Qwen 14B — Benchmarks

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

Overall rank: #21 of 73 open modelscomposite 56.6/100 across 3 benchmarks in 3 categories · methodology

Knowledge

BenchmarkScoreOpen rankAll models
MMLU66.3%#33 / 76#76 / 136

Math

BenchmarkScoreOpen rankAll models
GSM8K61.3%#23 / 59#32 / 93

Reasoning

BenchmarkScoreOpen rankAll models
BIG-Bench Hard53.4%#17 / 37#24 / 50

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