Llama 2 7B Base [4bit] [rev: 6fdf2e60f86f]: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1290 ± 37, rank #8863 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 74.59 | Accuracy (%) (5-shot) | 37.5 |
| Open LLM Leaderboard v1 - HellaSwag | 77.74 | Normalized accuracy (%) (10-shot) | 31.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 53.07 | Normalized accuracy (%) (25-shot) | 28.5 |
| Open LLM Leaderboard v1 - GSM8K | 5.38 | Accuracy (%) (5-shot) | 24 |
| Open LLM Leaderboard v1 - MMLU | 43.8 | Accuracy (%) (5-shot) | 22.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 38.98 | MC2 (%) (0-shot) | 9.7 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-base-4bit-rev-6fdf2e60f86f · How It Works · Data refreshed daily, snapshot 2026-11-08.