airoboros-33B-gpt4-1.4: benchmark results
Provider: Jon Durbin. Access: Open.
Aggregate Rating 1369 ± 15, rank #7197 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 37 | Accuracy (%) | 94.5 |
| MMLU-by-task - Anatomy | 59.26 | Accuracy (%) | 94.1 |
| MMLU-by-task - Virology | 52.41 | Accuracy (%) | 92.8 |
| MMLU-by-task - HellaSwag | 65.88 | Accuracy (%) | 90.8 |
| MMLU-by-task - ARC Challenge | 61.43 | Accuracy (%) | 90.6 |
| MMLU-by-task - Moral Disputes | 70.23 | Accuracy (%) | 90.4 |
| MMLU-by-task - Jurisprudence | 76.85 | Accuracy (%) | 90.2 |
| MMLU-by-task - Sociology | 81.09 | Accuracy (%) | 90.1 |
| MMLU-by-task - Astronomy | 65.79 | Accuracy (%) | 89.7 |
| MMLU-by-task - Nutrition | 66.01 | Accuracy (%) | 89.7 |
| MMLU-by-task - International Law | 78.51 | Accuracy (%) | 89.5 |
| MMLU-by-task - High School Biology | 71.29 | Accuracy (%) | 89.3 |
Interactive version: theaggregate.ai/model?slug=airoboros-33b-gpt4-1-4 · How It Works · Data refreshed daily, snapshot 2026-11-08.