Meta Llama 3 8B Instruct — Benchmarks

Benchmark scores for Meta Llama 3 8B Instruct aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #72 of 73 open modelscomposite 17.1/100 across 5 benchmarks in 3 categories · methodology

Knowledge

BenchmarkScoreOpen rankAll models
MMLU-Pro41.0%#81 / 119#197 / 259
MMLU68.8%#27 / 76#66 / 136

Math

BenchmarkScoreOpen rankAll models
AIME 2024/20250.8%#32 / 34#152 / 155
MATH Level 56.1%#29 / 32#104 / 108

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond26.1%#42 / 46#176 / 182

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