{
  "id": 238637,
  "title": "Qwen3.8 Max now ranked as the best overall model by agentic index",
  "url": "https://urgent.news/2026/08/06/qwen3-8-max-now-ranked-as-the-best-overall-model-by-agentic-index",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-06T18:44:49.000Z",
  "source": {
    "name": "Hacker News Best",
    "slug": "hacker-news-best",
    "url": "https://artificialanalysis.ai/?intelligence=agentic-index"
  },
  "original_language": "en",
  "account": "Agentic Analysis Index v4.1.1 has crowned Qwen3.8 Max as the top overall model, according to recent evaluations. The index assesses models based on GDPval-AA v2, τ³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, and AA-LCR. These evaluations encompass various tasks, such as GDP valuation, banking, software engineering, coding, text-to-speech, speech-to-text, speech-to-speech, and quantitative analysis on spreadsheets and documents. The index also factors in the availability of model weights, weighted average costs, and performance metrics across different AI models. Qwen3.8 Max's superior performance across these diverse tasks solidifies its position as the most versatile and efficient model according to the Agentic Analysis Index.",
  "summary": "Article URL: https://artificialanalysis.ai/?intelligence=agentic-index Comments URL: https://news.ycombinator.com/item?id=49200652 Points: 368 # Comments: 228",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}