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: #40 of 73 open modelscomposite 42.6/100 across 6 benchmarks in 4 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
Terminal-Bench33.4%#8 / 16#40 / 57

Knowledge

BenchmarkScoreOpen rankAll models
SimpleQA31.5%#8 / 11#46 / 65

Math

BenchmarkScoreOpen rankAll models
AIME 2024/202583.3%#8 / 34#52 / 155
FrontierMath2.4%#9 / 12#82 / 101

Reasoning

BenchmarkScoreOpen rankAll models
SimpleBench47.7%#6 / 19#45 / 90
GPQA Diamond83.3%#8 / 46#52 / 182

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

GLM 4.7 Benchmarks — Scores & Rankings | llmrun