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: #69 of 123 open modelscomposite 44/100 across 8 benchmarks in 4 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
SciCode43.8%#19 / 50#90 / 155

Knowledge

BenchmarkScoreOpen rankAll models
SimpleQA34.0%#11 / 15#47 / 78

Math

BenchmarkScoreOpen rankAll models
AIME 2024/202593.3%#8 / 74#47 / 270
FrontierMath33.5%#2 / 12#21 / 101
ProofBench22.2%#6 / 21#32 / 64

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond89.9%#10 / 83#39 / 291
SimpleBench55.1%#5 / 23#42 / 101
CritPt4.6%#14 / 50#83 / 167

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