Llama 3.1 405B Instruct — Benchmarks

Benchmark scores for Llama 3.1 405B Instruct aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #44 of 75 open modelscomposite 46/100 across 5 benchmarks in 3 categories · methodology

Knowledge

BenchmarkScoreOpen rankAll models
MMLU84.5%#6 / 76#13 / 136

Math

BenchmarkScoreOpen rankAll models
AIME 2024/20259.7%#16 / 30#103 / 142
MATH Level 549.8%#14 / 32#64 / 108

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond50.9%#16 / 42#106 / 170
SimpleBench23.0%#14 / 17#65 / 76

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