Llama 3 13B Instruct (Publisher: Andrijdavid): benchmark results
Provider: Meta.
Aggregate Rating 1343 ± 38, rank #7902 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 50.07 | MC2 (%) (0-shot) | 47 |
| Open LLM Leaderboard v1 - MMLU | 59.08 | Accuracy (%) (5-shot) | 44.6 |
| Open LLM Leaderboard v1 - GSM8K | 13.34 | Accuracy (%) (5-shot) | 35.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 53.16 | Normalized accuracy (%) (25-shot) | 28.8 |
| Open LLM Leaderboard v1 - WinoGrande | 68.9 | Accuracy (%) (5-shot) | 23 |
| Open LLM Leaderboard v1 - HellaSwag | 69.07 | Normalized accuracy (%) (10-shot) | 19.8 |
Interactive version: theaggregate.ai/model?slug=llama-3-13b-instruct-publisher-andrijdavid · How It Works · Data refreshed daily, snapshot 2026-11-08.