{
 "generated": "2026-11-03",
 "node": {
  "id": "event:sig-0088",
  "type": "Event",
  "name": "SemiAnalysis 自己做了个前沿模型基准 GDPx：最高分只有 12%，金融与法律在二元评分下全军 0%",
  "slug": "sig-0088",
  "kind": "signal",
  "kind_zh": "行业信号",
  "date": "2026-11-03",
  "summary": "11-02 发布，定位是取代 OpenAI 已显陈旧的 GDPval。覆盖 11 个高价值领域（芯片设计、网络安全、生物、金融、法律、量化交易、RSI、硬件设计、材料科学、对齐、软件工程），联合 14 家垂类数据供应商出题，强调真实 agentic 工作环境而不是孤立任务。结果是最高分模型综合只拿到 12%，Opus 5.5 在量化交易和芯片设计等领域领先；金融和法律任务难到所有模型在二元评分下都是 0%；部分模型还被自家安全分类器显著拉低分数。独立研究机构下场自建产业价值口径的基准，这是第一家。",
  "url": "https://newsletter.semianalysis.com/p/gdpx-measuring-frontier-model-capabilities",
  "evidence": [
   {
    "kind": "own",
    "label": "本站页面",
    "url": "https://xiaopingfeng.com/graph/signals/#sig-0088",
    "text": "AI 行业信号流（独立研究机构）：SemiAnalysis 自己做了个前沿模型基准 GDPx：最高分只有 12%，金融与法律在二元评分下全军 0%"
   },
   {
    "kind": "media",
    "url": "https://newsletter.semianalysis.com/p/gdpx-measuring-frontier-model-capabilities",
    "text": "信号的原文出处（SemiAnalysis）"
   }
  ],
  "entry": "derived",
  "category": "research",
  "category_zh": "独立研究机构",
  "source_name": "SemiAnalysis",
  "source_id": "org-semianalysis",
  "links": [
   {
    "label": "SemiAnalysis",
    "url": "https://newsletter.semianalysis.com/p/gdpx-measuring-frontier-model-capabilities"
   }
  ],
  "degree": 0
 },
 "page": "https://xiaopingfeng.com/graph/e/event/sig-0088/",
 "out": [
  {
   "type": "placed_in",
   "sentence": "SemiAnalysis 自己做了个前沿模型基准 GDPx：最高分只有 12%，金融与法律在二元评分下全军 0%出现在 Landscape 的「独立研究机构」",
   "direction": "out",
   "id": "layer:ai-industry-signals--5",
   "name": "独立研究机构",
   "status": "derived",
   "evidence": [
    {
     "kind": "own",
     "label": "本站页面",
     "url": "https://xiaopingfeng.com/graph/signals/#sig-0088",
     "text": "AI 行业信号流（独立研究机构）：SemiAnalysis 自己做了个前沿模型基准 GDPx：最高分只有 12%，金融与法律在二元评分下全军 0%"
    }
   ]
  },
  {
   "type": "involves",
   "sentence": "SemiAnalysis 自己做了个前沿模型基准 GDPx：最高分只有 12%，金融与法律在二元评分下全军 0%涉及SemiAnalysis",
   "direction": "out",
   "id": "org:semianalysis",
   "name": "SemiAnalysis",
   "role": "issuer",
   "note": "信源：SemiAnalysis",
   "status": "derived",
   "evidence": [
    {
     "kind": "own",
     "label": "本站页面",
     "url": "https://xiaopingfeng.com/graph/signals/#sig-0088",
     "text": "AI 行业信号流（独立研究机构）：SemiAnalysis 自己做了个前沿模型基准 GDPx：最高分只有 12%，金融与法律在二元评分下全军 0%"
    }
   ]
  },
  {
   "type": "mentions",
   "sentence": "SemiAnalysis 自己做了个前沿模型基准 GDPx：最高分只有 12%，金融与法律在二元评分下全军 0%提到OpenAI",
   "direction": "out",
   "id": "org:openai",
   "name": "OpenAI",
   "status": "derived",
   "evidence": [
    {
     "kind": "own",
     "label": "本站页面",
     "text": "名称匹配：「OpenAI」出现在信号的正文里",
     "url": "https://xiaopingfeng.com/graph/signals/#sig-0088"
    }
   ]
  }
 ],
 "in": []
}