dromedary-65B-lora-HF: benchmark results
TheBloke's full merged-weight Hugging Face publication reconstructed from zhiqings/dromedary-65b-lora-delta-v0 and the corresponding original Llama weights. The original delta release remains separately credited; this repository distributes the merged model rather than only delta weights. Provider: TheBloke. Access: Open.
Aggregate Rating 1387 ± 15, rank #6635 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Chemistry | 54 | Accuracy (%) | 100 |
| MMLU-by-task - Computer Security | 80 | Accuracy (%) | 99.7 |
| MMLU-by-task - Virology | 54.22 | Accuracy (%) | 96.7 |
| MMLU-by-task - Management | 82.52 | Accuracy (%) | 96.4 |
| MMLU-by-task - Formal Logic | 46.03 | Accuracy (%) | 94.1 |
| MMLU-by-task - Logical Fallacies | 79.14 | Accuracy (%) | 93.9 |
| MMLU-by-task - High School Mathematics | 33.33 | Accuracy (%) | 93.3 |
| MMLU-by-task - US Foreign Policy | 87 | Accuracy (%) | 93.2 |
| MMLU-by-task - Moral Disputes | 73.7 | Accuracy (%) | 92.9 |
| MMLU-by-task - Astronomy | 73.68 | Accuracy (%) | 92.8 |
| MMLU-by-task - High School Statistics | 53.7 | Accuracy (%) | 92.4 |
| MMLU-by-task - Human Sexuality | 76.34 | Accuracy (%) | 92.4 |
Interactive version: theaggregate.ai/model?slug=dromedary-65b-lora-hf · How It Works · Data refreshed daily, snapshot 2026-11-08.