Llama 3 8B Ultra Instruct [float16] [rev: 86da0c95da55]: benchmark results
Provider: Meta.
Aggregate Rating 1436 ± 34, rank #4371 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 70.36 | Accuracy (%) (5-shot) | 92.7 |
| Open LLM Leaderboard v1 - MMLU | 68.32 | Accuracy (%) (5-shot) | 91.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 64.59 | Normalized accuracy (%) (25-shot) | 67.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 52.8 | MC2 (%) (0-shot) | 57.4 |
| Open LLM Leaderboard v1 - WinoGrande | 76.95 | Accuracy (%) (5-shot) | 52 |
| Open LLM Leaderboard v1 - HellaSwag | 81.63 | Normalized accuracy (%) (10-shot) | 46.1 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-ultra-instruct-float16-rev-86da0c95da55 · How It Works · Data refreshed daily, snapshot 2026-11-08.