Z AI just dropped the highest-scoring open-weight model on the Artificial Analysis Intelligence Index. GLM-5.2 landed a score of 51, edging past its predecessor GLM-5’s score of 50 and staking its claim as the benchmark leader in the open model category.
What GLM-5.2 actually brings to the table
GLM-5.2 features a 1 million token context window, a fivefold increase from GLM-5.1’s 200K token limit. Z AI has optimized this release specifically for coding and long-term agentic tasks. The model includes dual thinking-effort levels designed to enhance its coding capabilities, essentially giving developers a toggle between speed and depth depending on the complexity of the problem.
The company is positioning GLM-5.2 as the top performer on benchmarks like FrontierSWE and PostTrainBench, both of which test real-world software engineering and post-training task completion.
The pace is the story
