Llama 2 70B Ensemble V6: benchmark results
Provider: Meta.
Aggregate Rating 1420 ± 20, rank #5187 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Machine Learning | 58.04 | Accuracy (%) | 99.2 |
| MMLU-by-task - Moral Scenarios | 64.25 | Accuracy (%) | 99.2 |
| MMLU-by-task - Professional Accounting | 57.45 | Accuracy (%) | 99 |
| MMLU-by-task - ARC Challenge | 67.75 | Accuracy (%) | 98.8 |
| MMLU-by-task - Professional Law | 56.71 | Accuracy (%) | 98.7 |
| MMLU-by-task - TruthfulQA MC2 | 62.43 | Accuracy (%) | 98.5 |
| MMLU-by-task - Formal Logic | 50 | Accuracy (%) | 98.4 |
| MMLU-by-task - Management | 83.5 | Accuracy (%) | 98.3 |
| MMLU-by-task - High School US History | 91.67 | Accuracy (%) | 98.2 |
| MMLU-by-task - Elementary Mathematics | 46.03 | Accuracy (%) | 97.9 |
| MMLU-by-task - TruthfulQA MC1 | 43.82 | Accuracy (%) | 97.8 |
| MMLU-by-task - High School World History | 88.61 | Accuracy (%) | 97.2 |
Interactive version: theaggregate.ai/model?slug=llama-2-70b-ensemble-v6 · How It Works · Data refreshed daily, snapshot 2026-11-08.