llama-13B-4bit-alpaca: benchmark results
Provider: Meta.
Aggregate Rating 1266 ± 19, rank #9115 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 36 | Accuracy (%) | 91.7 |
| MMLU-by-task - HellaSwag | 62.18 | Accuracy (%) | 74.6 |
| MMLU-by-task - ARC Challenge | 53.5 | Accuracy (%) | 63.2 |
| MMLU-by-task - Sociology | 64.18 | Accuracy (%) | 56 |
| MMLU-by-task - US Foreign Policy | 70 | Accuracy (%) | 55.6 |
| MMLU-by-task - TruthfulQA MC1 | 29.38 | Accuracy (%) | 54.6 |
| MMLU-by-task - Machine Learning | 33.04 | Accuracy (%) | 53.4 |
| MMLU-by-task - College Biology | 47.22 | Accuracy (%) | 52.9 |
| MMLU-by-task - Public Relations | 54.55 | Accuracy (%) | 52.8 |
| MMLU-by-task - Astronomy | 44.74 | Accuracy (%) | 52.6 |
| MMLU-by-task - Management | 61.17 | Accuracy (%) | 52.1 |
| MMLU-by-task - Computer Security | 59 | Accuracy (%) | 51.1 |
Interactive version: theaggregate.ai/model?slug=llama-13b-4bit-alpaca · How It Works · Data refreshed daily, snapshot 2026-11-08.