Meta Llama 3 70B — Benchmarks

Benchmark scores for Meta Llama 3 70B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Knowledge

BenchmarkScoreOpen rankAll models
MMLU-Pro52.8%#60 / 119#161 / 259

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