airoboros-33B-gpt4: benchmark results
Provider: Jon Durbin. Access: Open.
Aggregate Rating 1370 ± 15, rank #7185 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Medical Genetics | 69 | Accuracy (%) | 94.3 |
| MMLU-by-task - HellaSwag | 66.29 | Accuracy (%) | 91.3 |
| MMLU-by-task - Logical Fallacies | 74.85 | Accuracy (%) | 90.9 |
| MMLU-by-task - Miscellaneous | 80.2 | Accuracy (%) | 90.8 |
| MMLU-by-task - Prehistory | 71.6 | Accuracy (%) | 90.2 |
| MMLU-by-task - Public Relations | 69.09 | Accuracy (%) | 90.2 |
| MMLU-by-task - Virology | 51.2 | Accuracy (%) | 90.1 |
| MMLU-by-task - ARC Challenge | 61.18 | Accuracy (%) | 89.9 |
| MMLU-by-task - Moral Disputes | 69.08 | Accuracy (%) | 89.8 |
| MMLU-by-task - Nutrition | 66.01 | Accuracy (%) | 89.7 |
| MMLU-by-task - Professional Law | 46.61 | Accuracy (%) | 89.5 |
| MMLU-by-task - Sociology | 80.6 | Accuracy (%) | 89.5 |
Interactive version: theaggregate.ai/model?slug=airoboros-33b-gpt4 · How It Works · Data refreshed daily, snapshot 2026-11-08.