Llama 3 8B Instruct 262k [float16] [rev: 2aa64ee2c2e1]: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1383 ± 38, rank #6774 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 64.27 | Accuracy (%) (5-shot) | 67.4 |
| Open LLM Leaderboard v1 - GSM8K | 47.23 | Accuracy (%) (5-shot) | 60.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 48.37 | MC2 (%) (0-shot) | 40.9 |
| Open LLM Leaderboard v1 - WinoGrande | 73.01 | Accuracy (%) (5-shot) | 30.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 53.16 | Normalized accuracy (%) (25-shot) | 28.8 |
| Open LLM Leaderboard v1 - HellaSwag | 75.53 | Normalized accuracy (%) (10-shot) | 26.7 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-instruct-262k-float16-rev-2aa64ee2c2e1 · How It Works · Data refreshed daily, snapshot 2026-11-08.