Qwen2.5 72B Instruct — Benchmarks

Benchmark scores for Qwen2.5 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: #57 of 123 open modelscomposite 49.4/100 across 4 benchmarks in 3 categories · methodology

Knowledge

BenchmarkScoreOpen rankAll models
MMLU85.3%#3 / 77#9 / 136

Math

BenchmarkScoreOpen rankAll models
AIME 2024/20258.1%#53 / 74#221 / 270
MATH Level 563.2%#11 / 32#52 / 108

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond49.1%#49 / 83#214 / 291

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