HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks
Home/Orgs/meta-llama/meta-llama/Llama-3.1-405B

meta-llama/Llama-3.1-405B

family llama · 2 variants · unknown

provider
meta-llama
released
—
huggingface
https://huggingface.co/meta-llama/Llama-3.1-405B
best scores
MMLU: 84.4PopQA: 55.7TruthfulQA: 46.8BBH: 88.0DROP: 61.3MATH: 63.4GSM8K: 76.2HumanEval: 86.2IFEval: 72.8AlpacaEval: 12.4

Best scores per benchmark

benchmarkcategorybest score
BBHreasoning88.0
HumanEvalcoding86.2
MMLUknowledge84.4
GSM8Kmath76.2
IFEvalinstruction-following72.8
MATHmath63.4
DROPreasoning61.3
PopQAknowledge55.7
TruthfulQAsafety46.8
AlpacaEvalchat12.4

Variants (2)

variantkindquantbitsvRAMdlorgyear
Llama-3.1-405Boriginalbf1616.0109,868meta-llama2024
Llama-3.1-Tulu-3-405B-SFToriginalbf1616.095allenai2025
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.