HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Home/Orgs/meta-llama/meta-llama/Llama-2-70b

meta-llama/Llama-2-70b

family llama · 1 variants · unknown

provider: meta-llama
released: —
huggingface: https://huggingface.co/meta-llama/Llama-2-70b
best scores: MATH: 6.95MMLU: 35.1BBH: 30.3AGIEval: 23.9

Best scores per benchmark

benchmark	category	best score
MMLU	knowledge	35.1
BBH	reasoning	30.3
AGIEval	reasoning	23.9
MATH	math	6.95

Variants (1)

variant	kind	quant	bits	vRAM	dl	org	year
Llama-2-70b	original	bf16	16.0		14	meta-llama	2024

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.