Llama 2. 7B Merge Orcafamily: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1343 ± 34, rank #7900 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 49.68 | MC2 (%) (0-shot) | 45.7 |
| Open LLM Leaderboard v1 - WinoGrande | 75.93 | Accuracy (%) (5-shot) | 44.9 |
| Open LLM Leaderboard v1 - HellaSwag | 81.17 | Normalized accuracy (%) (10-shot) | 43.8 |
| Open LLM Leaderboard v1 - GSM8K | 23.12 | Accuracy (%) (5-shot) | 42.8 |
| Open LLM Leaderboard v1 - ARC Challenge | 56.91 | Normalized accuracy (%) (25-shot) | 36.3 |
| Open LLM Leaderboard v1 - MMLU | 51.49 | Accuracy (%) (5-shot) | 30.7 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-merge-orcafamily · How It Works · Data refreshed daily, snapshot 2026-11-08.