Llama 2 7B Base Guanaco 1k: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1294 ± 14, rank #8829 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Econometrics | 34.21 | Accuracy (%) | 82.6 |
| MMLU-by-task - Conceptual Physics | 43.83 | Accuracy (%) | 71.7 |
| MMLU-by-task - College Mathematics | 34 | Accuracy (%) | 69.2 |
| MMLU-by-task - High School Mathematics | 28.52 | Accuracy (%) | 64.7 |
| MMLU-by-task - Global Facts | 35 | Accuracy (%) | 64.2 |
| MMLU-by-task - High School Government And Politics | 73.06 | Accuracy (%) | 63.2 |
| MMLU-by-task - Elementary Mathematics | 31.22 | Accuracy (%) | 62.7 |
| MMLU-by-task - World Religions | 71.93 | Accuracy (%) | 62.5 |
| MMLU-by-task - Human Sexuality | 58.78 | Accuracy (%) | 62.2 |
| MMLU-by-task - Clinical Knowledge | 54.34 | Accuracy (%) | 62 |
| MMLU-by-task - College Biology | 52.08 | Accuracy (%) | 61 |
| MMLU-by-task - International Law | 66.12 | Accuracy (%) | 60.4 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-base-guanaco-1k · How It Works · Data refreshed daily, snapshot 2026-11-08.