Llama 3.1 405B Instruct: benchmark results
Meta Llama 3.1 405B instruction-tuned checkpoint. Provider: Meta. Released 2024-07-23. Access: Open.
Unified ELO 1558 ± 1, rank #406 of 1392 rated models, from 218 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM SeaHELM - XNLI (th) | 70 | EM | 100 |
| HELM ThaiExam - TPAT-1 | 68.1 | EM | 100 |
| HELM ThaiExam - A-Level | 66.93 | EM | 98.8 |
| BenCzechMark | 83.19 | Average Score (%) | 98.6 |
| HELM SeaHELM - IndicXNLI | 63.3 | EM | 97.5 |
| MERA - ruDetox | 38.13 | Joint Score (%) | 97.1 |
| MERA - RCB | 60.5 | Accuracy (%) | 96.2 |
| MixEval | 66.2 | Score | 96.1 |
| HELM ThaiExam - ThaiExam | 68.23 | EM | 95.1 |
| HELM SeaHELM - Flores (en-ta) | 50.9 | ChrF++ | 95 |
| HELM SeaHELM - IndicSentiment | 98.3 | Macro F1 score | 95 |
| HELM Lite | 88.91 | Mean win rate (self-reported) | 94.7 |
Interactive version: theaggregate.ai/model?slug=llama-3-1-405b-instruct · How It Works · Data refreshed daily, snapshot 2026-09-05.