GLM 5 — Benchmarks

Benchmark scores for GLM 5 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #12 of 73 open modelscomposite 63.6/100 across 8 benchmarks in 4 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
Terminal-Bench52.4%#1 / 16#22 / 57
SWE-bench Multilingual69.7%#1 / 4#4 / 14

Knowledge

BenchmarkScoreOpen rankAll models
MMLU-Pro86.0%#5 / 119#30 / 259

Math

BenchmarkScoreOpen rankAll models
AIME 2024/202580.0%#10 / 34#57 / 155
FrontierMath16.4%#6 / 12#48 / 101

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond87.8%#4 / 46#31 / 182
ARC-AGI44.7%#4 / 10#79 / 158
SimpleBench53.2%#4 / 19#39 / 90

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