Alibaba's Qwen3.7-Max ranks 4th globally in coding, 2nd among LLM vendors

The global coding leaderboard Code Arena updated. Alibaba's flagship model Qwen3.7-Max scored 1541 points, ranking 4th worldwide and 2nd among all LLM companies, just behind the Claude series.

The platform tests real coding skills like debugging and refactoring, using random user blind tests to prevent cheating. Qwen3.7-Max outperformed models like Claude Opus 4-6, GLM-5.1, and Kimi K2.6.

On the Design Arena, another blind-test platform known as the "Olympics of AI," Qwen3.7-Max also made the top 10.