Meituan LongCat Launches General 365: A New Benchmark Highlighting AI Reasoning Gaps
Meituan's LongCat team has officially released General 365, a new evaluation benchmark focused on the reasoning capabilities of Large Language Models (LLMs). The benchmark's debut included a comprehensive test of 26 mainstream models, revealing that complex reasoning remains a significant hurdle for current AI technology. According to the results, Gemini 3 Pro—currently considered one of the most powerful models—achieved an accuracy rate of only 62.8%. Furthermore, the vast majority of the models tested were unable to reach a 60% accuracy level, which is typically considered a passing grade. This release sets a more rigorous standard for the industry, emphasizing the need for continued advancement in logical processing and providing a transparent look at the current limitations of top-tier AI systems.
