Llama 3.1 8B Instruct (verifiable): benchmark results
Provider: Meta. Released 2024-07-23.
Aggregate Rating 1486 ± 28, rank #2571 of 10916 rated models, from 1 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Medmarks | 0.4 | Win Rate | 14.1 |
Interactive version: theaggregate.ai/model?slug=llama-3-1-8b-instruct-verifiable · How It Works · Data refreshed daily, snapshot 2026-11-08.