Llama 2 7B HF — Benchmarks

Benchmark scores for Llama 2 7B HF aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #59 of 73 open modelscomposite 30.7/100 across 5 benchmarks in 3 categories · methodology

Knowledge

Benchmark	Score	Open rank	All models
HellaSwag	77.2%	#18 / 42	#37 / 76
MMLU-Pro	20.3%	#108 / 119	#244 / 259
MMLU	45.8%	#61 / 76	#113 / 136

Math

Benchmark	Score	Open rank	All models
GSM8K	16.7%	#53 / 59	#76 / 93

Reasoning

Benchmark	Score	Open rank	All models
BIG-Bench Hard	39.2%	#28 / 37	#38 / 50

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