Llama 3 12B: benchmark results
Provider: Meta.
Aggregate Rating 1384 ± 32, rank #6736 of 10916 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 66.47 | Accuracy (%) (5-shot) | 87.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 51.48 | MC2 (%) (0-shot) | 52 |
| Open LLM Leaderboard v1 - GSM8K | 33.06 | Accuracy (%) (5-shot) | 49.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 57.51 | Normalized accuracy (%) (25-shot) | 37.7 |
| Open LLM Leaderboard v1 - WinoGrande | 74.51 | Accuracy (%) (5-shot) | 37 |
| Open LLM Leaderboard v1 - HellaSwag | 75.87 | Normalized accuracy (%) (10-shot) | 27.5 |
| YALL Nous Leaderboard | 44.35 | Average | 8.2 |
Interactive version: theaggregate.ai/model?slug=llama-3-12b · How It Works · Data refreshed daily, snapshot 2026-11-08.