GLM 5.3 Flash — Benchmarks

Benchmark scores for GLM 5.3 Flash aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #22 of 123 open modelscomposite 62.6/100 across 8 benchmarks in 3 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
SciCode46.1%#14 / 50#80 / 155
LiveBench Coding79.0#4 / 16#19 / 54

Math

BenchmarkScoreOpen rankAll models
AIME 2024/202593.9%#7 / 74#42 / 270
LiveBench Math81.2#12 / 16#46 / 54
ProofBench21.0%#8 / 21#35 / 64

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond90.1%#9 / 83#36 / 291
LiveBench Reasoning77.6#12 / 16#44 / 54
CritPt15.4%#6 / 50#51 / 167

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