微软为 Copilot Researcher 推出 Critique 与 Council 功能,DRACO 测试得分 57.4 领先行业

GateNews

Gate News 消息,3 月 31 日,微软周一宣布为 Copilot Researcher 推出两项新功能——Critique 与 Council,将 OpenAI 的 GPT 与 Anthropic 的 Claude 结合用于同一研究任务。Critique 采用串联协作模式:GPT 负责规划研究、检索资料并生成初稿,Claude 随后担任审阅者,核查事实准确性与引用质量;Council 则让两个模型并行独立生成报告,再由第三个裁判模型对比差异、归纳分歧。在涵盖医疗、法律、科技等 10 个领域共 100 项复杂研究任务的 DRACO 基准测试中,搭载 Critique 的 Copilot 得分 57.4 分,领先第二名近 14%,远超 Claude Opus 4.6 单独运行的 42.7 分。

Disclaimer: The information on this page may come from third parties and does not represent the views or opinions of Gate. The content displayed on this page is for reference only and does not constitute any financial, investment, or legal advice. Gate does not guarantee the accuracy or completeness of the information and shall not be liable for any losses arising from the use of this information. Virtual asset investments carry high risks and are subject to significant price volatility. You may lose all of your invested principal. Please fully understand the relevant risks and make prudent decisions based on your own financial situation and risk tolerance. For details, please refer to Disclaimer.
Commento
0/400
Nessun commento