四款國產模型集成登頂 DRACO 榜單把簡體中文原文的重點轉成繁體中文讀者更容易閱讀的脈絡。核心在於 OpenSquilla argues that routing and consensus across four Chinese models can beat single flagship models on deep-research tasks at lower cost.
變化在哪裡
目前可核驗的事實包括：DeepSeek v4, GLM-5.2, Kimi K2.7 and Qwen3.7 in an Agentic Routing flow, Brave Search DRACO score 64.09 versus Opus 4.8 at 59.11 and GPT-5.5 at 53.28, average task cost of $0.12, and DuckDuckGo score 60.85 at $0.39。這些細節讓新聞不只停留在發布會口號。
為什麼重要
The harness layer can become valuable when it selects models, collects evidence, merges answers and logs decisions rather than buying only the strongest model. AI 新聞已經不能只看模型分數，還要看成本、供應、監管與真實工作流程。
接下來看什麼
DRACO uses LLM judging, so real workflows must confirm long-task failure rates, traceability and enterprise deployment cost. 下一步要看的不是更多宣傳，而是第三方測試、客戶續用與長時間穩定性。
參考來源：OpenSquilla GitHub, Agentic Routing technical report and DRACO leaderboard、CocoLoop。