🔥GLM-5.1 Tops the Chart LMArena Code Ranking Open Source First, Third Globally

According to 1M AI News monitoring, the global AI evaluation platform LMArena updates the Code Arena special ranking, with GLM-5.1 ranking first among open-source models worldwide and third among all models globally. This model inherits the previous generation's state-of-the-art open-source coding capabilities and achieves breakthroughs in long-term tasks: building a Linux desktop from scratch in 8 hours, breaking the vector database optimization bottleneck after 655 iterations, and optimizing real machine learning model loads with 1,000 rounds of tool invocation. Under the same standards as the METR leaderboard, GLM-5.1 is the only open-source model capable of sustained work at the 8-hour level, and is one of the few, aside from Claude Opus 4.6, with this ability…