Llama 3.1 405B Instruct FP8 — benchmark results

Llama 3.1 405B Instruct evaluated in FP8 quantization. Provider: Meta. Released 2024-07-23. Access: Open.

Unified ELO 1615 ± 11, rank #443 of 1776 rated models, from 117 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open PL LLM - Generative72.51Average Generative Score (%)99.7
Open PL LLM Leaderboard69.44Average Score (%)99.7
EuroEval Swedish76.31Average Score (%)99.5
Open PL LLM - Multiple Choice65.44Average Multiple-Choice Score (%)99.3
EuroEval German66.56Average Score (%)99.1
EuroEval Faroese NLU - FoQA79.74Reading comprehension Score (%)99
EuroEval English NLU - SST-570.29Sentiment classification Score (%)98.8
EuroEval English77.88Average Score (%)98.5
EuroEval Swedish NLU75.35NLU Average Score (%)98.3
EuroEval Norwegian NLU - Norec64.42Sentiment classification Score (%)98.2
EuroEval German Common Sense Reasoning82.81Common Sense Reasoning Average Score (%)98.1
EuroEval Spanish64.11Average Score (%)98.1

Interactive version: theaggregate.ai/model?slug=llama-3-1-405b-instruct-fp8 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.