Llama 3 8B Instruct Norefusal: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1412 ± 35, rank #5538 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 66.48 | Accuracy (%) (5-shot) | 87.4 |
| Open LLM Leaderboard v1 - GSM8K | 59.82 | Accuracy (%) (5-shot) | 71.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 51.47 | MC2 (%) (0-shot) | 52 |
| Open LLM Leaderboard v1 - ARC Challenge | 60.58 | Normalized accuracy (%) (25-shot) | 48.4 |
| Open LLM Leaderboard v1 - WinoGrande | 74.43 | Accuracy (%) (5-shot) | 36.5 |
| Open LLM Leaderboard v1 - HellaSwag | 78.18 | Normalized accuracy (%) (10-shot) | 33.1 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-instruct-norefusal · How It Works · Data refreshed daily, snapshot 2026-11-08.