Microsoft introduces Critique and Council features for Copilot Researcher, with a DRACO test score of 57.4, leading the industry

GateNews

Gate News update. On March 31, Monday, Microsoft announced two new features for Copilot Researcher—Critique and Council—combining OpenAI’s GPT and Anthropic’s Claude for the same research tasks. Critique uses a sequential collaborative mode: GPT is responsible for planning the research, retrieving sources, and drafting an initial report, and then Claude acts as a reviewer to verify factual accuracy and the quality of citations; Council, meanwhile, lets the two models generate reports in parallel independently, and then a third judge model compares differences and summarizes disagreements. In the DRACO benchmark test covering 100 complex research tasks across 10 fields including healthcare, law, and technology, Copilot with Critique scored 57.4, nearly 14% ahead of second place, far exceeding the 42.7 score Claude Opus achieved when running alone.

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.
Comment
0/400
No comments