GLM 4.7 — Benchmarks

Benchmark scores for GLM 4.7 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #87 of 123 open modelscomposite 36.1/100 across 9 benchmarks in 4 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
Terminal-Bench33.4%#8 / 16#40 / 57
SciCode45.1%#16 / 50#85 / 155

Knowledge

BenchmarkScoreOpen rankAll models
SimpleQA32.2%#13 / 15#55 / 78

Math

BenchmarkScoreOpen rankAll models
AIME 2024/202583.3%#19 / 74#91 / 270
FrontierMath2.4%#9 / 12#82 / 101
ProofBench6.0%#16 / 21#56 / 64

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond83.3%#20 / 83#94 / 291
SimpleBench47.7%#9 / 23#54 / 101
CritPt1.7%#22 / 50#100 / 167

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