Llama 2 13B Sharegpt4: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1342 ± 15, rank #7922 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - HellaSwag | 65.78 | Accuracy (%) | 90.7 |
| MMLU-by-task - College Computer Science | 49 | Accuracy (%) | 86.2 |
| MMLU-by-task - ARC Challenge | 58.79 | Accuracy (%) | 85.4 |
| MMLU-by-task - Moral Scenarios | 42.91 | Accuracy (%) | 85.4 |
| MMLU-by-task - College Mathematics | 37 | Accuracy (%) | 85.2 |
| MMLU-by-task - Human Sexuality | 66.41 | Accuracy (%) | 84.7 |
| MMLU-by-task - High School Biology | 68.06 | Accuracy (%) | 84.5 |
| MMLU-by-task - College Biology | 62.5 | Accuracy (%) | 84 |
| MMLU-by-task - Virology | 48.19 | Accuracy (%) | 83.9 |
| MMLU-by-task - High School Microeconomics | 58.82 | Accuracy (%) | 83.1 |
| MMLU-by-task - World Religions | 78.36 | Accuracy (%) | 83.1 |
| MMLU-by-task - Prehistory | 65.43 | Accuracy (%) | 82.5 |
Interactive version: theaggregate.ai/model?slug=llama-2-13b-sharegpt4 · How It Works · Data refreshed daily, snapshot 2026-11-08.