airoboros-7B-gpt4-1.4.1-qlora: benchmark results
Provider: Jon Durbin. Access: Open.
Aggregate Rating 1241 ± 16, rank #9333 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Global Facts | 36 | Accuracy (%) | 70 |
| MMLU-by-task - HellaSwag | 59.56 | Accuracy (%) | 54.9 |
| MMLU-by-task - High School Statistics | 38.43 | Accuracy (%) | 50.1 |
| MMLU-by-task - Anatomy | 43.7 | Accuracy (%) | 47.1 |
| MMLU-by-task - ARC Challenge | 48.89 | Accuracy (%) | 46.1 |
| MMLU-by-task - Miscellaneous | 58.88 | Accuracy (%) | 44.7 |
| MMLU-by-task - College Computer Science | 36 | Accuracy (%) | 44.5 |
| MMLU-by-task - High School European History | 52.73 | Accuracy (%) | 44.5 |
| MMLU-by-task - Professional Psychology | 40.2 | Accuracy (%) | 43.4 |
| MMLU-by-task - College Biology | 40.97 | Accuracy (%) | 43.2 |
| MMLU-by-task - Medical Genetics | 46 | Accuracy (%) | 43.1 |
| MMLU-by-task - Professional Medicine | 44.49 | Accuracy (%) | 42.8 |
Interactive version: theaggregate.ai/model?slug=airoboros-7b-gpt4-1-4-1-qlora · How It Works · Data refreshed daily, snapshot 2026-11-08.