LLaMA-65B (Publisher: huggingface): benchmark results
Provider: Meta.
Aggregate Rating 1414 ± 35, rank #5470 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 82.56 | Accuracy (%) (5-shot) | 84.6 |
| Open LLM Leaderboard v1 - HellaSwag | 86.09 | Normalized accuracy (%) (10-shot) | 78.6 |
| Open LLM Leaderboard v1 - MMLU | 63.93 | Accuracy (%) (5-shot) | 64.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 63.48 | Normalized accuracy (%) (25-shot) | 62.9 |
| Open LLM Leaderboard v1 - GSM8K | 27.67 | Accuracy (%) (5-shot) | 45.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 43.43 | MC2 (%) (0-shot) | 23.4 |
Interactive version: theaggregate.ai/model?slug=llama-65b-publisher-huggingface · How It Works · Data refreshed daily, snapshot 2026-11-08.