Z.ai: GLM 5.2
1M ctxtextOpen weight753B params$1.40/M in · $4.40/M out
HLE 31 · CritPt 4.6 · DeepSWE 18 · NL2Repo 42.7 · AIME 2026 95.3 · GPQA-Diamond 86.2 · ProgramBench 50.9 · SWE-Marathon 1 · SWE-bench Pro 58.4 · IMOAnswerBench 83.8 · PostTrainBench 20.1 · Tool-Decathlon 40.7
GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks. With a truly usable 1M-token context window, it can handle project-level engineering context, execute long-running tasks more reliably, follow...