Qwen 7B — Benchmarks

Benchmark scores for Qwen 7B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #44 of 73 open modelscomposite 41.1/100 across 3 benchmarks in 3 categories · methodology

Knowledge

BenchmarkScoreOpen rankAll models
MMLU45.0%#62 / 76#114 / 136

Math

BenchmarkScoreOpen rankAll models
GSM8K51.7%#31 / 59#44 / 93

Reasoning

BenchmarkScoreOpen rankAll models
BIG-Bench Hard45.0%#23 / 37#31 / 50

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