Llama 2 13B Ensemble V4: benchmark results
Provider: Meta.
Aggregate Rating 1345 ± 18, rank #7843 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Computer Security | 74 | Accuracy (%) | 92 |
| MMLU-by-task - TruthfulQA MC1 | 38.07 | Accuracy (%) | 92 |
| MMLU-by-task - US Foreign Policy | 85 | Accuracy (%) | 89.3 |
| MMLU-by-task - High School Statistics | 49.07 | Accuracy (%) | 89.2 |
| MMLU-by-task - ARC Challenge | 60.15 | Accuracy (%) | 88.5 |
| MMLU-by-task - Management | 76.7 | Accuracy (%) | 86.8 |
| MMLU-by-task - Business Ethics | 59 | Accuracy (%) | 85.8 |
| MMLU-by-task - High School Microeconomics | 60.5 | Accuracy (%) | 85.8 |
| MMLU-by-task - TruthfulQA MC2 | 51.82 | Accuracy (%) | 84.6 |
| MMLU-by-task - Conceptual Physics | 48.51 | Accuracy (%) | 84.4 |
| MMLU-by-task - Medical Genetics | 63 | Accuracy (%) | 84.2 |
| MMLU-by-task - Human Aging | 66.82 | Accuracy (%) | 84 |
Interactive version: theaggregate.ai/model?slug=llama-2-13b-ensemble-v4 · How It Works · Data refreshed daily, snapshot 2026-11-08.