Llama 2 70B Dolphin Peft: benchmark results
Provider: Meta.
Aggregate Rating 1429 ± 19, rank #4726 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Geography | 89.9 | Accuracy (%) | 99.6 |
| MMLU-by-task - High School Physics | 49.67 | Accuracy (%) | 99.6 |
| MMLU-by-task - International Law | 88.43 | Accuracy (%) | 99.5 |
| MMLU-by-task - Jurisprudence | 84.26 | Accuracy (%) | 99.4 |
| MMLU-by-task - Computer Security | 79 | Accuracy (%) | 99.1 |
| MMLU-by-task - Astronomy | 82.24 | Accuracy (%) | 98.4 |
| MMLU-by-task - Anatomy | 63.7 | Accuracy (%) | 97.8 |
| MMLU-by-task - Marketing | 90.6 | Accuracy (%) | 97.8 |
| MMLU-by-task - Medical Genetics | 72 | Accuracy (%) | 97.8 |
| MMLU-by-task - Virology | 54.82 | Accuracy (%) | 97.8 |
| MMLU-by-task - Security Studies | 79.59 | Accuracy (%) | 97.4 |
| MMLU-by-task - US Foreign Policy | 91 | Accuracy (%) | 97.4 |
Interactive version: theaggregate.ai/model?slug=llama-2-70b-dolphin-peft · How It Works · Data refreshed daily, snapshot 2026-11-08.