LLaMA-33B: benchmark results
Provider: Meta. Released 2023-02-24. Access: Open.
Aggregate Rating 1370 ± 13, rank #7184 of 10916 rated models, from 80 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Public Relations | 72.73 | Accuracy (%) | 95.9 |
| MMLU-by-task - HellaSwag | 68 | Accuracy (%) | 95.4 |
| MMLU-by-task - College Mathematics | 40 | Accuracy (%) | 95.3 |
| MMLU-by-task - Professional Law | 50.13 | Accuracy (%) | 92.7 |
| MMLU-by-task - ARC Challenge | 62.2 | Accuracy (%) | 91.7 |
| MMLU-by-task - US Foreign Policy | 86 | Accuracy (%) | 91.5 |
| MMLU-by-task - High School Government And Politics | 88.6 | Accuracy (%) | 91.4 |
| MMLU-by-task - Virology | 51.81 | Accuracy (%) | 91.4 |
| MMLU-by-task - International Law | 80.17 | Accuracy (%) | 91.2 |
| MMLU-by-task - World Religions | 81.87 | Accuracy (%) | 91.2 |
| MMLU-by-task - Human Sexuality | 72.52 | Accuracy (%) | 90.9 |
| MMLU-by-task - Security Studies | 71.84 | Accuracy (%) | 90.9 |
Interactive version: theaggregate.ai/model?slug=llama-33b · How It Works · Data refreshed daily, snapshot 2026-11-08.