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
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open PL LLM - Generative | 72.51 | Average Generative Score (%) | 99.7 |
| Open PL LLM Leaderboard | 69.44 | Average Score (%) | 99.7 |
| EuroEval Swedish | 76.31 | Average Score (%) | 99.5 |
| Open PL LLM - Multiple Choice | 65.44 | Average Multiple-Choice Score (%) | 99.3 |
| EuroEval German | 66.56 | Average Score (%) | 99.1 |
| EuroEval Faroese NLU - FoQA | 79.74 | Reading comprehension Score (%) | 99 |
| EuroEval English NLU - SST-5 | 70.29 | Sentiment classification Score (%) | 98.8 |
| EuroEval English | 77.88 | Average Score (%) | 98.5 |
| EuroEval Swedish NLU | 75.35 | NLU Average Score (%) | 98.3 |
| EuroEval Norwegian NLU - Norec | 64.42 | Sentiment classification Score (%) | 98.2 |
| EuroEval German Common Sense Reasoning | 82.81 | Common Sense Reasoning Average Score (%) | 98.1 |
| EuroEval Spanish | 64.11 | Average 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.