Llama 2 70B Ensemble V5: benchmark results
Provider: Meta.
Aggregate Rating 1428 ± 20, rank #4777 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Geography | 90.4 | Accuracy (%) | 99.9 |
| MMLU-by-task - Elementary Mathematics | 47.88 | Accuracy (%) | 99.6 |
| MMLU-by-task - Security Studies | 81.22 | Accuracy (%) | 99.4 |
| MMLU-by-task - College Medicine | 68.21 | Accuracy (%) | 99.2 |
| MMLU-by-task - TruthfulQA MC1 | 45.9 | Accuracy (%) | 99.2 |
| MMLU-by-task - TruthfulQA MC2 | 63.45 | Accuracy (%) | 99.1 |
| MMLU-by-task - Logical Fallacies | 82.82 | Accuracy (%) | 99 |
| MMLU-by-task - Sociology | 89.55 | Accuracy (%) | 99 |
| MMLU-by-task - Abstract Algebra | 40 | Accuracy (%) | 98.9 |
| MMLU-by-task - ARC Challenge | 67.75 | Accuracy (%) | 98.8 |
| MMLU-by-task - Clinical Knowledge | 73.96 | Accuracy (%) | 98.7 |
| MMLU-by-task - Moral Scenarios | 60.67 | Accuracy (%) | 98.6 |
Interactive version: theaggregate.ai/model?slug=llama-2-70b-ensemble-v5 · How It Works · Data refreshed daily, snapshot 2026-11-08.