Llama 3.1 Instruct Turbo 405B — benchmark results
Provider: Meta. Released 2024-07-23. Access: Open.
Unified ELO 1553 ± 63, rank #680 of 1839 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Safety BBQ | 94.5 | BBQ accuracy (%) | 57.6 |
| HELM Safety SimpleSafetyTests | 98.8 | LM Evaluated Safety score (%) | 51.2 |
| HELM Safety XSTest | 95.9 | LM Evaluated Safety score (%) | 51.2 |
| HELM Safety | 89.7 | Mean score (self-reported) | 37.3 |
| HELM AIR-Bench | 58.6 | Refusal Rate (%) | 33.7 |
| HELM Safety HarmBench | 62.7 | LM Evaluated Safety score (%) | 27.9 |
| HELM Safety Anthropic Red Team | 96.5 | LM Evaluated Safety score (%) | 16.9 |
Interactive version: theaggregate.ai/model?slug=llama-3-1-instruct-turbo-405b · How It Works · Data refreshed daily, snapshot 2026-08-05.