On May 26, 2024, the highly anticipated global third-party programming capability benchmark, Code Arena, released its latest rankings. Alibaba's newest flagship large language model, Qwen3.7-Max, demonstrated remarkable performance in this evaluation, securing an impressive score of 1541.
This achievement places Qwen3.7-Max ahead of several prominent models, including GPT-5.5 and Gemini-3.5-Flash. According to the Code Arena leaderboard, Qwen3.7-Max now ranks second globally among major LLM providers, with its programming capabilities surpassed only by Anthropic's Claude series. This milestone highlights Alibaba Cloud's significant advancements in large language model programming and code generation.
