Llama 2 7B Instruct Peft [Adapter]: benchmark results
Provider: Meta.
Aggregate Rating 1302 ± 35, rank #8700 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 48.5 | MC2 (%) (0-shot) | 41.4 |
| Open LLM Leaderboard v1 - WinoGrande | 74.43 | Accuracy (%) (5-shot) | 36.5 |
| Open LLM Leaderboard v1 - HellaSwag | 78.92 | Normalized accuracy (%) (10-shot) | 36.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 51.19 | Normalized accuracy (%) (25-shot) | 25.6 |
| Open LLM Leaderboard v1 - MMLU | 46.63 | Accuracy (%) (5-shot) | 25.2 |
| Open LLM Leaderboard v1 - GSM8K | 5.99 | Accuracy (%) (5-shot) | 25 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-instruct-peft-adapter · How It Works · Data refreshed daily, snapshot 2026-11-08.