Z.AI · LIVEBENCH 2026-06-25

GLM-5.3 Flash

Published benchmark results for this specific model configuration.

glm-5.3-flash

Overall score71.6 / 100

Cost / successful task$0.031USD · benchmark workload

Weight accessOpen weights

Where this configuration performs

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

Reasoning77.6

Coding79.0

Agentic Coding56.8

Mathematics81.2

Data Analysis76.4

Language77.3

Instruction Following52.8

Task-level results

theory of mind73.1zebra puzzle79.5spatial96.0logic with navigation62.0code generation77.5code completion80.4javascript63.6typescript46.7python60.0AMPS Hard97.0integrals with game45.0math comp93.1olympiad89.8consecutive events84.3tablejoin48.8tablereformat96.1connections93.7plot unscrambling60.3typos78.0paraphrase48.0simplify47.0story generation59.9summarize56.5

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