Llama 2 70B IA3 Guanaco: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1421 ± 17, rank #5137 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - International Law | 89.26 | Accuracy (%) | 99.9 |
| MMLU-by-task - US Foreign Policy | 93 | Accuracy (%) | 99.6 |
| MMLU-by-task - High School Mathematics | 35.56 | Accuracy (%) | 98.8 |
| MMLU-by-task - Virology | 55.42 | Accuracy (%) | 98.8 |
| MMLU-by-task - Jurisprudence | 83.33 | Accuracy (%) | 98.1 |
| MMLU-by-task - High School Geography | 87.88 | Accuracy (%) | 97.8 |
| MMLU-by-task - Medical Genetics | 72 | Accuracy (%) | 97.8 |
| MMLU-by-task - Public Relations | 73.64 | Accuracy (%) | 97.6 |
| MMLU-by-task - High School Biology | 81.94 | Accuracy (%) | 97.4 |
| MMLU-by-task - Nutrition | 75.49 | Accuracy (%) | 96.5 |
| MMLU-by-task - Astronomy | 80.26 | Accuracy (%) | 96.4 |
| MMLU-by-task - High School Chemistry | 53.2 | Accuracy (%) | 96.4 |
Interactive version: theaggregate.ai/model?slug=llama-2-70b-ia3-guanaco · How It Works · Data refreshed daily, snapshot 2026-11-08.