Llama 3 8B Instruct (Publisher: Meta Llama): benchmark results
Provider: Meta.
Aggregate Rating 1418 ± 36, rank #5284 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 67.07 | Accuracy (%) (5-shot) | 88.8 |
| Open LLM Leaderboard v1 - GSM8K | 68.69 | Accuracy (%) (5-shot) | 86.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 51.65 | MC2 (%) (0-shot) | 52.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 60.75 | Normalized accuracy (%) (25-shot) | 49.3 |
| Open LLM Leaderboard v1 - WinoGrande | 74.51 | Accuracy (%) (5-shot) | 37 |
| Open LLM Leaderboard v1 - HellaSwag | 78.55 | Normalized accuracy (%) (10-shot) | 34.3 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-instruct-publisher-meta-llama · How It Works · Data refreshed daily, snapshot 2026-11-08.