      "event_date": "2026-06-16",
      "source": "follow-builders X feed",
      "importance": "notable",
      "image_urls": []
    },
    {
      "author": "Aaron Levie",
      "handle": "levie",
      "editorial_category": "x_discussion",
      "content": "原帖围绕模型产品和能力变化给出一条工程落地线索，重点是企业分发、销售和服务这些真正难被 AI 立刻抹平的成本；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": "One of the biggest questions in AI is how far behind open weights models remain from closed models at any given time. There are huge differences in market structures depending on whether open weights models remain 3 or 6 months behind, or if they fall behind by years. The answer to this will determine how the chip stack plays out, where inference can be run, what sovereign AI looks like, what happens at the applied AI layer, what the margin structure looks like in AI, how much companies can aff...",
      "translation": "原帖围绕模型产品和能力变化给出一条工程落地线索，重点是企业分发、销售和服务这些真正难被 AI 立刻抹平的成本；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/2067070918300664161",
      "role": "builder",
      "event_date": "2026-06-17",
      "source": "follow-builders X feed",
      "importance": "notable",
      "image_urls": []
    },
    {
      "author": "Madhu Guru",
      "handle": "realmadhuguru",
      "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": "The real prize in the SpaceX-Cursor deal is the agentic harness that will become the core for automating all knowledge work at scale. Here’s what SpaceX is getting: 1. Production-grade agentic harness -planning, context management, tool use, iteration, verification, memory, error recovery. Any product experience can be completely redesigned in an AI-native way with this harness. 2. Expertise on the full AI stack - model, evals, harness, application layer. 3. End to end product lifecycle focus: ...",
      "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/realmadhuguru",
      "url": "https://x.com/realmadhuguru/status/2066935654500671499",
      "role": "builder",
      "event_date": "2026-06-16",
      "source": "follow-builders X feed",
      "importance": "notable",
      "image_urls": []
    },
    {
      "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": "Bim bada boum. I am in France for the week and we are rolling out all the most exciting Codex features across Europe. Coincidence or did the team think I wasn't able to be productive otherwise? https://t.co/LilIl4XkJF",
      "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/2067064381855187231",
      "role": "builder",
      "event_date": "2026-06-17",
      "source": "follow-builders X feed",
      "importance": "notable",
      "image_urls": []
    },
    {
      "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": "This was fixed. You know what's coming 👀 Give us 24 hours to reset the Codex rate limits across all plans. https://t.co/vx3Jb7YT6K",
      "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/2066956441173323943",
      "role": "builder",
      "event_date": "2026-06-16",
      "source": "follow-builders X feed",
      "importance": "notable",
      "image_urls": []
    },
    {
      "author": "Thibault Sottiaux",
      "handle": "thsottiaux",
      "editorial_category": "x_discussion",
      "content": "原帖围绕AI 工具和 agent 实践给出一条工程落地线索，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": "Oy. We are aware that some Codex users are experiencing high error rates with \"model at capacity\" and are working to bring things back to being stable. https://t.co/R3dCKGGtQw",
      "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/2066865154902380796",
      "role": "builder",
      "event_date": "2026-06-16",
      "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": "Publishing a new tutorial to make Codex or Claude Code your personal advisor using a skill with 4 files. Plus, I managed to save Fable's advice too before it got restricted 🥲 📌 Subscribe to get the tutorial tmr: https://t.co/MbOfeFUJbn https://t.co/bYW7tP4v0l",
      "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/2067056979974160749",
      "role": "builder",
      "event_date": "2026-06-17",
      "source": "follow-builders X feed",
      "importance": "notable",
      "image_urls": []
    },
    {
      "author": "Aaron Levie",
      "handle": "levie",
      "editorial_category": "x_discussion",
      "content": "Aaron Levie 认为市场误判了“AI 会吞掉企业软件”的速度。写软件本身确实更便宜了，但企业软件真正昂贵的部分一直是分发、销售、实施和长期服务，所以 AI 不会自动抹平这些护城河。",
      "original_text": "The Cursor deal is symbolically quite significant. It was effectively the first mega success in the applied layer of AI. They firmly proved out the value proposition of having a deep domain focus, the role you play as a model router, when to lean into frontier models vs. when to train your own, and the role of applied AI GTM and distribution to make sure you’re actually taking advantage of the market opportunity. Every aspect of their business was tuned to carve out ground and keep doubling dow...",
      "translation": "Aaron Levie 认为市场误判了“AI 会吞掉企业软件”的速度。写软件本身确实更便宜了，但企业软件真正昂贵的部分一直是分发、销售、实施和长期服务，所以 AI 不会自动抹平这些护城河。",
      "avatar_url": "https://unavatar.io/x/levie",
      "url": "https://x.com/levie/status/2066908002809221496",
      "role": "builder",
      "event_date": "2026-06-16",
      "source": "follow-builders X feed",
      "importance": "notable",
      "image_urls": []
    }
  ],
  "official_org_updates": [],
  "evidence_assets": [],
  "generated_at": "2026-06-17T11:00:59.232Z",
  "report_status": "normal",
  "canonical_url": "https://jasonxzwen.github.io/ai-daily-cn/reports/2026/06/2026-06-17.html",
  "html_path": "reports/2026/06/2026-06-17.html",
  "stories": [
    {
      "story_id": "main-content-openai-news-predicting-model-behavior-before-release-by-simulating-deplo",
      "title": "OpenAI News RSS: Deployment Simulation",
      "importance": "major",
      "trend": "AI industry",
      "event_date": "2026-06-16",
      "primary_entity": "OpenAI News RSS",
      "event_type": "research",
      "object": "OpenAI News RSS: Deployment Simulation",
      "what_happened": "OpenAI披露模型能力和评估方法更新，材料覆盖能力边界、评估设置、数据来源、使用场景和限制说明，边界落在结论仍要依赖可复现评测、真实任务和公开限制。",
      "why_it_matters": "当前公开的是实验设置、数据范围、对比基线、复现材料和作者承认的限制。",
      "evidence_level": "primary",
      "sources": [
        {
          "label": "OpenAI News RSS",
          "url": "https://openai.com/index/deployment-simulation",
          "type": "official"
        }
      ]
    },
    {
      "story_id": "main-content-alibaba-cloud-blog-qwen-robotworld-boundless-worlds-for-embodied-agents",
      "title": "Qwen 团队介绍机器人学习与多模态推理实验",
      "importance": "major",
      "trend": "AI industry",
      "event_date": "2026-06-17",
      "primary_entity": "Alibaba Cloud Blog",
      "event_type": "update",
      "object": "Qwen 团队介绍机器人学习与多模态推理实验",
      "what_happened": "36Kr 专访围绕具身智能短板、VLA 与世界模型关系展开，核心是机器人是否能补上物理规律和因果预测能力。",
      "why_it_matters": "**Qwen 团队介绍机器人学习与多模态推理实验**：文章把行业焦虑落到具身智能的物理世界理解能力，讨论世界模型是否能成为补足 VLA 路线短板的方向。",
      "evidence_level": "primary",
      "sources": [
        {
          "label": "Alibaba Cloud Blog",
          "url": "https://www.alibabacloud.com/blog/qwen-robotworld-boundless-worlds-for-embodied-agents_603268",
          "type": "official"
        }
      ]
    },
    {
      "story_id": "main-content-microsoft-official-blog-achieving-success-with-ai",
      "title": "Official Microsoft Blog: Achieving Success With AI",
      "importance": "major",
      "trend": "AI industry",
      "event_date": "2026-06-16",
      "primary_entity": "Official Microsoft Blog",
      "event_type": "research",
      "object": "Official Microsoft Blog: Achieving Success With AI",
      "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": "已披露细节覆盖投入方向、合作节奏、组织动作、执行安排和后续资源配置。",
      "evidence_level": "primary",
      "sources": [
        {
          "label": "Official Microsoft Blog",
          "url": "https://blogs.microsoft.com/blog/2026/06/16/achieving-success-with-ai/",
          "type": "official"
        }
      ]
    },
    {
      "story_id": "main-content-google-deepmind-rss-unlocking-uk-house-building-with-ai-accelerated-plan",
      "title": "DeepMind展示住房建设约束规划项目",
      "importance": "major",
      "trend": "AI industry",
      "event_date": "2026-06-16",
      "primary_entity": "Google DeepMind RSS",
      "event_type": "update",
      "object": "DeepMind展示住房建设约束规划项目",
      "what_happened": "DeepMind展示住房建设约束规划项目，材料覆盖选址约束、基础设施取舍、规划流程和公共部门决策支持，边界落在这类 AI 规划工具的价值取决于数据边界、审批流程和责任归属。",
      "why_it_matters": "已披露细节覆盖适用对象、证据来源、执行安排、后续时间表和风险边界。",
      "evidence_level": "primary",
      "sources": [
        {
          "label": "Google DeepMind RSS",
          "url": "https://deepmind.google/blog/unlocking-uk-house-building-with-ai-accelerated-planning/",
          "type": "official"
        }
      ]
    },
    {
      "story_id": "main-content-google-keyword-scaling-the-uk-government-s-ai-vision",
      "title": "Google Keyword Blog: Google Cloud Summit London 2026",
      "importance": "major",
      "trend": "AI industry",
      "event_date": "2026-06-17",
      "primary_entity": "Google Keyword Blog",
      "event_type": "update",
      "object": "Google Keyword Blog: Google Cloud Summit London 2026",
      "what_happened": "Google Keyword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": "已披露细节覆盖适用对象、证据来源、执行安排、后续时间表和风险边界。",
      "evidence_level": "primary",
      "sources": [
        {
          "label": "Google Keyword Blog",
          "url": "https://blog.google/company-news/inside-google/around-the-globe/google-europe/united-kingdom/google-cloud-summit-london-2026/",
          "type": "official"
        }
      ]
    },
    {
      "story_id": "main-content-github-microsoft-org-microsoft-added-lanslote-to-microsoft-easycopilotla",
      "title": "microsoft/easycopilotlab2 开源项目更新 agent 工作流能力",
      "importance": "notable",
      "trend": "open source AI",
      "event_date": "2026-06-16",
      "primary_entity": "Microsoft GitHub Organization",
      "event_type": "launch",
      "object": "microsoft/easycopilotlab2 开源项目更新 agent 工作流能力",
      "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": "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。",
      "evidence_level": "primary",
      "sources": [
        {
          "label": "Microsoft GitHub Organization",
          "url": "https://github.com/microsoft/easycopilotlab2",
          "type": "github"
        }
      ]
    },
    {
      "story_id": "main-content-huggingface-zai-org-glm-5-2-built-for-long-horizon-tasks",
      "title": "Z.ai Hugging Face Organization: Glm 52 Blog",
      "importance": "major",
      "trend": "open source AI",
      "event_date": "2026-06-17",
      "primary_entity": "Z.ai Hugging Face Organization",
      "event_type": "update",
      "object": "Z.ai Hugging Face Organization: Glm 52 Blog",
      "what_happened": "相关团队更新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": "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。",
      "evidence_level": "primary",
      "sources": [
        {
          "label": "Z.ai Hugging Face Organization",
          "url": "https://huggingface.co/blog/zai-org/glm-52-blog",
          "type": "primary"
        }
      ]
    },
    {
      "story_id": "main-content-xai-company-news-agent-dashboard-in-grok-build",
      "title": "Agent Dashboard发布生产 agent 观测面板",
      "importance": "major",
      "trend": "AI products and developer workflow",
      "event_date": "2026-06-16",
      "primary_entity": "xAI Company News",
      "event_type": "launch",
      "object": "Agent Dashboard发布生产 agent 观测面板",
      "what_happened": "Agent Dashboard发布生产 agent 观测面板，材料覆盖工具调用轨迹、事故时间线、成本归因、回滚状态和发布健康度，边界落在观测价值取决于能否把失败记录、成本和发布状态串进同一条链路。",
      "why_it_matters": "当前公开的是部署方式、权限、上下文管理和失败恢复边界。",
      "evidence_level": "primary",
      "sources": [
        {
          "label": "xAI Company News",
          "url": "https://x.ai/news/agent-dashboard",
          "type": "official"
        }
      ]
    }
  ],
  "quality_status": {
    "status": "degraded",
    "public_note": "Some discovery coverage is degraded; this report may be incomplete.",
    "affected_sections": [
      "huggingface_trending"
    ],
    "degraded_events": [
      {
        "section": "huggingface_trending",
        "message": "huggingface_trending coverage is degraded and should be disclosed in the public report.",
        "severity": "degraded"
      }
    ]
  }
}