GLM 5.1 — Benchmarks

Benchmark scores for GLM 5.1 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #23 of 73 open modelscomposite 56/100 across 5 benchmarks in 3 categories · methodology

Knowledge

BenchmarkScoreOpen rankAll models
SimpleQA37.3%#5 / 11#39 / 65

Math

BenchmarkScoreOpen rankAll models
AIME 2024/202592.2%#4 / 34#27 / 155
FrontierMath33.5%#2 / 12#21 / 101

Reasoning

BenchmarkScoreOpen rankAll models
SimpleBench55.1%#3 / 19#35 / 90
GPQA Diamond85.5%#6 / 46#40 / 182

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