Llama 2 70B Ensemble V3: benchmark results
Provider: Meta.
Aggregate Rating 1421 ± 21, rank #5132 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Elementary Mathematics | 48.41 | Accuracy (%) | 99.9 |
| MMLU-by-task - Clinical Knowledge | 76.23 | Accuracy (%) | 99.8 |
| MMLU-by-task - Logical Fallacies | 83.44 | Accuracy (%) | 99.4 |
| MMLU-by-task - TruthfulQA MC2 | 64.22 | Accuracy (%) | 99.4 |
| MMLU-by-task - HellaSwag | 69.37 | Accuracy (%) | 99.2 |
| MMLU-by-task - Computer Security | 79 | Accuracy (%) | 99.1 |
| MMLU-by-task - TruthfulQA MC1 | 45.53 | Accuracy (%) | 99.1 |
| MMLU-by-task - College Physics | 42.16 | Accuracy (%) | 98.8 |
| MMLU-by-task - High School European History | 84.85 | Accuracy (%) | 98.6 |
| MMLU-by-task - High School Government And Politics | 94.3 | Accuracy (%) | 98.6 |
| MMLU-by-task - Machine Learning | 56.25 | Accuracy (%) | 98.6 |
| MMLU-by-task - Professional Law | 56.45 | Accuracy (%) | 98.5 |
Interactive version: theaggregate.ai/model?slug=llama-2-70b-ensemble-v3 · How It Works · Data refreshed daily, snapshot 2026-11-08.