Qwen2.5 7B Instruct — Benchmarks

Benchmark scores for Qwen2.5 7B Instruct aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #106 of 123 open modelscomposite 26.8/100 across 3 benchmarks in 3 categories · methodology

Knowledge

BenchmarkScoreOpen rankAll models
MMLU72.9%#22 / 77#53 / 136

Math

BenchmarkScoreOpen rankAll models
AIME 2024/20252.5%#65 / 74#252 / 270

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond35.5%#65 / 83#256 / 291

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

Qwen2.5 7B Instruct Benchmarks — Scores & Rankings | llmrun