Qwen3 14B — Benchmarks

Benchmark scores for Qwen3 14B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #76 of 123 open modelscomposite 41.3/100 across 4 benchmarks in 3 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
SciCode31.6%#40 / 50#137 / 155

Math

BenchmarkScoreOpen rankAll models
AIME 2024/202566.4%#29 / 74#138 / 270

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond63.8%#36 / 83#185 / 291
CritPt0.0%#46 / 50#162 / 167

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