On May 21, third-party model evaluation institution Artificial Analysis released its latest global LLM comprehensive leaderboard. Alibaba's flagship Qwen3.7-Max, with a score of 56.6, broke into the global top 5, while also ranking #1 among domestic models — its performance is now close to the strongest single-model level of GPT-5.5, Claude Opus 4.7, and Gemini 3.5 Ultra.