Llama 2 13B QLoRA: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1347 ± 15, rank #7790 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Moral Scenarios | 45.59 | Accuracy (%) | 90.2 |
| MMLU-by-task - Anatomy | 52.59 | Accuracy (%) | 87.3 |
| MMLU-by-task - College Medicine | 54.91 | Accuracy (%) | 86.5 |
| MMLU-by-task - Professional Law | 45.05 | Accuracy (%) | 86.4 |
| MMLU-by-task - Professional Accounting | 45.74 | Accuracy (%) | 86.3 |
| MMLU-by-task - High School US History | 79.41 | Accuracy (%) | 85.9 |
| MMLU-by-task - Prehistory | 66.36 | Accuracy (%) | 84.8 |
| MMLU-by-task - International Law | 75.21 | Accuracy (%) | 84.2 |
| MMLU-by-task - Medical Genetics | 63 | Accuracy (%) | 84.2 |
| MMLU-by-task - Miscellaneous | 76.88 | Accuracy (%) | 82.9 |
| MMLU-by-task - Logical Fallacies | 68.71 | Accuracy (%) | 82.6 |
| MMLU-by-task - Moral Disputes | 64.45 | Accuracy (%) | 82.3 |
Interactive version: theaggregate.ai/model?slug=llama-2-13b-qlora · How It Works · Data refreshed daily, snapshot 2026-11-08.