GLM 5.2 — Benchmarks

Benchmark scores for GLM 5.2 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #1 of 73 open modelscomposite 82.7/100 across 3 benchmarks in 3 categories · methodology

Coding

Benchmark	Score	Open rank	All models
LiveBench Coding	79.7	#1 / 8	#12 / 37

Math

Benchmark	Score	Open rank	All models
LiveBench Math	89.8	#2 / 8	#17 / 37

Reasoning

Benchmark	Score	Open rank	All models
LiveBench Reasoning	78.6	#4 / 8	#28 / 37

Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.