llama-13B-pretrained-dropout: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1293 ± 16, rank #8841 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Mathematics | 38 | Accuracy (%) | 89.5 |
| MMLU-by-task - Machine Learning | 41.96 | Accuracy (%) | 84.6 |
| MMLU-by-task - Econometrics | 33.33 | Accuracy (%) | 80.1 |
| MMLU-by-task - TruthfulQA MC1 | 34.39 | Accuracy (%) | 77.3 |
| MMLU-by-task - Global Facts | 36 | Accuracy (%) | 70 |
| MMLU-by-task - TruthfulQA MC2 | 48.6 | Accuracy (%) | 68.4 |
| MMLU-by-task - ARC Challenge | 54.44 | Accuracy (%) | 66.6 |
| MMLU-by-task - Anatomy | 48.15 | Accuracy (%) | 66.5 |
| MMLU-by-task - Elementary Mathematics | 31.75 | Accuracy (%) | 65.7 |
| MMLU-by-task - Moral Scenarios | 29.05 | Accuracy (%) | 64.9 |
| MMLU-by-task - International Law | 66.94 | Accuracy (%) | 61.9 |
| MMLU-by-task - US Foreign Policy | 75 | Accuracy (%) | 61.9 |
Interactive version: theaggregate.ai/model?slug=llama-13b-pretrained-dropout · How It Works · Data refreshed daily, snapshot 2026-11-08.