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.

Coding

BenchmarkScoreRank
Terminal-Bench33.3%#5 / 11

Knowledge

BenchmarkScoreRank
SimpleQA31.5%#3 / 4

Math

BenchmarkScoreRank
AIME 2024/202583.3%#3 / 22

Reasoning

BenchmarkScoreRank
GPQA Diamond83.3%#3 / 28
SimpleBench47.7%#3 / 10

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