Llama 2 7B Guanaco Dolphin 500: benchmark results
Provider: Meta.
Aggregate Rating 1324 ± 35, rank #8268 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 81.62 | Normalized accuracy (%) (10-shot) | 46 |
| Open LLM Leaderboard v1 - ARC Challenge | 56.74 | Normalized accuracy (%) (25-shot) | 36 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.93 | MC2 (%) (0-shot) | 35.9 |
| Open LLM Leaderboard v1 - WinoGrande | 74.11 | Accuracy (%) (5-shot) | 35 |
| Open LLM Leaderboard v1 - GSM8K | 12.74 | Accuracy (%) (5-shot) | 34.6 |
| Open LLM Leaderboard v1 - MMLU | 48.68 | Accuracy (%) (5-shot) | 27.9 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-guanaco-dolphin-500 · How It Works · Data refreshed daily, snapshot 2026-11-08.