Llama 7B — Benchmarks

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

Overall rank: #62 of 73 open modelscomposite 28.6/100 across 4 benchmarks in 3 categories · methodology

Knowledge

Benchmark	Score	Open rank	All models
HellaSwag	76.2%	#23 / 42	#43 / 76
MMLU	35.6%	#71 / 76	#126 / 136

Math

Benchmark	Score	Open rank	All models
GSM8K	11.0%	#55 / 59	#79 / 93

Reasoning

Benchmark	Score	Open rank	All models
BIG-Bench Hard	33.5%	#34 / 37	#47 / 50

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