Qwen3 32B — Benchmarks

Benchmark scores for Qwen3 32B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #70 of 123 open modelscomposite 44/100 across 5 benchmarks in 3 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
Aider Polyglot40.0%#11 / 18#46 / 69
SciCode35.4%#35 / 50#130 / 155

Math

BenchmarkScoreOpen rankAll models
AIME 2024/202566.9%#27 / 74#134 / 270

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond65.7%#33 / 83#178 / 291
CritPt0.3%#33 / 50#127 / 167

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

Qwen3 32B Benchmarks — Scores & Rankings | llmrun