Qwen3 8B — Benchmarks

Benchmark scores for Qwen3 8B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #95 of 123 open modelscomposite 33.3/100 across 4 benchmarks in 3 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
SciCode22.6%#45 / 50#150 / 155

Math

BenchmarkScoreOpen rankAll models
AIME 2024/202556.1%#36 / 74#159 / 270

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond56.8%#40 / 83#197 / 291
CritPt0.0%#48 / 50#164 / 167

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