Llama 2 70B LoRA Assemble: benchmark results
Provider: Meta.
Aggregate Rating 1425 ± 19, rank #4899 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 44 | Accuracy (%) | 100 |
| MMLU-by-task - College Computer Science | 62 | Accuracy (%) | 99.9 |
| MMLU-by-task - TruthfulQA MC2 | 64.8 | Accuracy (%) | 99.8 |
| MMLU-by-task - ARC Challenge | 68.52 | Accuracy (%) | 99.6 |
| MMLU-by-task - Public Relations | 75.45 | Accuracy (%) | 99.6 |
| MMLU-by-task - TruthfulQA MC1 | 46.51 | Accuracy (%) | 99.4 |
| MMLU-by-task - High School Geography | 89.39 | Accuracy (%) | 99.3 |
| MMLU-by-task - High School Physics | 49.01 | Accuracy (%) | 99.3 |
| MMLU-by-task - High School Biology | 82.9 | Accuracy (%) | 99 |
| MMLU-by-task - Elementary Mathematics | 46.56 | Accuracy (%) | 98.6 |
| MMLU-by-task - Professional Medicine | 74.26 | Accuracy (%) | 98.6 |
| MMLU-by-task - Professional Law | 56.45 | Accuracy (%) | 98.5 |
Interactive version: theaggregate.ai/model?slug=llama-2-70b-lora-assemble · How It Works · Data refreshed daily, snapshot 2026-11-08.