Guanaco: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1190 ± 17, rank #9673 of 10916 rated models, from 69 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Machine Learning | 37.5 | Accuracy (%) | 71.9 |
| InstructEval - Problem Solving | 39.2 | Average (%, MMLU/BBH/DROP/CRASS/HumanEval) | 70.4 |
| MMLU-by-task - College Mathematics | 32 | Accuracy (%) | 53.7 |
| MMLU-by-task - Moral Scenarios | 25.03 | Accuracy (%) | 44.1 |
| MMLU-by-task - ARC Challenge | 46.08 | Accuracy (%) | 41.8 |
| MMLU-by-task - HellaSwag | 54.85 | Accuracy (%) | 39.7 |
| MMLU-by-task - Human Aging | 42.15 | Accuracy (%) | 38.3 |
| MMLU-by-task - Miscellaneous | 46.49 | Accuracy (%) | 38 |
| MMLU-by-task - Computer Security | 45 | Accuracy (%) | 37.5 |
| MMLU-by-task - Marketing | 49.57 | Accuracy (%) | 37.3 |
| MMLU-by-task - World Religions | 45.61 | Accuracy (%) | 36.7 |
| MMLU-by-task - Professional Psychology | 32.84 | Accuracy (%) | 36.4 |
Interactive version: theaggregate.ai/model?slug=guanaco · How It Works · Data refreshed daily, snapshot 2026-11-08.