Llama 3 12B Instruct: benchmark results
Provider: mlabonne. Access: Open.
Aggregate Rating 1407 ± 31, rank #5772 of 10916 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 66.72 | Accuracy (%) (5-shot) | 88 |
| Open LLM Leaderboard v1 - GSM8K | 52.46 | Accuracy (%) (5-shot) | 64.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 52.54 | MC2 (%) (0-shot) | 56.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 58.45 | Normalized accuracy (%) (25-shot) | 39.8 |
| Open LLM Leaderboard v1 - HellaSwag | 78.87 | Normalized accuracy (%) (10-shot) | 36.1 |
| YALL Nous Leaderboard | 50 | Average | 32.9 |
| Open LLM Leaderboard v1 - WinoGrande | 71.98 | Accuracy (%) (5-shot) | 27.8 |
Interactive version: theaggregate.ai/model?slug=llama-3-12b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.