Llama 2 13B Dolphin 5w: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1349 ± 15, rank #7734 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Anatomy | 53.33 | Accuracy (%) | 88.9 |
| MMLU-by-task - Jurisprudence | 75 | Accuracy (%) | 87.6 |
| MMLU-by-task - Clinical Knowledge | 62.64 | Accuracy (%) | 87.4 |
| MMLU-by-task - High School Chemistry | 45.81 | Accuracy (%) | 87.2 |
| MMLU-by-task - Human Aging | 67.71 | Accuracy (%) | 87.2 |
| MMLU-by-task - Moral Disputes | 66.18 | Accuracy (%) | 87.1 |
| MMLU-by-task - US Foreign Policy | 84 | Accuracy (%) | 86.5 |
| MMLU-by-task - College Computer Science | 49 | Accuracy (%) | 86.2 |
| MMLU-by-task - Computer Security | 71 | Accuracy (%) | 86.2 |
| MMLU-by-task - High School Statistics | 47.69 | Accuracy (%) | 86 |
| MMLU-by-task - Electrical Engineering | 53.1 | Accuracy (%) | 85.4 |
| MMLU-by-task - Management | 75.73 | Accuracy (%) | 84.7 |
Interactive version: theaggregate.ai/model?slug=llama-2-13b-dolphin-5w · How It Works · Data refreshed daily, snapshot 2026-11-08.