Llama 2 7B Instruct: benchmark results
Provider: Meta. Released 2023-07-18.
Aggregate Rating 1282 ± 18, rank #8961 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Conceptual Physics | 43.4 | Accuracy (%) | 70 |
| MMLU-by-task - Philosophy | 60.45 | Accuracy (%) | 66.4 |
| MMLU-by-task - Machine Learning | 35.71 | Accuracy (%) | 64.2 |
| MMLU-by-task - Professional Medicine | 50.74 | Accuracy (%) | 62.7 |
| MMLU-by-task - World Religions | 71.93 | Accuracy (%) | 62.5 |
| MMLU-by-task - Electrical Engineering | 46.21 | Accuracy (%) | 58.8 |
| MMLU-by-task - Medical Genetics | 54 | Accuracy (%) | 58.3 |
| MMLU-by-task - College Medicine | 43.35 | Accuracy (%) | 58 |
| MMLU-by-task - High School European History | 63.03 | Accuracy (%) | 56.5 |
| MMLU-by-task - Computer Security | 61 | Accuracy (%) | 56.1 |
| MMLU-by-task - Business Ethics | 50 | Accuracy (%) | 55.9 |
| MMLU-by-task - High School Government And Politics | 68.39 | Accuracy (%) | 55.9 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.