Llama 2 70B Ensemble V8: benchmark results
Provider: Meta.
Aggregate Rating 1394 ± 18, rank #6363 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - TruthfulQA MC1 | 45.17 | Accuracy (%) | 98.9 |
| MMLU-by-task - TruthfulQA MC2 | 62.11 | Accuracy (%) | 98.2 |
| MMLU-by-task - Machine Learning | 53.57 | Accuracy (%) | 97.6 |
| MMLU-by-task - ARC Challenge | 65.61 | Accuracy (%) | 96.7 |
| MMLU-by-task - US Foreign Policy | 88 | Accuracy (%) | 94.4 |
| MMLU-by-task - Clinical Knowledge | 70.57 | Accuracy (%) | 94.1 |
| MMLU-by-task - Conceptual Physics | 62.98 | Accuracy (%) | 93.8 |
| MMLU-by-task - High School Geography | 85.35 | Accuracy (%) | 93.7 |
| MMLU-by-task - Prehistory | 76.54 | Accuracy (%) | 93.6 |
| MMLU-by-task - Human Aging | 74.44 | Accuracy (%) | 93.5 |
| MMLU-by-task - Professional Law | 52.09 | Accuracy (%) | 93.5 |
| MMLU-by-task - High School Government And Politics | 90.67 | Accuracy (%) | 93.4 |
Interactive version: theaggregate.ai/model?slug=llama-2-70b-ensemble-v8 · How It Works · Data refreshed daily, snapshot 2026-11-08.