Llama 3 8B [float16] [rev: B6887ce03ea4]: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1414 ± 34, rank #5463 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 66.7 | Accuracy (%) (5-shot) | 88 |
| Open LLM Leaderboard v1 - WinoGrande | 78.45 | Accuracy (%) (5-shot) | 63.3 |
| Open LLM Leaderboard v1 - GSM8K | 45.19 | Accuracy (%) (5-shot) | 59.3 |
| Open LLM Leaderboard v1 - HellaSwag | 82.23 | Normalized accuracy (%) (10-shot) | 49.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 60.24 | Normalized accuracy (%) (25-shot) | 46.8 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 42.93 | MC2 (%) (0-shot) | 22 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-float16-rev-b6887ce03ea4 · How It Works · Data refreshed daily, snapshot 2026-11-08.