Llama 2 70B Ensemble V2: benchmark results
Provider: Meta.
Aggregate Rating 1417 ± 20, rank #5325 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Clinical Knowledge | 77.74 | Accuracy (%) | 100 |
| MMLU-by-task - TruthfulQA MC1 | 46.63 | Accuracy (%) | 99.6 |
| MMLU-by-task - TruthfulQA MC2 | 64.51 | Accuracy (%) | 99.5 |
| MMLU-by-task - College Mathematics | 42 | Accuracy (%) | 98.4 |
| MMLU-by-task - Econometrics | 45.61 | Accuracy (%) | 97.8 |
| MMLU-by-task - High School European History | 84.24 | Accuracy (%) | 97.5 |
| MMLU-by-task - Logical Fallacies | 81.6 | Accuracy (%) | 97.2 |
| MMLU-by-task - Business Ethics | 74 | Accuracy (%) | 96.7 |
| MMLU-by-task - College Physics | 39.22 | Accuracy (%) | 96.7 |
| MMLU-by-task - High School Biology | 81.61 | Accuracy (%) | 96.4 |
| MMLU-by-task - Moral Scenarios | 54.64 | Accuracy (%) | 96.4 |
| MMLU-by-task - Elementary Mathematics | 44.44 | Accuracy (%) | 96.3 |
Interactive version: theaggregate.ai/model?slug=llama-2-70b-ensemble-v2 · How It Works · Data refreshed daily, snapshot 2026-11-08.