guanaco-13B-HF: benchmark results
TheBloke's Hugging Face publication of Tim Dettmers' Guanaco 13B, whose original release is timdettmers/guanaco-13b. Conversion publication is credited separately from the original model creator. Provider: TheBloke. Access: Open.
Aggregate Rating 1301 ± 16, rank #8719 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - HellaSwag | 63.53 | Accuracy (%) | 83.5 |
| MMLU-by-task - Professional Medicine | 54.78 | Accuracy (%) | 78.9 |
| MMLU-by-task - College Mathematics | 35 | Accuracy (%) | 75 |
| MMLU-by-task - Formal Logic | 35.71 | Accuracy (%) | 72.7 |
| MMLU-by-task - High School Mathematics | 29.26 | Accuracy (%) | 70.6 |
| MMLU-by-task - Global Facts | 36 | Accuracy (%) | 70 |
| MMLU-by-task - US Foreign Policy | 79 | Accuracy (%) | 70 |
| MMLU-by-task - ARC Challenge | 54.86 | Accuracy (%) | 68.6 |
| MMLU-by-task - Virology | 44.58 | Accuracy (%) | 67.8 |
| MMLU-by-task - College Computer Science | 44 | Accuracy (%) | 67.6 |
| MMLU-by-task - TruthfulQA MC1 | 31.82 | Accuracy (%) | 65.9 |
| MMLU-by-task - Moral Scenarios | 28.72 | Accuracy (%) | 64.1 |
Interactive version: theaggregate.ai/model?slug=guanaco-13b-hf · How It Works · Data refreshed daily, snapshot 2026-11-08.