Qwen2 72B Instruct — Benchmarks

Benchmark scores for Qwen2 72B Instruct aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #39 of 73 open modelscomposite 42.9/100 across 4 benchmarks in 3 categories · methodology

Knowledge

BenchmarkScoreOpen rankAll models
MMLU-Pro64.4%#44 / 119#121 / 259
MMLU82.4%#8 / 76#19 / 136

Math

BenchmarkScoreOpen rankAll models
MATH Level 539.1%#18 / 32#75 / 108

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond40.8%#31 / 46#145 / 182

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