Llama 2 13B Beluga QLoRA: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1350 ± 15, rank #7697 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Physics | 39.22 | Accuracy (%) | 96.7 |
| MMLU-by-task - College Chemistry | 49 | Accuracy (%) | 95.8 |
| MMLU-by-task - High School Chemistry | 48.77 | Accuracy (%) | 92.1 |
| MMLU-by-task - High School Statistics | 52.78 | Accuracy (%) | 91.8 |
| MMLU-by-task - International Law | 78.51 | Accuracy (%) | 89.5 |
| MMLU-by-task - High School Microeconomics | 63.87 | Accuracy (%) | 89.4 |
| MMLU-by-task - Logical Fallacies | 71.17 | Accuracy (%) | 88 |
| MMLU-by-task - Philosophy | 67.52 | Accuracy (%) | 87.4 |
| MMLU-by-task - Miscellaneous | 77.78 | Accuracy (%) | 87 |
| MMLU-by-task - Moral Disputes | 65.9 | Accuracy (%) | 86.6 |
| MMLU-by-task - Moral Scenarios | 42.79 | Accuracy (%) | 85.2 |
| MMLU-by-task - Human Sexuality | 66.41 | Accuracy (%) | 84.7 |
Interactive version: theaggregate.ai/model?slug=llama-2-13b-beluga-qlora · How It Works · Data refreshed daily, snapshot 2026-11-08.