[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-gpt-55-tops-artificial-analysis-score-60-zh":3,"article-related-gpt-55-tops-artificial-analysis-score-60-zh":30,"series-tools-39f058b8-5f14-4b03-b717-457e28c7130e":74},{"id":4,"slug":5,"title":6,"content":7,"summary":8,"source":9,"source_url":10,"author":11,"image_url":12,"cover_image":12,"category":13,"language":14,"translated_content":11,"related_article_id":15,"keywords":16,"key_takeaways":22,"views":26,"created_at":27,"published_at":28,"topic_cluster_id":29},"39f058b8-5f14-4b03-b717-457e28c7130e","gpt-55-tops-artificial-analysis-score-60-zh","GPT-5.5 以 60 分登頂","\u003Cp data-speakable=\"summary\">Artificial Analysis 將 GPT-5.5（xhigh）排在智能榜首，分數是 60。\u003C\u002Fp>\u003Cp>這次\u003Ca href=\"\u002Fnews\u002F5-grok-updates-turn-chat-into-tools-zh\">更新把\u003C\u002Fa> 523 款模型放進同一個比較頁，涵蓋智能、速度、延遲、價格與上下文窗口。對只想快速選 \u003Ca href=\"\u002Ftag\u002Fapi\">API\u003C\u002Fa> 的\u003Ca href=\"\u002Fnews\u002Fgoogle-ai-studio-android-app-building-web-zh\">開發\u003C\u002Fa>者來說，這比翻一堆單篇 benchmark 省事得多。\u003C\u002Fp>\u003Ctable>\u003Cthead>\u003Ctr>\u003Cth>項目\u003C\u002Fth>\u003Cth>數值\u003C\u002Fth>\u003C\u002Ftr>\u003C\u002Fthead>\u003Ctbody>\u003Ctr>\u003Ctd>智能榜首\u003C\u002Ftd>\u003Ctd>GPT-5.5 (xhigh)\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>智能分數\u003C\u002Ftd>\u003Ctd>60\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>納入模型數\u003C\u002Ftd>\u003Ctd>523\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Intelligence Index 版本\u003C\u002Ftd>\u003Ctd>v4.0\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>v4.0 評測數\u003C\u002Ftd>\u003Ctd>10\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>最快模型\u003C\u002Ftd>\u003Ctd>Mercury 2\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>最高速度\u003C\u002Ftd>\u003Ctd>825 tokens\u002Fs\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>最低延遲模型\u003C\u002Ftd>\u003Ctd>Command A+\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>最低延遲\u003C\u002Ftd>\u003Ctd>0.33s\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>最便宜模型\u003C\u002Ftd>\u003Ctd>Qwen3.5 0.8B\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>最低價格\u003C\u002Ftd>\u003Ctd>$0.01 \u002F 1M tokens\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>最大上下文窗口\u003C\u002Ftd>\u003Ctd>Llama 4 Scout\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>最大上下文\u003C\u002Ftd>\u003Ctd>10m tokens\u003C\u002Ftd>\u003C\u002Ftr>\u003C\u002Ftbody>\u003C\u002Ftable>\u003Ch2>發生了什麼\u003C\u002Fh2>\u003Cp>\u003Ca href=\"https:\u002F\u002Fartificialanalysis.ai\" target=\"_blank\" rel=\"noopener\">Artificial Analysis\u003C\u002Fa> 更新了模型比較中心，現在可直接對照智能、輸出速度、延遲、價格與 context window。它的 Intelligence Index v4.0 這次採用 10 項評測，包含 GDPval-AA、Terminal-Bench Hard、SciCode、AA-Omniscience、Humanity's Last Exam、GPQA Diamond 與 CritPt。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779537969912-mv8m.png\" alt=\"GPT-5.5 以 60 分登頂\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>榜單頂端由 GPT-5.5（xhigh）與 GPT-5.5（high）包辦，分數都站在前段班。後面則是 \u003Ca href=\"https:\u002F\u002Fwww.anthropic.com\" target=\"_blank\" rel=\"noopener\">Claude\u003C\u002Fa> \u003Ca href=\"\u002Ftag\u002Fopus-47\">Opus 4.7\u003C\u002Fa>（max）與 \u003Ca href=\"https:\u002F\u002Fgemini.google\" target=\"_blank\" rel=\"noopener\">Gemini\u003C\u002Fa> 3.1 Pro Preview，顯示高階模型競爭仍集中在少數幾家。\u003C\u002Fp>\u003Cp>其他欄位也很直觀：Mercury 2 以 825 tokens\u002Fs 拿下速度第一，Command A+ 以 0.33 秒延遲居首，Qwen3.5 0.8B 以每 100 萬 tokens 0.01 美元成為最便宜選項，\u003Ca href=\"https:\u002F\u002Fai.meta.com\" target=\"_blank\" rel=\"noopener\">Llama\u003C\u002Fa> 4 Scout 則把上下文窗口拉到 1000 萬 tokens。這讓同一頁就能看出不同模型各自擅長的方向。\u003C\u002Fp>\u003Cul>\u003Cli>523 款模型被放進同一個比較框架。\u003C\u002Fli>\u003Cli>Intelligence Index v4.0 使用 10 項評測。\u003C\u002Fli>\u003Cli>價格欄位採 blended cache-input-output rate。\u003C\u002Fli>\u003Cli>開源與商用模型都一起列出。\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>為什麼重要\u003C\u002Fh2>\u003Cp>對開發者來說，這種排行的價值不在於誰拿第一，而在於能不能快速做取捨。做 \u003Ca href=\"\u002Ftag\u002Fagent\">agent\u003C\u002Fa>、\u003Ca href=\"\u002Ftag\u002Frag\">RAG\u003C\u002Fa>、coding assistant 或高流量 API 服務時，智能分數高不代表成本、延遲與上下文也能同時過關。\u003C\u002Fp>\u003Cp>這也影響採購方式。團隊如果只看單一 benchmark，很容易選到「最會答題」但不適合產品的模型；把價格、吞吐與延遲一起看，才比較接近真實\u003Ca href=\"\u002Fnews\u002Fwhy-xai-grok-3-api-launch-matters-zh\">上線\u003C\u002Fa>條件。\u003C\u002Fp>\u003Cp>換句話說，現在的模型競爭已經不是單點比高分，而是看誰能在品質、速度與成本之間拿出更實用的組合。對產品團隊而言，這種表格比宣傳頁更接近決策工具。\u003C\u002Fp>\u003Ch2>結尾\u003C\u002Fh2>\u003Cp>GPT-5.5 以 60 分登頂，真正的訊號是：模型選型正在從「誰最強」變成「誰最適合你的工作負載」。下一次要下單前，先問自己：你要的是最高分，還是最能跑產品的那一個？\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779537965566-kf35.png\" alt=\"GPT-5.5 以 60 分登頂\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n","Artificial Analysis 更新 523 款模型排行，GPT-5.5（xhigh）以 60 分拿下智能榜首，並同步顯示速度、延遲、價格與上下文窗口比較。","artificialanalysis.ai","https:\u002F\u002Fartificialanalysis.ai\u002Fmodels",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779537969912-mv8m.png","tools","zh","a08034a7-cc0d-470a-8af6-a9cb95738cca",[17,18,19,20,21],"GPT-5.5","Artificial Analysis","benchmark","model ranking","AI model comparison",[23,24,25],"GPT-5.5（xhigh）在 Artificial Analysis 智能榜拿下 60 分第一。","這次更新納入 523 款模型，並把速度、延遲、價格與上下文放在同頁比較。","對開發者而言，選模型不再只看分數，而是看是否符合產品的成本與效能需求。",5,"2026-05-23T12:05:38.079215+00:00","2026-05-23T12:05:38.041+00:00","c3c88dd2-a940-438a-b359-0e5a24562273",{"tags":31,"relatedLang":33,"relatedPosts":37},[32],{"name":19,"slug":19},{"id":15,"slug":34,"title":35,"language":36},"gpt-55-tops-artificial-analysis-score-60-en","GPT-5.5 tops Artificial Analysis with score of 60","en",[38,44,50,56,62,68],{"id":39,"slug":40,"title":41,"cover_image":42,"image_url":42,"created_at":43,"category":13},"419deb6d-ea65-4fa7-9dd1-73763f373b53","bailian-token-plan-agent-credits-guide-zh","百炼Token Plan把Agent接入变简单","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783929835818-cyp6.png","2026-07-13T08:03:24.024727+00:00",{"id":45,"slug":46,"title":47,"cover_image":48,"image_url":48,"created_at":49,"category":13},"5c5c6733-6f41-49ca-b61e-c0a53399c327","one-api-gateway-turns-six-ai-apis-into-one-zh","一個閘道把六個 AI API 收成一套","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783883027640-gz6i.png","2026-07-12T19:03:22.171684+00:00",{"id":51,"slug":52,"title":53,"cover_image":54,"image_url":54,"created_at":55,"category":13},"953466bc-6d94-4ffe-944b-ac7728d09184","fde-playbook-fixes-broken-agent-projects-zh","FDE 讓烂尾 Agent 回正軌","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783881221882-yw1n.png","2026-07-12T18:33:16.193979+00:00",{"id":57,"slug":58,"title":59,"cover_image":60,"image_url":60,"created_at":61,"category":13},"bd3b5d5c-02d9-49c4-8ca4-dcb6df373374","ai-zaobao-template-daily-to-reusable-report-zh","AI 早报拆成可复用周报","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783879420413-rlwb.png","2026-07-12T18:03:11.617929+00:00",{"id":63,"slug":64,"title":65,"cover_image":66,"image_url":66,"created_at":67,"category":13},"33302498-49ec-4a00-8e2c-61b6f9fc3ece","claude-reflect-turns-usage-into-retention-zh","Claude Reflect 把使用變留存","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783793005956-n1ea.png","2026-07-11T18:03:01.486301+00:00",{"id":69,"slug":70,"title":71,"cover_image":72,"image_url":72,"created_at":73,"category":13},"5f08bf54-0ddb-4884-b541-75e33ad21b30","midjourney-turns-prompt-ideas-into-art-zh","Midjourney 把提示詞變成可重用流程","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783694003831-eilt.png","2026-07-10T14:32:55.765266+00:00",[75,80,85,90,95,100,105,110,115,120],{"id":76,"slug":77,"title":78,"created_at":79},"855cd52f-6fab-46cc-a7c1-42195e8a0de4","surepath-real-time-mcp-policy-controls-zh","SurePath 推出即時 MCP 政策控管","2026-03-26T07:57:40.77233+00:00",{"id":81,"slug":82,"title":83,"created_at":84},"9b19ab54-edef-4dbd-9ce4-a51e4bae4ebb","mcp-in-2026-the-ai-tool-layer-teams-use-zh","2026 年 MCP：團隊真的在用的 AI 工具層","2026-03-26T08:01:46.589694+00:00",{"id":86,"slug":87,"title":88,"created_at":89},"af9c46c3-7a28-410b-9f04-32b3de30a68c","prompting-in-2026-what-actually-works-zh","2026 提示工程，真正有用的是什麼","2026-03-26T08:08:12.453028+00:00",{"id":91,"slug":92,"title":93,"created_at":94},"05553086-6ed0-4758-81fd-6cab24b575e0","garry-tan-open-sources-claude-code-toolkit-zh","Garry Tan 開源 Claude Code 工具包","2026-03-26T08:26:20.068737+00:00",{"id":96,"slug":97,"title":98,"created_at":99},"042a73a2-18a2-433d-9e8f-9802b9559aac","github-ai-projects-to-watch-in-2026-zh","2026 必看 20 個 GitHub AI 專案","2026-03-26T08:28:09.619964+00:00",{"id":101,"slug":102,"title":103,"created_at":104},"a5f94120-ac0d-4483-9a8b-63590071ac6a","claude-code-vs-cursor-2026-zh","Claude Code 與 Cursor 深度對比：202…","2026-03-26T13:27:14.279193+00:00",{"id":106,"slug":107,"title":108,"created_at":109},"0975afa1-e0c7-4130-a20d-d890eaed995e","practical-github-guide-learning-ml-2026-zh","2026 機器學習入門 GitHub 實用指南","2026-03-27T01:16:49.712576+00:00",{"id":111,"slug":112,"title":113,"created_at":114},"bfdb467a-290f-4a80-b3a9-6f081afb6dff","aiml-2026-student-ai-ml-lab-repo-review-zh","AIML-2026：像課綱的學生實驗 Repo","2026-03-27T01:21:51.467798+00:00",{"id":116,"slug":117,"title":118,"created_at":119},"80cabc3e-09fc-4ff5-8f07-b8d68f5ae545","ai-trending-github-repos-and-research-feeds-zh","AI Trending：把 AI 資源收成一張表","2026-03-27T01:31:35.262183+00:00",{"id":121,"slug":122,"title":123,"created_at":124},"3ce6e6e2-bac5-463e-9f8d-45caabcc61f7","awesome-ai-for-science-research-tools-map-zh","AI 科研工具清單，開始像地圖了","2026-03-27T01:46:50.521945+00:00"]