Llama 2 70B LoRA Assemble V2: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1433 ± 17, rank #4544 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 43 | Accuracy (%) | 99.9 |
| MMLU-by-task - High School Geography | 90.4 | Accuracy (%) | 99.9 |
| MMLU-by-task - TruthfulQA MC2 | 64.79 | Accuracy (%) | 99.7 |
| MMLU-by-task - College Computer Science | 61 | Accuracy (%) | 99.6 |
| MMLU-by-task - TruthfulQA MC1 | 46.63 | Accuracy (%) | 99.6 |
| MMLU-by-task - ARC Challenge | 68.34 | Accuracy (%) | 99.3 |
| MMLU-by-task - High School Biology | 83.23 | Accuracy (%) | 99.3 |
| MMLU-by-task - High School Microeconomics | 78.15 | Accuracy (%) | 99 |
| MMLU-by-task - Public Relations | 74.55 | Accuracy (%) | 99 |
| MMLU-by-task - Clinical Knowledge | 74.34 | Accuracy (%) | 98.9 |
| MMLU-by-task - Elementary Mathematics | 46.56 | Accuracy (%) | 98.6 |
| MMLU-by-task - Logical Fallacies | 82.21 | Accuracy (%) | 98.4 |
Interactive version: theaggregate.ai/model?slug=llama-2-70b-lora-assemble-v2 · How It Works · Data refreshed daily, snapshot 2026-11-08.