Llama 2 7B Base [float16] [rev: E8f058fa738B]: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1308 ± 34, rank #8590 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 14.48 | Accuracy (%) (5-shot) | 36.4 |
| Open LLM Leaderboard v1 - HellaSwag | 78.59 | Normalized accuracy (%) (10-shot) | 34.8 |
| Open LLM Leaderboard v1 - WinoGrande | 74.03 | Accuracy (%) (5-shot) | 34.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 53.07 | Normalized accuracy (%) (25-shot) | 28.5 |
| Open LLM Leaderboard v1 - MMLU | 46.87 | Accuracy (%) (5-shot) | 25.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 38.76 | MC2 (%) (0-shot) | 9.1 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-base-float16-rev-e8f058fa738b · How It Works · Data refreshed daily, snapshot 2026-11-08.