We also introduce an agentic streaming inference framework that supports thousand-second-scale generation while mitigating drift.

GLM-5.2 is the highest-ranked open-source model, showing that its 1M context has translated into practical long-horizon delivery capability.

The model kept finding better approaches the longer it ran, which connects directly to the long horizon behavior that makes agentic models actually useful in production.

GLM-5.1 did not plateau after 50 or 100 submissions, but continued to find meaningful improvements over 600+ iterations with 6,000+ tool calls, ultimately reaching 21.5k QPS—roughly 6× the best result achieved in a single 50-turn session.