Z.AI · LIVEBENCH 2026-06-25

GLM-5.2

Published benchmark results for this specific model configuration.

glm-5.2

Overall score73.2 / 100

Cost / successful task$0.225USD · benchmark workload

Weight accessOpen weights

Where this configuration performs

Category averages from the same release, on a 0–100 scale.

Reasoning78.6

Coding79.7

Agentic Coding51.8

Mathematics89.8

Data Analysis73.7

Language76.2

Instruction Following62.3

Task-level results

theory of mind75.0zebra puzzle65.5spatial94.0logic with navigation80.0code generation78.9code completion80.4javascript63.6typescript36.7python55.0AMPS Hard98.0integrals with game76.0math comp96.1olympiad89.0consecutive events79.3tablejoin45.9tablereformat96.1connections94.0plot unscrambling60.7typos74.0paraphrase62.3simplify55.7story generation62.9summarize68.4

Source files: Scores ↗ Categories ↗ Costs ↗ . Missing cost is unknown, never free. Compare configurations within the same release.