Llama 2 7B LoRA Assemble: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1315 ± 15, rank #8450 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - TruthfulQA MC1 | 37.94 | Accuracy (%) | 91.6 |
| MMLU-by-task - TruthfulQA MC2 | 53.18 | Accuracy (%) | 89.8 |
| MMLU-by-task - Medical Genetics | 65 | Accuracy (%) | 88.5 |
| MMLU-by-task - High School European History | 70.3 | Accuracy (%) | 80.4 |
| MMLU-by-task - Abstract Algebra | 33 | Accuracy (%) | 75.6 |
| MMLU-by-task - Conceptual Physics | 44.68 | Accuracy (%) | 74.5 |
| MMLU-by-task - Electrical Engineering | 49.66 | Accuracy (%) | 73.9 |
| MMLU-by-task - High School World History | 73.42 | Accuracy (%) | 71.9 |
| MMLU-by-task - Global Facts | 36 | Accuracy (%) | 70 |
| MMLU-by-task - Security Studies | 61.22 | Accuracy (%) | 69.9 |
| MMLU-by-task - College Biology | 56.25 | Accuracy (%) | 68.2 |
| MMLU-by-task - ARC Challenge | 54.78 | Accuracy (%) | 68.1 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-lora-assemble · How It Works · Data refreshed daily, snapshot 2026-11-08.