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.

Coding

BenchmarkScoreRank
SWE-bench Verified74.2%#1 / 2

Knowledge

BenchmarkScoreRank
SimpleQA37.3%#2 / 4

Math

BenchmarkScoreRank
AIME 2024/202592.2%#1 / 22
FrontierMath33.5%#1 / 3

Reasoning

BenchmarkScoreRank
GPQA Diamond85.5%#2 / 28
SimpleBench58.7%#1 / 10

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