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.

Knowledge

BenchmarkScoreRank
MMLU66.5%#16 / 36

Math

BenchmarkScoreRank
AIME 2024/20250.8%#20 / 22
MATH Level 56.1%#21 / 23

Reasoning

BenchmarkScoreRank
GPQA Diamond26.1%#25 / 28

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