Zhi Tong Cai Jing·2025-09-24 03:05Core Insights - Alibaba Cloud Tongyi Qwen has launched its largest and most powerful model to date, Qwen3-Max, following the release of the Qwen3-2507 series [1] - The preview version of Qwen3-Max-Instruct ranks third on the LMArena text leaderboard, surpassing GPT-5-Chat [1] - The official version of Qwen3-Max has enhanced capabilities in coding and agent functions, achieving industry-leading performance across comprehensive benchmark tests in knowledge, reasoning, programming, instruction adherence, human preference alignment, agent tasks, and multilingual understanding [1] Model Specifications - Qwen3-Max features over 1 trillion parameters and was pre-trained using 36 trillion tokens [1] - The model architecture follows the design paradigm of the Qwen3 series and employs a global-batch load balancing loss proposed by Tongyi [1] Enhanced Version - The reasoning-enhanced version, Qwen3-Max-Thinking, has demonstrated exceptional potential, achieving 100% accuracy in high-difficulty reasoning benchmark tests such as AIME25 and HMMT [1]