Meituan’s LongCat Team Releases VitaBench 2.0 Agent Evaluation Benchmark
2026-06-25 13:12:48
Meituan’s LongCat team has released VitaBench 2.0, following the launch of VitaBench 1.0 in October 2025, according to 36Kr. The company described VitaBench 2.0 as an agent evaluation benchmark for long-term, dynamic user modeling in real-life scenarios, designed to systematically assess large language models’ personalization and proactiveness in sustained, real, and changing user interactions.
Disclaimer:
1. The information provided does not constitute investment advice. Investors should make independent decisions and bear all risks themselves.
2. The copyright of this content belongs to the original author. The views expressed herein are solely those of the author and do not represent the stance or position of this website.
