LLaMA-13B (Publisher: huggingface): benchmark results
Provider: Meta.
Aggregate Rating 1317 ± 37, rank #8397 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 76.24 | Accuracy (%) (5-shot) | 47 |
| Open LLM Leaderboard v1 - HellaSwag | 80.93 | Normalized accuracy (%) (10-shot) | 42.8 |
| Open LLM Leaderboard v1 - ARC Challenge | 56.23 | Normalized accuracy (%) (25-shot) | 35.1 |
| Open LLM Leaderboard v1 - GSM8K | 7.58 | Accuracy (%) (5-shot) | 27.1 |
| Open LLM Leaderboard v1 - MMLU | 47.67 | Accuracy (%) (5-shot) | 26.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 39.48 | MC2 (%) (0-shot) | 11.1 |
Interactive version: theaggregate.ai/model?slug=llama-13b-publisher-huggingface · How It Works · Data refreshed daily, snapshot 2026-11-08.