Qwen 14B Chat — Benchmarks

Benchmark scores for Qwen 14B Chat 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 73 open modelscomposite 56.5/100 across 3 benchmarks in 3 categories · methodology

Knowledge

BenchmarkScoreOpen rankAll models
MMLU65.0%#35 / 76#79 / 136

Math

BenchmarkScoreOpen rankAll models
GSM8K61.2%#24 / 59#33 / 93

Reasoning

BenchmarkScoreOpen rankAll models
BIG-Bench Hard55.0%#15 / 37#22 / 50

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