llama-base-7B: benchmark results
Provider: Meta.
Aggregate Rating 1214 ± 15, rank #9524 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Mathematics | 34 | Accuracy (%) | 69.2 |
| MMLU-by-task - HellaSwag | 57.55 | Accuracy (%) | 44.8 |
| MMLU-by-task - ARC Challenge | 47.7 | Accuracy (%) | 44.1 |
| MMLU-by-task - Conceptual Physics | 37.45 | Accuracy (%) | 43.3 |
| MMLU-by-task - Logical Fallacies | 42.94 | Accuracy (%) | 42.4 |
| MMLU-by-task - College Physics | 23.53 | Accuracy (%) | 41.6 |
| MMLU-by-task - Professional Medicine | 44.12 | Accuracy (%) | 41 |
| MMLU-by-task - College Biology | 38.19 | Accuracy (%) | 40.7 |
| MMLU-by-task - High School Psychology | 48.44 | Accuracy (%) | 40.5 |
| MMLU-by-task - Sociology | 47.26 | Accuracy (%) | 40.3 |
| MMLU-by-task - Nutrition | 39.54 | Accuracy (%) | 39.8 |
| MMLU-by-task - International Law | 52.07 | Accuracy (%) | 39.6 |
Interactive version: theaggregate.ai/model?slug=llama-base-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.