airoboros-33B-gpt4-1.2: benchmark results
Provider: Jon Durbin. Access: Open.
Aggregate Rating 1373 ± 15, rank #7085 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 38 | Accuracy (%) | 96.5 |
| MMLU-by-task - Medical Genetics | 70 | Accuracy (%) | 95.5 |
| MMLU-by-task - World Religions | 83.63 | Accuracy (%) | 93.4 |
| MMLU-by-task - ARC Challenge | 63.23 | Accuracy (%) | 93.3 |
| MMLU-by-task - Public Relations | 70.91 | Accuracy (%) | 93.3 |
| MMLU-by-task - Elementary Mathematics | 40.48 | Accuracy (%) | 92 |
| MMLU-by-task - Anatomy | 55.56 | Accuracy (%) | 91.6 |
| MMLU-by-task - Professional Medicine | 61.03 | Accuracy (%) | 91.6 |
| MMLU-by-task - HellaSwag | 66.43 | Accuracy (%) | 91.5 |
| MMLU-by-task - Sociology | 82.59 | Accuracy (%) | 91.1 |
| MMLU-by-task - Security Studies | 70.61 | Accuracy (%) | 90.5 |
| MMLU-by-task - Moral Disputes | 70.23 | Accuracy (%) | 90.4 |
Interactive version: theaggregate.ai/model?slug=airoboros-33b-gpt4-1-2 · How It Works · Data refreshed daily, snapshot 2026-11-08.